diff --git a/.agents/skills/diagnose/SKILL.md b/.agents/skills/diagnose/SKILL.md new file mode 100644 index 0000000..ed55bda --- /dev/null +++ b/.agents/skills/diagnose/SKILL.md @@ -0,0 +1,117 @@ +--- +name: diagnose +description: Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression. +--- + +# Diagnose + +A discipline for hard bugs. Skip phases only when explicitly justified. + +When exploring the codebase, use the project's domain glossary to get a clear mental model of the relevant modules, and check ADRs in the area you're touching. + +## Phase 1 — Build a feedback loop + +**This is the skill.** Everything else is mechanical. If you have a fast, deterministic, agent-runnable pass/fail signal for the bug, you will find the cause — bisection, hypothesis-testing, and instrumentation all just consume that signal. If you don't have one, no amount of staring at code will save you. + +Spend disproportionate effort here. **Be aggressive. Be creative. Refuse to give up.** + +### Ways to construct one — try them in roughly this order + +1. **Failing test** at whatever seam reaches the bug — unit, integration, e2e. +2. **Curl / HTTP script** against a running dev server. +3. **CLI invocation** with a fixture input, diffing stdout against a known-good snapshot. +4. **Headless browser script** (Playwright / Puppeteer) — drives the UI, asserts on DOM/console/network. +5. **Replay a captured trace.** Save a real network request / payload / event log to disk; replay it through the code path in isolation. +6. **Throwaway harness.** Spin up a minimal subset of the system (one service, mocked deps) that exercises the bug code path with a single function call. +7. **Property / fuzz loop.** If the bug is "sometimes wrong output", run 1000 random inputs and look for the failure mode. +8. **Bisection harness.** If the bug appeared between two known states (commit, dataset, version), automate "boot at state X, check, repeat" so you can `git bisect run` it. +9. **Differential loop.** Run the same input through old-version vs new-version (or two configs) and diff outputs. +10. **HITL bash script.** Last resort. If a human must click, drive _them_ with `scripts/hitl-loop.template.sh` so the loop is still structured. Captured output feeds back to you. + +Build the right feedback loop, and the bug is 90% fixed. + +### Iterate on the loop itself + +Treat the loop as a product. Once you have _a_ loop, ask: + +- Can I make it faster? (Cache setup, skip unrelated init, narrow the test scope.) +- Can I make the signal sharper? (Assert on the specific symptom, not "didn't crash".) +- Can I make it more deterministic? (Pin time, seed RNG, isolate filesystem, freeze network.) + +A 30-second flaky loop is barely better than no loop. A 2-second deterministic loop is a debugging superpower. + +### Non-deterministic bugs + +The goal is not a clean repro but a **higher reproduction rate**. Loop the trigger 100×, parallelise, add stress, narrow timing windows, inject sleeps. A 50%-flake bug is debuggable; 1% is not — keep raising the rate until it's debuggable. + +### When you genuinely cannot build a loop + +Stop and say so explicitly. List what you tried. Ask the user for: (a) access to whatever environment reproduces it, (b) a captured artifact (HAR file, log dump, core dump, screen recording with timestamps), or (c) permission to add temporary production instrumentation. Do **not** proceed to hypothesise without a loop. + +Do not proceed to Phase 2 until you have a loop you believe in. + +## Phase 2 — Reproduce + +Run the loop. Watch the bug appear. + +Confirm: + +- [ ] The loop produces the failure mode the **user** described — not a different failure that happens to be nearby. Wrong bug = wrong fix. +- [ ] The failure is reproducible across multiple runs (or, for non-deterministic bugs, reproducible at a high enough rate to debug against). +- [ ] You have captured the exact symptom (error message, wrong output, slow timing) so later phases can verify the fix actually addresses it. + +Do not proceed until you reproduce the bug. + +## Phase 3 — Hypothesise + +Generate **3–5 ranked hypotheses** before testing any of them. Single-hypothesis generation anchors on the first plausible idea. + +Each hypothesis must be **falsifiable**: state the prediction it makes. + +> Format: "If is the cause, then will make the bug disappear / will make it worse." + +If you cannot state the prediction, the hypothesis is a vibe — discard or sharpen it. + +**Show the ranked list to the user before testing.** They often have domain knowledge that re-ranks instantly ("we just deployed a change to #3"), or know hypotheses they've already ruled out. Cheap checkpoint, big time saver. Don't block on it — proceed with your ranking if the user is AFK. + +## Phase 4 — Instrument + +Each probe must map to a specific prediction from Phase 3. **Change one variable at a time.** + +Tool preference: + +1. **Debugger / REPL inspection** if the env supports it. One breakpoint beats ten logs. +2. **Targeted logs** at the boundaries that distinguish hypotheses. +3. Never "log everything and grep". + +**Tag every debug log** with a unique prefix, e.g. `[DEBUG-a4f2]`. Cleanup at the end becomes a single grep. Untagged logs survive; tagged logs die. + +**Perf branch.** For performance regressions, logs are usually wrong. Instead: establish a baseline measurement (timing harness, `performance.now()`, profiler, query plan), then bisect. Measure first, fix second. + +## Phase 5 — Fix + regression test + +Write the regression test **before the fix** — but only if there is a **correct seam** for it. + +A correct seam is one where the test exercises the **real bug pattern** as it occurs at the call site. If the only available seam is too shallow (single-caller test when the bug needs multiple callers, unit test that can't replicate the chain that triggered the bug), a regression test there gives false confidence. + +**If no correct seam exists, that itself is the finding.** Note it. The codebase architecture is preventing the bug from being locked down. Flag this for the next phase. + +If a correct seam exists: + +1. Turn the minimised repro into a failing test at that seam. +2. Watch it fail. +3. Apply the fix. +4. Watch it pass. +5. Re-run the Phase 1 feedback loop against the original (un-minimised) scenario. + +## Phase 6 — Cleanup + post-mortem + +Required before declaring done: + +- [ ] Original repro no longer reproduces (re-run the Phase 1 loop) +- [ ] Regression test passes (or absence of seam is documented) +- [ ] All `[DEBUG-...]` instrumentation removed (`grep` the prefix) +- [ ] Throwaway prototypes deleted (or moved to a clearly-marked debug location) +- [ ] The hypothesis that turned out correct is stated in the commit / PR message — so the next debugger learns + +**Then ask: what would have prevented this bug?** If the answer involves architectural change (no good test seam, tangled callers, hidden coupling) hand off to the `/improve-codebase-architecture` skill with the specifics. Make the recommendation **after** the fix is in, not before — you have more information now than when you started. diff --git a/.agents/skills/grill-with-docs/ADR-FORMAT.md b/.agents/skills/grill-with-docs/ADR-FORMAT.md new file mode 100644 index 0000000..da7e78e --- /dev/null +++ b/.agents/skills/grill-with-docs/ADR-FORMAT.md @@ -0,0 +1,47 @@ +# ADR Format + +ADRs live in `docs/adr/` and use sequential numbering: `0001-slug.md`, `0002-slug.md`, etc. + +Create the `docs/adr/` directory lazily — only when the first ADR is needed. + +## Template + +```md +# {Short title of the decision} + +{1-3 sentences: what's the context, what did we decide, and why.} +``` + +That's it. An ADR can be a single paragraph. The value is in recording *that* a decision was made and *why* — not in filling out sections. + +## Optional sections + +Only include these when they add genuine value. Most ADRs won't need them. + +- **Status** frontmatter (`proposed | accepted | deprecated | superseded by ADR-NNNN`) — useful when decisions are revisited +- **Considered Options** — only when the rejected alternatives are worth remembering +- **Consequences** — only when non-obvious downstream effects need to be called out + +## Numbering + +Scan `docs/adr/` for the highest existing number and increment by one. + +## When to offer an ADR + +All three of these must be true: + +1. **Hard to reverse** — the cost of changing your mind later is meaningful +2. **Surprising without context** — a future reader will look at the code and wonder "why on earth did they do it this way?" +3. **The result of a real trade-off** — there were genuine alternatives and you picked one for specific reasons + +If a decision is easy to reverse, skip it — you'll just reverse it. If it's not surprising, nobody will wonder why. If there was no real alternative, there's nothing to record beyond "we did the obvious thing." + +### What qualifies + +- **Architectural shape.** "We're using a monorepo." "The write model is event-sourced, the read model is projected into Postgres." +- **Integration patterns between contexts.** "Ordering and Billing communicate via domain events, not synchronous HTTP." +- **Technology choices that carry lock-in.** Database, message bus, auth provider, deployment target. Not every library — just the ones that would take a quarter to swap out. +- **Boundary and scope decisions.** "Customer data is owned by the Customer context; other contexts reference it by ID only." The explicit no-s are as valuable as the yes-s. +- **Deliberate deviations from the obvious path.** "We're using manual SQL instead of an ORM because X." Anything where a reasonable reader would assume the opposite. These stop the next engineer from "fixing" something that was deliberate. +- **Constraints not visible in the code.** "We can't use AWS because of compliance requirements." "Response times must be under 200ms because of the partner API contract." +- **Rejected alternatives when the rejection is non-obvious.** If you considered GraphQL and picked REST for subtle reasons, record it — otherwise someone will suggest GraphQL again in six months. diff --git a/.agents/skills/grill-with-docs/CONTEXT-FORMAT.md b/.agents/skills/grill-with-docs/CONTEXT-FORMAT.md new file mode 100644 index 0000000..ddfa247 --- /dev/null +++ b/.agents/skills/grill-with-docs/CONTEXT-FORMAT.md @@ -0,0 +1,77 @@ +# CONTEXT.md Format + +## Structure + +```md +# {Context Name} + +{One or two sentence description of what this context is and why it exists.} + +## Language + +**Order**: +{A concise description of the term} +_Avoid_: Purchase, transaction + +**Invoice**: +A request for payment sent to a customer after delivery. +_Avoid_: Bill, payment request + +**Customer**: +A person or organization that places orders. +_Avoid_: Client, buyer, account + +## Relationships + +- An **Order** produces one or more **Invoices** +- An **Invoice** belongs to exactly one **Customer** + +## Example dialogue + +> **Dev:** "When a **Customer** places an **Order**, do we create the **Invoice** immediately?" +> **Domain expert:** "No — an **Invoice** is only generated once a **Fulfillment** is confirmed." + +## Flagged ambiguities + +- "account" was used to mean both **Customer** and **User** — resolved: these are distinct concepts. +``` + +## Rules + +- **Be opinionated.** When multiple words exist for the same concept, pick the best one and list the others as aliases to avoid. +- **Flag conflicts explicitly.** If a term is used ambiguously, call it out in "Flagged ambiguities" with a clear resolution. +- **Keep definitions tight.** One sentence max. Define what it IS, not what it does. +- **Show relationships.** Use bold term names and express cardinality where obvious. +- **Only include terms specific to this project's context.** General programming concepts (timeouts, error types, utility patterns) don't belong even if the project uses them extensively. Before adding a term, ask: is this a concept unique to this context, or a general programming concept? Only the former belongs. +- **Group terms under subheadings** when natural clusters emerge. If all terms belong to a single cohesive area, a flat list is fine. +- **Write an example dialogue.** A conversation between a dev and a domain expert that demonstrates how the terms interact naturally and clarifies boundaries between related concepts. + +## Single vs multi-context repos + +**Single context (most repos):** One `CONTEXT.md` at the repo root. + +**Multiple contexts:** A `CONTEXT-MAP.md` at the repo root lists the contexts, where they live, and how they relate to each other: + +```md +# Context Map + +## Contexts + +- [Ordering](./src/ordering/CONTEXT.md) — receives and tracks customer orders +- [Billing](./src/billing/CONTEXT.md) — generates invoices and processes payments +- [Fulfillment](./src/fulfillment/CONTEXT.md) — manages warehouse picking and shipping + +## Relationships + +- **Ordering → Fulfillment**: Ordering emits `OrderPlaced` events; Fulfillment consumes them to start picking +- **Fulfillment → Billing**: Fulfillment emits `ShipmentDispatched` events; Billing consumes them to generate invoices +- **Ordering ↔ Billing**: Shared types for `CustomerId` and `Money` +``` + +The skill infers which structure applies: + +- If `CONTEXT-MAP.md` exists, read it to find contexts +- If only a root `CONTEXT.md` exists, single context +- If neither exists, create a root `CONTEXT.md` lazily when the first term is resolved + +When multiple contexts exist, infer which one the current topic relates to. If unclear, ask. diff --git a/.agents/skills/grill-with-docs/SKILL.md b/.agents/skills/grill-with-docs/SKILL.md new file mode 100644 index 0000000..5ea0aa9 --- /dev/null +++ b/.agents/skills/grill-with-docs/SKILL.md @@ -0,0 +1,88 @@ +--- +name: grill-with-docs +description: Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions. +--- + + + +Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer. + +Ask the questions one at a time, waiting for feedback on each question before continuing. + +If a question can be answered by exploring the codebase, explore the codebase instead. + + + + + +## Domain awareness + +During codebase exploration, also look for existing documentation: + +### File structure + +Most repos have a single context: + +``` +/ +├── CONTEXT.md +├── docs/ +│ └── adr/ +│ ├── 0001-event-sourced-orders.md +│ └── 0002-postgres-for-write-model.md +└── src/ +``` + +If a `CONTEXT-MAP.md` exists at the root, the repo has multiple contexts. The map points to where each one lives: + +``` +/ +├── CONTEXT-MAP.md +├── docs/ +│ └── adr/ ← system-wide decisions +├── src/ +│ ├── ordering/ +│ │ ├── CONTEXT.md +│ │ └── docs/adr/ ← context-specific decisions +│ └── billing/ +│ ├── CONTEXT.md +│ └── docs/adr/ +``` + +Create files lazily — only when you have something to write. If no `CONTEXT.md` exists, create one when the first term is resolved. If no `docs/adr/` exists, create it when the first ADR is needed. + +## During the session + +### Challenge against the glossary + +When the user uses a term that conflicts with the existing language in `CONTEXT.md`, call it out immediately. "Your glossary defines 'cancellation' as X, but you seem to mean Y — which is it?" + +### Sharpen fuzzy language + +When the user uses vague or overloaded terms, propose a precise canonical term. "You're saying 'account' — do you mean the Customer or the User? Those are different things." + +### Discuss concrete scenarios + +When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about the boundaries between concepts. + +### Cross-reference with code + +When the user states how something works, check whether the code agrees. If you find a contradiction, surface it: "Your code cancels entire Orders, but you just said partial cancellation is possible — which is right?" + +### Update CONTEXT.md inline + +When a term is resolved, update `CONTEXT.md` right there. Don't batch these up — capture them as they happen. Use the format in [CONTEXT-FORMAT.md](./CONTEXT-FORMAT.md). + +`CONTEXT.md` should be totally devoid of implementation details. Do not treat `CONTEXT.md` as a spec, a scratch pad, or a repository for implementation decisions. It is a glossary and nothing else. + +### Offer ADRs sparingly + +Only offer to create an ADR when all three are true: + +1. **Hard to reverse** — the cost of changing your mind later is meaningful +2. **Surprising without context** — a future reader will wonder "why did they do it this way?" +3. **The result of a real trade-off** — there were genuine alternatives and you picked one for specific reasons + +If any of the three is missing, skip the ADR. Use the format in [ADR-FORMAT.md](./ADR-FORMAT.md). + + diff --git a/.agents/skills/sm-flow/SKILL.md b/.agents/skills/sm-flow/SKILL.md new file mode 100644 index 0000000..2e79191 --- /dev/null +++ b/.agents/skills/sm-flow/SKILL.md @@ -0,0 +1,107 @@ +--- +name: sm-flow +description: OpenSpec-first 工程流程 harness。仅在用户显式调用 /sm-flow、/sm-flow explore、/sm-flow apply、/sm-flow archive,或明确要求使用 sm-flow 流程时使用;不要根据需求类型自动触发。 +--- + +# SM Flow + +SM Flow 是一个**协议层 harness**——编排 OpenSpec 的完整生命周期。它通过阶段、门控、人类对齐和长期记忆,约束 agent 以正确的顺序、条件和标准使用 OpenSpec。 + +sm-flow 会自动维护 `devflow/` 目录作为项目长期记忆。用户不需要手动管理它,sm-flow 会在流程中自动读取和回填。 + +## 触发规则 + +只在用户显式调用时使用 sm-flow: + +- 用户输入 `/sm-flow`、`/sm-flow explore`、`/sm-flow apply`、`/sm-flow archive`。 +- 用户用自然语言明确要求"使用 sm-flow"、"走 sm-flow 流程"或等价表达。 + +不要根据需求类型自动触发 sm-flow。即使任务涉及 OpenSpec、跨模块、接口契约、需求澄清或 devflow 归档,只要用户没有显式要求 sm-flow,就按普通工程任务处理。 + +## 四层架构 + +``` +sm-flow → 编排层(harness):阶段、门控、产物约束、人类对齐 + OpenSpec → 执行引擎:propose/apply/archive 的能力提供方 + devflow/ → 记忆层:为编排层提供上下文,接收执行结果的回填 + code → 实现结果:apply 的产出 +``` + +- OpenSpec 是唯一执行真理源:apply 阶段只能基于 OpenSpec 执行,不能绕过 OpenSpec 直接写代码。 +- devflow 是上下文真理源:术语、历史决策、验收记录来自 devflow,用于增强 OpenSpec,不替代 OpenSpec。 +- 如果 devflow 和 OpenSpec 冲突,先汇报冲突、让用户确认、修正 OpenSpec,再继续执行。 +- propose 阶段产出的 OpenSpec 默认为 **Draft OpenSpec**:它是澄清和审计对象,不是 apply 的执行许可。 +- 只有通过 commit 检查后的 OpenSpec 才是 **Committed OpenSpec**;apply 只能执行 Committed OpenSpec。 + +## 核心规则 + +以下 6 条是硬约束,违反即流程失败。其余约束按阶段定义在 `references/phase-contracts.md`。 + +1. **OpenSpec 是唯一执行真理源**。apply 阶段必须读取 Committed OpenSpec 文件作为执行依据;对话中的描述不等于产物。Draft OpenSpec 是讨论对象,不是执行许可。 +2. **不得跳过 context**。生成 OpenSpec 前,必须先读取相关 devflow 上下文(glossary、ADR、历史项目)。 +3. **不得跳过 grill**。必须按 `references/scales.md` 的当前分档要求完成澄清或验证。 +4. **不得跳过 commit**。进入 apply 前,Draft OpenSpec 必须通过 commit 检查成为 Committed OpenSpec。 +5. **冲突必须先分类再处理**。OpenSpec 不准(规格遗漏)→ 修正 OpenSpec;代码偏离(实现偏差)→ 修正代码;不确定或涉及设计方向 → 暂停并等待用户确认。 +6. **能力来源必须显式声明**。每个阶段先声明使用外部子 skill / OpenSpec CLI / sm-flow 内置协议;外部能力不可用时可使用 `references/fallbacks.md` 的内置协议,但必须标注为 fallback。若外部能力和内置协议都不可用,流程失败。 + +每个阶段的过程约束(question pool、one-at-a-time、cross-artifact 对齐、冲突回写等)和质量约束(可观测产出要求)见 `references/phase-contracts.md` 中对应阶段的退出条件和 checkpoint。 + +## 用户命令 + +| 命令 | 用户意图 | harness 内部行为 | +|---|---|---| +| `/sm-flow` | 完整流程 | clarify → context → propose → grill → specify → audit → commit → apply → archive | +| `/sm-flow explore` | 先想想 | 带上下文的探索模式 | +| `/sm-flow apply` | 只执行 | 检查 commit gate → apply | +| `/sm-flow archive` | 收尾 | 回填 devflow + 归档确认 | + +用户也可以用自然语言指定从某个阶段继续,例如"ops-message-support 的 grill 已经做完了,继续"。harness 识别意图后,自动补做最小前置检查,然后从指定阶段继续。 + +## 可见 Checkpoint + +内部阶段不是用户 API。对用户汇报进度时,默认只暴露 4 个 checkpoint: + +| Checkpoint | 覆盖内部阶段 | 用户可见含义 | +|---|---|---| +| Discover | clarify + context + propose + grill | 澄清目标、读取 devflow、形成轻量 proposal、解决关键问题 | +| Commit | specify + audit + commit | 补全 OpenSpec、做架构/产物对齐、生成 Committed OpenSpec | +| Apply | apply | 基于 Committed OpenSpec 实现和验证 | +| Archive | archive | 回填 devflow、汇报验收、询问是否归档 OpenSpec | + +除非用户要求看细节,进度汇报、暂停点和恢复提示应使用 checkpoint 名称,而不是逐个暴露 9 个内部阶段。内部阶段仍按顺序执行,并以 `references/phase-contracts.md` 为准。 + +## 首次加载 + +执行前只读取当前任务需要的 reference 文件: + +- 需要执行阶段时,先读取 `references/phase-contracts.md`;如果当前阶段涉及接口影响分级、分档、启动规则、快速模式或完成标准,再补读 `references/operating-rules.md`;如果外部 OpenSpec 能力或子 skill 不可用,再补读 `references/fallbacks.md`。 +- 判断或执行 `micro / standard / complex` 分档时,读取 `references/scales.md`;其它文件不得重复定义分档细节。 +- 当 checkpoint / gate / fallback / Draft / Committed 等术语含义不清,或需要统一对用户说明时,读取 `references/glossary.md`。 +- 创建或更新 PRD、ADR、验收报告、词汇表、复合知识文档时,读取 `references/templates.md`。 +- archive 阶段或需要从 OpenSpec 提取产物时,读取 `references/archive-rules.md`。 + +## 内部阶段 + +9 个内部阶段,按执行顺序: + +1. clarify — 入口澄清:接收初始需求,澄清到可生成轻量 proposal。 +2. context — 上下文收集:读取 devflow 的 glossary、ADR、历史项目、compound knowledge。 +3. propose — 轻量 propose:只生成 proposal.md,不调用 openspec-propose。 +4. grill — 人类对齐澄清:evidence-driven 查证 + user-interview one-at-a-time,回写 proposal。 +5. specify — 细化 + 对齐:基于已稳定的 proposal 补全 design/specs/tasks,做 cross-artifact 对齐。 +6. audit — 架构审计:审计结果如果影响实现,回写 OpenSpec design/tasks。 +7. commit — Commit OpenSpec:检查 Draft OpenSpec 是否达到可执行状态,提交为 Committed OpenSpec。 +8. apply — OpenSpec 执行:基于 Committed OpenSpec 实现代码。 +9. archive — 回填 + 归档:从 OpenSpec 产物和 decisions.md 提炼长期档案,询问是否归档。 + +每个阶段的进入条件、动作、输出和退出标准见 `references/phase-contracts.md`。 + +关键阶段的完成判断也以 `references/phase-contracts.md` 为准;如果缺少显式 checkpoint 或能力来源声明,该阶段不得视为已完成。 + +## 快速模式 + +快速模式的具体约束见 `references/operating-rules.md`。 + +## 完成标准 + +流程完成标准见 `references/operating-rules.md`。 diff --git a/.agents/skills/sm-flow/references/archive-rules.md b/.agents/skills/sm-flow/references/archive-rules.md new file mode 100644 index 0000000..49b65b7 --- /dev/null +++ b/.agents/skills/sm-flow/references/archive-rules.md @@ -0,0 +1,167 @@ +# 归档规则 + +archive 阶段的目标是把 OpenSpec 产物、实现结果和过程日志转化为持久、可读、可复用的项目记忆。sm-flow 在 clarify → apply 期间只维护 `decisions.md` 作为过程日志,archive 阶段从中提取完整 devflow 档案。 + +## Archive 强制执行顺序 + +Archive 阶段必须按以下顺序执行,不得跳过或重排: + +### Step 1: 创建 devflow 档案(必需) + +- [ ] 创建 `devflow/projects/YYYY-MM-DD-{slug}/brief.md` + (从 proposal.md 提取:背景、目标、范围、非目标) + +- [ ] 按 `references/scales.md` 的当前分档决定是否创建 `devflow/projects/YYYY-MM-DD-{slug}/evidence.md` + (创建时从 decisions.md 提取 evidence-driven 记录) + +- [ ] 创建 `devflow/projects/YYYY-MM-DD-{slug}/decisions.md` + (整理为最终版:关键决策、权衡、风险) + +- [ ] 创建 `devflow/projects/YYYY-MM-DD-{slug}/acceptance.md` + (记录:静态验证、脚本验证、浏览器/人工验证、未验证) + +### Step 2: 更新索引(必需) + +- [ ] 在 `devflow/index.md` 末尾追加或更新一行: + `| YYYY-MM-DD | slug | 领域 | 关键词 | openspec/changes/xxx | {status} |` + +### Step 3: 标记 OpenSpec(必需) + +- [ ] 创建 `openspec/changes/{slug}/.archive-ready` 文件 + +### Step 4: 向用户汇报(必需) + +- [ ] 列出创建的 devflow 档案文件路径(验证文件实际存在于磁盘) +- [ ] 汇报验证情况(按静态验证、脚本验证、浏览器/人工验证、未验证分类) +- [ ] 列出剩余风险或后续事项 +- [ ] 询问:**是否现在归档 OpenSpec?** + +### Step 5: 用户确认后执行 OpenSpec Archive(可选) + +- [ ] 调用 `openspec-archive-change` +- [ ] 记录 archive 结果 + +**自检**:在执行 Step 4 前,检查 Step 1-3 是否都完成。 + +--- + +## 目录规则 + +项目档案路径: + +```text +devflow/projects/YYYY-MM-DD-{slug}/ +``` + +archive 阶段按 `references/scales.md` 的当前分档创建以下文件: + +- `brief.md`:从 proposal.md 提取背景、目标、范围、非目标。 +- `evidence.md`:从 decisions.md 中的 evidence-driven 记录提取;是否独立创建按 `references/scales.md` 执行。 +- `decisions.md`:保持为最终版,整理格式。 +- `acceptance.md`:从实现结果和验证结果提取。 + +同时维护仓库级索引: + +- `devflow/index.md` + +按需创建以下扩展文件: + +- `prd.md` +- `research.md` +- `design.md` +- `tasks.md` +- `alignment.md` +- `adr/*.md` + +不要逐字复制完整 OpenSpec 文件,也不要重复 OpenSpec 的 proposal/design/tasks。应提炼 OpenSpec 如何指导执行:背景、证据、用户决策、任务状态、假设、验证结果、风险,以及执行中对 OpenSpec 的修正。 + +## 产物分档 + +分档的适用场景和必须文件见 `references/scales.md`。本文件只定义 archive 阶段的创建顺序、提取映射和索引规则。 + +## 提取映射 + +| 来源 | 提取内容 | 写入位置 | +| --- | --- | --- | +| `decisions.md`(过程日志) | question pool、evidence-driven 汇报状态、user-interview 确认状态、关键取舍 | `decisions.md`(整理格式为最终版) | +| `decisions.md`(过程日志) | evidence-driven 结论、代码/文档证据 | `evidence.md` | +| `proposal.md` | 为什么做、做什么、范围、非目标 | `brief.md` | +| `design.md` | 技术方案、关键决策、风险;只提炼长期有用内容 | `evidence.md` / 按需 `design.md` | +| `specs/**/*.md` | requirement 标题和 scenario 意图 | `brief.md` 或 `acceptance.md` 的验收追踪 | +| `tasks.md` | checkbox 状态、剩余工作、执行切片 | `acceptance.md`;复杂项目可拆 `tasks.md` | +| 测试/构建输出 | 验证命令、结果、验证类型 | `acceptance.md` | +| diagnose 记录 | 根因、修复、回归验证 | `acceptance.md` | +| 词汇表更新 | 术语和业务规则 | `devflow/glossary/CONTEXT.md` | +| 可复用经验 | 持久工程知识 | `devflow/compound/YYYY-MM-DD-{type}-{slug}.md` | +| 项目索引 | 日期、slug、领域、关键词、关联 OpenSpec、状态 | `devflow/index.md` | + +## 索引维护规则 + +`devflow/index.md` 是 context 阶段的默认入口,archive 阶段回填时必须维护。 + +最小字段: + +| 日期 | slug | 领域 | 关键词 | 关联 OpenSpec | 状态 | +| --- | --- | --- | --- | --- | --- | + +规则: + +- 每个 `devflow/projects/YYYY-MM-DD-{slug}/` 默认对应一行索引。 +- archive 阶段新建或更新项目档案时,必须新增或更新对应行。 +- 如果项目仍在进行,状态写 `active`;已验收但未 archive 写 `accepted-unarchived`;已 archive 写 `archived`;暂停写 `paused`。 +- 关键词只放能帮助 context 阶段定位的术语,不复制 brief 内容。 +- 如果无法准确判断领域或状态,写 `unknown`,并在 `acceptance.md` 记录待补。 + +## 验收记录规则 + +必须真实记录验证情况,并按类型分类: + +- **静态验证**:语法检查、grep/rg 检查、结构检查、类型检查等不运行完整功能的验证。 +- **脚本验证**:生成脚本、测试命令、构建命令、自动化检查等可重复命令。 +- **浏览器/人工验证**:需要用户或代理在界面中点击、观察、确认的行为验证。 +- **未验证**:未运行的验证必须记录原因、风险和建议补验步骤。 + +记录要求: + +- 如果验证通过,记录命令/步骤和覆盖范围。 +- 如果验证失败,记录失败摘要和是否阻塞验收。 +- 如果需要人工验证,列出明确步骤,不要用"手动测试一下"这种模糊描述。 + +## ADR 规则 + +同时满足以下条件时创建 ADR: + +1. 决策难以逆转。 +2. 缺少上下文会让未来维护者困惑。 +3. 决策来自真实权衡,而不是简单偏好。 + +项目内 ADR 存放于: + +```text +devflow/projects/YYYY-MM-DD-{slug}/adr/ +``` + +跨项目可复用决策或经验存放于: + +```text +devflow/compound/YYYY-MM-DD-decision-{slug}.md +``` + +## 归档确认 + +OpenSpec archive 是显式 human-in-the-loop 动作。archive 前必须确认 devflow 已经回填 OpenSpec 的关键执行信息: + +- archive 阶段可以建议 archive,但必须先询问用户。 +- 在用户确认前,不要执行 archive。 +- 如果用户暂不归档,在 acceptance 中记录原因或状态。 +- 如果用户确认归档,执行后记录 archive 结果和剩余档案位置。 + +## 归档交接 + +archive 阶段结束时告诉用户: + +- 创建或更新了哪些档案文件。 +- `devflow/index.md` 是否已更新。 +- 运行了哪些验证,并按静态验证、脚本验证、浏览器/人工验证、未验证分类。 +- 还剩哪些风险或后续事项。 +- 明确询问:是否现在 archive OpenSpec change? diff --git a/.agents/skills/sm-flow/references/fallbacks.md b/.agents/skills/sm-flow/references/fallbacks.md new file mode 100644 index 0000000..63c5e89 --- /dev/null +++ b/.agents/skills/sm-flow/references/fallbacks.md @@ -0,0 +1,49 @@ +# 内置执行协议 + +本文件只在外部 OpenSpec CLI 或子 skill 不可用时使用。fallback 不是跳过阶段,而是由 sm-flow 用文件方式完成同等最小产物。每次使用 fallback 都必须写入 `decisions.md` 或 `acceptance.md`,说明能力来源、缺失能力、影响和剩余风险。 + +## 通用规则 + +- 优先使用外部能力;只有不可用、不可发现或无法在当前环境调用时才使用内置协议。 +- 不得因为使用 fallback 跳过 context、grill、commit、apply 授权或 archive 确认。 +- fallback 产物仍写入 `openspec/changes/{slug}/` 和 `devflow/projects/YYYY-MM-DD-{slug}/`。 +- 如果内置协议也无法满足阶段退出条件,暂停并向用户说明阻塞项。 + +## grill 内置协议 + +- 建立 question pool,至少覆盖术语、边界、验收;涉及参考实现或项目基础设施时加入技术实现问题。 +- 将问题标记为 `evidence-driven` 或 `user-interview`。 +- 先查证 evidence-driven 问题并汇报结论,再逐个询问 user-interview 问题。 +- 按 `references/scales.md` 的当前分档满足 grill 要求。 +- 将 question pool、证据结论、用户原话和确认状态写入 `decisions.md`;影响实现的结论回写 `proposal.md`。 + +## openspec 提案内置协议 + +- 在 `openspec/changes/{slug}/` 创建或更新: + - `proposal.md`:问题、方案、范围、非目标、上下文约束、风险。 + - 设计产物:实现设计、接口影响、关键决策、架构风险;形式按 `references/scales.md` 的当前分档要求执行。 + - `specs/*/spec.md` 或等价 functional spec:描述用户可观察行为和验收场景。 + - `tasks.md`:按可执行切片拆分任务,并给每项写可验证验收标准。 +- 运行 cross-artifact 对齐检查:proposal → 设计产物 → specs → tasks。 +- 如果发现 gap,先修正 OpenSpec,再进入 commit。 + +## audit 内置协议 + +- 用 5 句话以内说明模块链路、数据所有权、跨模块依赖、架构风险和是否需要回写 OpenSpec。 +- 如果风险影响实现,修正设计产物或 `tasks.md`。 +- 将结论写入 `decisions.md`。 + +## openspec apply 内置协议 + +- 只依据 Committed OpenSpec 的 specs/tasks 实现;devflow 只作上下文参考。 +- 开始前检查 `.committed` 文件;缺失则返回 commit。 +- 如触发 pre-apply checkpoint,先阅读参考实现、grep 项目基础设施模式,并把技术栈清单写入 `decisions.md`。 +- 按 tasks 的纵向切片实现、验证并更新任务状态。 +- 发现冲突时按三类处理:OpenSpec 不准则修 OpenSpec,代码偏离则修代码,不确定则暂停等用户确认。 + +## openspec archive 内置协议 + +- 不删除或移动 OpenSpec change;只标记归档准备状态。 +- 完成 devflow 回填、更新 `devflow/index.md`、创建 `.archive-ready`。 +- 向用户汇报已创建文件、验证分类、剩余风险,并询问是否需要真实 OpenSpec archive。 +- 如果外部 archive 能力仍不可用,在 `acceptance.md` 标记 `accepted-unarchived`。 diff --git a/.agents/skills/sm-flow/references/glossary.md b/.agents/skills/sm-flow/references/glossary.md new file mode 100644 index 0000000..9528b40 --- /dev/null +++ b/.agents/skills/sm-flow/references/glossary.md @@ -0,0 +1,21 @@ +# 术语表 + +本文件统一 sm-flow 协议中的核心词。优先使用这些词,避免同一概念多种说法。 + +| 术语 | 含义 | 使用边界 | +| --- | --- | --- | +| sm-flow | 协议层 harness | 编排 OpenSpec 生命周期,不替代 OpenSpec | +| OpenSpec | 当前变更的执行真理源 | apply 只能依据 Committed OpenSpec | +| devflow | 长期记忆和上下文层 | 提供术语、历史决策、验收记录,不直接指挥实现 | +| checkpoint | 用户可见检查点 | 默认只暴露 Discover / Commit / Apply / Archive | +| gate | 硬门控 | 不满足就不能进入下一关键动作,如 commit gate | +| Draft OpenSpec | 讨论和审计对象 | propose/specify 期间产生,不能直接 apply | +| Committed OpenSpec | 已通过 commit gate 的 OpenSpec | apply 的唯一执行依据 | +| fallback | 内置执行协议 | 外部 OpenSpec CLI 或子 skill 不可用时使用,必须标注 | +| decisions.md | 过程日志 | clarify 到 apply 期间记录问题、证据、决策、冲突和回写 | +| .committed | commit gate 标记文件 | 存在才可进入合规 apply | +| .archive-ready | archive 准备标记文件 | 表示 devflow 已回填,等待用户确认是否 archive | +| Discover | 用户可见 checkpoint | 覆盖 clarify + context + propose + grill | +| Commit | 用户可见 checkpoint | 覆盖 specify + audit + commit | +| Apply | 用户可见 checkpoint | 覆盖 apply | +| Archive | 用户可见 checkpoint | 覆盖 archive | diff --git a/.agents/skills/sm-flow/references/operating-rules.md b/.agents/skills/sm-flow/references/operating-rules.md new file mode 100644 index 0000000..5ce2558 --- /dev/null +++ b/.agents/skills/sm-flow/references/operating-rules.md @@ -0,0 +1,120 @@ +# 运行规则 + +本文件承载稳定但不必放在顶层 `SKILL.md` 的运行规则。 + +## 接口影响分级 + +接口影响分级判断的是"记录在哪里、是否需要独立文档",不是判断"是否需要关注"。凡涉及字段、DTO、service 方法、API、事件、回调、数据库契约、命令契约、跨模块调用语义或内部决策逻辑变化,都必须先做分级。 + +| 级别 | 判断条件 | 产物要求 | +| --- | --- | --- | +| L1 内部实现 | 不改变任何调用方可观察的接口、字段、状态、错误码、数据范围、排序、过滤、权限结果、状态流转、副作用或文档承诺 | 不需要接口影响文档,只在 OpenSpec tasks 或 acceptance 记录验证 | +| L2 内部接口 | 改 DTO、service 方法、内部事件、内部 RPC 或内部判断逻辑,且所有消费者都在同一实现范围内 | 必须记录接口影响范围,可内联到 OpenSpec design/specs/tasks 或 devflow evidence/decisions | +| L3 协作接口 | 影响其他模块、其他服务、前端、外部系统、跨团队消费者、数据库契约、消息事件、回调或 SDK | 必须产出独立接口文档或等价独立章节 | +| L4 破坏性接口 | 删除字段、改字段语义、改状态机、改错误码、破坏兼容、旧调用方可能失败,或需要迁移、灰度、回滚 | 独立接口文档 + 迁移/回滚说明;必要时创建 ADR | + +判断策略: + +- 如果只是修复 bug,让接口回到原 OpenSpec 或原文档承诺,通常是 L1/L2。 +- 如果判断逻辑改变了返回数据、错误码、状态、权限结果、排序/过滤、幂等性、时序或副作用,至少按 L3 检查。 +- 如果旧调用方不改代码会失败、少数据、多数据、状态不同或错误码不同,按 L4 处理。 +- 如果无法确定调用方边界或兼容性,默认提高一级并作为 `user-interview` 问题等待确认。 + +## 启动检查 + +1. 识别用户命令意图: + - `/sm-flow`(无参数):完整流程,从 clarify 开始。 + - `/sm-flow apply [change]`:只执行,检查 commit gate → apply。 + - `/sm-flow explore`:带上下文的探索模式,不走标准阶段链。 + - `/sm-flow archive [change]`:收尾,回填 devflow + 归档确认。 + - 明确要求"使用 sm-flow"或"走 sm-flow 流程":按显式调用处理。 + - 自然语言指定阶段继续:识别意图后,自动补做最小前置检查,然后从指定阶段继续。 +2. 判断启动模式: + - 完整模式:用户提供粗略想法或初始 PRD。 + - Research 模式:用户已有 research,需要转成或修正 OpenSpec。 + - PRD 文件模式:用户提供已有 PRD 路径。 + - 恢复模式:用户希望从某个阶段继续(补做最小前置检查)。 + - 快速模式:小改动,合并 gate;具体分档规则见 `references/scales.md`。 +3. 如果缺少 `devflow/`,初始化: + - `devflow/projects/` + - `devflow/glossary/CONTEXT.md` + - `devflow/compound/` +4. 如果根目录存在旧 `CONTEXT.md`,且 `devflow/glossary/CONTEXT.md` 不存在或为空,询问用户是迁移还是合并。 +5. 检查 OpenSpec 和子 skill 是否可用: + - OpenSpec 能力:`openspec-propose`、`openspec-apply-change`、`openspec-archive-change`。 + - 辅助能力:`to-prd`、`grill-with-docs`、`diagnose`、`tdd`、`zoom-out`。 +6. 如果 OpenSpec 或子 skill 不可用,不要静默跳过;使用内置执行协议(见 `references/fallbacks.md`),并在当前 checkpoint 说明 fallback 来源、影响和剩余风险。 + +## 进度汇报 + +用户可见进度默认折叠为 4 个 checkpoint: + +| Checkpoint | 内部阶段 | +| --- | --- | +| Discover | clarify + context + propose + grill | +| Commit | specify + audit + commit | +| Apply | apply | +| Archive | archive | + +汇报规则: + +- 面向用户时优先使用 checkpoint 名称,不逐个汇报 9 个内部阶段。 +- 内部阶段只在 checkpoint 摘要中作为证据列出,例如"Discover 已完成:读取了 devflow、生成 proposal、解决 2 个问题"。 +- 只有发生阻塞、冲突、fallback、用户要求继续某个内部阶段,或需要解释恢复位置时,才暴露内部阶段名。 +- 当前分档的汇报压缩规则见 `references/scales.md`;无论分档如何,都不要把内部阶段名当作用户操作入口。 + +## 项目标识规则 + +- 整个流程使用同一个 slug。 +- 优先使用 OpenSpec change name。 +- 如果还没有,则从功能标题生成 kebab-case slug。 +- 项目档案目录格式:`devflow/projects/YYYY-MM-DD-{slug}/`。 +- 如果目录已存在,默认恢复该项目;除非用户明确要求新开一轮。 + +## Devflow 产物分层 + +Devflow 是 sm-flow 自动维护的项目长期记忆层,不复制 OpenSpec 的执行产物。 + +**过程日志**(clarify → apply 期间维护): + +- `decisions.md`:question pool、evidence-driven 汇报状态、user-interview 确认状态、关键取舍、风险接受、OpenSpec 回写记录、冲突分类记录。 + +**最终档案**(archive 阶段从 decisions.md + OpenSpec 产物提取): + +- `brief.md`:背景、目标、范围、非目标、分档、关联 OpenSpec change。 +- `evidence.md`:代码/文档证据、历史决策、evidence-driven 结论和汇报状态;分档要求见 `references/scales.md` 和 `references/archive-rules.md`。 +- `acceptance.md`:实现结果、验证命令、未验证项、归档状态、后续事项。 + +**按需产物**(archive 阶段按需创建): + +- `prd.md`:需求复杂、用户明确要求、或需要对外协作。 +- `research.md`:存在真实调研、代码考古、竞品/API 对比或复杂方案比较。 +- `design.md`:不适合放进 OpenSpec design 的长期背景或架构审计摘要。 +- `tasks.md`:跨会话的人类追踪;执行任务仍属于 OpenSpec。 +- `alignment.md` / `clarifications.md`:仅在 gap 或澄清很多时使用。 +- `adr/*.md` 和 `compound/*.md`:仅在满足 ADR / compound knowledge 规则时使用。 + +**规模分档**:`micro / standard / complex` 的唯一规则源是 `references/scales.md`。 + +## 快速模式 + +快速模式适用于 `references/scales.md` 定义的 micro 变更。它合并 gate 而不仅仅是压缩产物;具体覆盖规则见 `references/scales.md`。 + +无论什么模式,以下内容必须保留: + +- context 最小上下文收集:至少检查 glossary 和相关 ADR。 +- grill 最小澄清:按 `references/scales.md` 当前分档要求执行;evidence-driven 结论仍需汇报。 +- commit gate:确认没有未解决用户问题、接口影响已记录、OpenSpec tasks/specs 可执行;完整性检查按 `references/scales.md` 当前分档要求执行。 +- apply 仍由 OpenSpec tasks/specs 驱动执行。 +- archive 轻量回填:记录验收结果、OpenSpec 链接和归档状态。 + +## 完成标准 + +只有同时满足以下条件,流程才算完成: + +- 用户可见的 Discover、Commit、Apply、Archive checkpoint 已完成,或未完成项已明确标记为暂停/不适用。 +- OpenSpec proposal、设计产物、specs、tasks 已按当前分档生成或更新到可执行状态。 +- 实现或规划工作已完成,且执行依据来自 OpenSpec。 +- 已运行验证,或已记录未运行验证的原因。 +- `devflow/projects/YYYY-MM-DD-{slug}/` 包含 `references/scales.md` 和 `references/archive-rules.md` 要求的当前分档档案。 +- 用户知道剩余风险与下一步,并已被询问是否归档 OpenSpec change。 diff --git a/.agents/skills/sm-flow/references/phase-contracts.md b/.agents/skills/sm-flow/references/phase-contracts.md new file mode 100644 index 0000000..423de8e --- /dev/null +++ b/.agents/skills/sm-flow/references/phase-contracts.md @@ -0,0 +1,352 @@ +# 阶段契约 + +本文件是 SM Flow 的逐阶段执行准则。核心原则:**sm-flow 编排 OpenSpec,OpenSpec 指挥执行,执行结果回填 devflow**。 + +执行顺序:clarify → context → propose → grill → specify → audit → commit → apply → archive。 + +## 目录 + +- clarify — 入口澄清 +- context — 上下文收集 +- propose — 轻量 propose +- grill — 人类对齐澄清 +- specify — 细化 + 对齐 +- audit — 架构审计 +- commit — Commit OpenSpec +- apply — OpenSpec 执行 +- archive — 回填 + 归档 + +## clarify — 入口澄清 + +**进入条件**:用户提供粗略想法、初始 PRD、已有 research、issue,或要求启动 SM Flow。 + +**动作**: +- 收集问题、期望结果、目标用户、涉及代码区域、约束条件和可能的非目标。 +- 如果用户已有 research,先识别它是否已经包含用户价值、技术方案、验收标准和任务拆分。 +- 如果输入过于模糊,最多追加三轮聚焦问题。 +- 当答案会改变 OpenSpec proposal/specs/tasks 时,优先一次只问一个问题。 +- 如果需要判断 `micro / standard / complex` 分档,补读 `references/scales.md`。 + +**退出条件**: +- 问题可以用 1-2 句话说清楚。 +- 期望结果可以用 1-2 句话说清楚。 +- 已列出已知影响代码或模块;如果未知,也明确标记。 +- 可以生成 OpenSpec change slug。 + +**输出**: +- 入口摘要。 +- 初步 slug。 +- devflow 规模分档:`micro` / `standard` / `complex`。 + +## context — 上下文收集 + +**进入条件**:clarify 已经有足够信息定位领域、项目或变更方向。 + +**动作**: +- 优先读取 `devflow/index.md`,按日期、slug、领域、关键词和关联 OpenSpec 定位候选项目。 +- 如果 `devflow/index.md` 不存在,先从 `devflow/projects/` 现有目录初始化轻量索引,再继续本次上下文收集。 +- 读取 `devflow/glossary/CONTEXT.md`,提取相关术语和业务规则。 +- 搜索 `devflow/projects/` 中相关 PRD、design、tasks、acceptance 和 ADR。 +- 搜索 `devflow/compound/` 中可复用 learning、trick、decision、explore。 +- 记录哪些上下文会影响 OpenSpec proposal、设计产物、specs 或 tasks。 +- 如果发现旧根目录 `CONTEXT.md` 与 `devflow/glossary/CONTEXT.md` 冲突,暂停并向用户汇报。 + +**退出条件**: +- 已形成"OpenSpec 输入上下文摘要"。 +- 已记录 `devflow/index.md` 的使用状态:已命中 / 已初始化 / 无相关条目。 +- 已列出相关 ADR 和不能违反的历史决策。 +- 已列出需要写入或修正 OpenSpec 的上下文点。 + +**输出**: +- 上下文摘要,写入 `decisions.md`(过程日志)。会影响实现的上下文必须标记为"需进入 OpenSpec"。 + +## propose — 轻量 propose + +**进入条件**:clarify + context 已经足够生成轻量 proposal。 + +**执行者**:sm-flow 内置协议。**不调用 openspec-propose**(完整 OpenSpec 产物留待 specify 阶段生成)。 + +**动作**: +- 创建或识别 `openspec/changes/{slug}/`。 +- 写入 `proposal.md`,包含:问题、建议方案、范围、非目标、来自 devflow 的上下文约束、风险。 +- **不生成 design.md、specs/、tasks.md**——这些留待 grill 澄清需求后在 specify 阶段补全。 +- 用 context 阶段的 devflow 上下文增强 proposal。 +- 在承诺方案方向前,先检查相关仓库代码。 + +**退出条件**: +- `openspec/changes/{slug}/proposal.md` 存在。 +- 关键假设已显式记录。 + +**输出**: +- Draft OpenSpec proposal.md(轻量版)。 + +**Human checkpoint**: +- 向用户简要说明 proposal 范围、关键假设、主要风险、devflow 上下文如何影响方案。 +- 作为 Discover checkpoint 的中间状态汇报;询问是否继续完成 Discover 的人类澄清部分。用户明确要求"全自动执行"时可跳过等待。 + +## grill — 人类对齐澄清 + +**进入条件**:propose 已有轻量 proposal.md。 + +**能力来源**:优先使用 `grill-with-docs`;不可用时使用 `references/fallbacks.md#grill-内置协议`,并在 `decisions.md` 标注 fallback。 + +**动作**: +- 优先使用 `grill-with-docs`。 +- 进入 grill 时先建立一个 question pool,并记录到 `decisions.md`: + - 默认至少覆盖术语、边界、验收三个维度。 + - **技术实现维度**(新增):当 proposal 提到参考实现、或涉及项目现有基础设施时,增加技术澄清问题: + - 参考实现的具体文件路径是什么? + - 项目现有的 [请求结构/MQ/缓存/加密/工具类] 标准是什么? + - 有哪些技术点需要先调研或新建? + - 如果变更涉及多模块、接口、权限、下游消费者、响应结构或生命周期规则,先把这些维度补进问题池。 +- 逐项标记每个问题的模式: + - `evidence-driven`:问题能通过代码、文档、测试、OpenSpec 或既有 ADR 证明;代理先查证,再向用户汇报证据、结论和是否需要确认。 + - `user-interview`:问题涉及产品偏好、范围边界、验收口径、风险接受度或价值取舍;必须问用户并等待确认。 +- evidence-driven 和 user-interview 的推进节奏:先批量查证 evidence-driven 并一次性汇报结论,再逐个处理 user-interview 问题。不要把所有问题攒到最后一起问。 +- 一次只问一个 `user-interview` 问题。 +- 每个 `user-interview` 问题必须等待用户显式回答,并在 decisions.md 中记录:问题原文、用户原话、确认状态(已确认/未确认)。未确认的问题不能从 question pool 移除。 +- 单个 `user-interview` 的确认只能解除该问题本身的阻塞,不能被解释为进入 apply 或修改执行目标文件的授权。 +- 对接口影响等级、消费者边界或兼容性存在不确定时,必须作为 `user-interview` 问题等待用户确认。 +- 如果澄清结果影响实现,必须回写 proposal.md。 +- 术语一旦确认,更新 `devflow/glossary/CONTEXT.md`。 +- 对难以逆转、依赖上下文、源自真实权衡的决策创建 ADR。 + +**退出条件**: +- question pool 已建立并覆盖当前 change 所需维度。 +- 已满足 `references/scales.md` 中当前分档的 grill 要求。每个问题都必须记录属于 `evidence-driven` 还是 `user-interview`。 +- 所有 evidence-driven 结论已向用户汇报。 +- 所有 user-interview 决策已获得用户确认。 +- 没有未解决或代理代确认的 user-interview 问题。 +- 没有未判级或未确认的接口影响问题。 +- 影响实现的结论已回写 proposal.md。 +- 单个 grill 决策确认不等于 apply 授权;grill 完成后必须停在 commit,等待用户明确要求进入 apply。 +- question pool、evidence-driven 结论、user-interview 确认必须写入 `decisions.md` 文件,不能只记录在对话中。 + +**输出**: +- 更新后的 proposal.md。 +- 澄清记录:写入 `decisions.md`。包含 question pool、evidence-driven 汇报状态、user-interview 确认状态。 +- 更新后的词汇表和 ADR。 + +**Human checkpoint**: +- 汇报已解决和未解决的问题、proposal 变更、术语和 ADR 更新。 +- 汇报 Discover checkpoint 完成情况,并询问是否继续进入 Commit checkpoint。 + +## specify — 细化 + 对齐 + +**进入条件**:grill 已退出,需求已通过澄清稳定下来。 + +**能力来源**:优先使用 `openspec-propose`(基于已稳定的 proposal 补全完整 OpenSpec);按需使用 `to-prd`。进入本阶段必须先声明调用方式;外部能力不可用时使用 `references/fallbacks.md#openspec-提案-内置协议`,并在 `decisions.md` 标注 fallback。 + +**动作**: +- 基于已稳定的 proposal.md 补全设计产物、specs/、tasks.md: + - 优先调用 `openspec-propose`,输入中明确说明"proposal.md 已存在,本次只需按当前分档补全设计产物/specs/tasks"。 + - 如果不可用,执行 `references/fallbacks.md#openspec-提案-内置协议`。 +- 如果没有结构化 PRD,按需按 `to-prd` 协议生成 `brief.md`;复杂需求、对外协作或用户明确要求时再生成 `prd.md`。 +- 独立 PRD 是否需要按 `references/scales.md` 的当前分档和用户要求判断。 +- 用 grill 阶段的 decisions.md 记录增强 OpenSpec 产物:确保 design/specs/tasks 反映所有已确认的决策。 +- **显式 cross-artifact 对齐检查**——在 checkpoint 中输出对齐检查表: + - `brief/prd` 中的目标、范围、非目标和验收预期 → `proposal` 是否覆盖。 + - `proposal` 中的范围、约束和关键承诺 → `design` 是否覆盖。 + - `design` 中影响实现的约束、接口影响和架构结论 → `specs` 或 `tasks` 是否覆盖。 + - `specs` 中的可观察行为 → `tasks` 是否覆盖为可执行切片。 + - 每项标记:已对齐 / 存在 gap。 +- 检查是否涉及接口影响: + - 接口影响分级定义见 `references/operating-rules.md#接口影响分级`。 + - 是否改变字段、DTO、service 方法、API、事件、回调、数据库契约、命令契约或跨模块调用语义。 + - 接口内部判断逻辑是否改变调用方可观察行为。 + - 按 L1/L2/L3/L4 记录接口影响等级;不确定时标记为 `user-interview` 问题。 +- 如果存在 gap,在进入下一阶段前修复 OpenSpec。 +- 如果发现不一致,优先修正 OpenSpec,而不是只修改 devflow 文档。 + +**退出条件**: +- OpenSpec 细化产物存在且与 proposal 对齐;产物形态按 `references/scales.md` 的当前分档要求执行。 +- `brief.md` 已覆盖背景、目标、范围和非目标;复杂需求存在独立 `prd.md` 或用户明确不需要 PRD。 +- cross-artifact 对齐检查表已生成(4 行,每行标记已对齐/存在 gap),没有未处理 gap。 +- 涉及接口变更时,已记录接口影响等级和产物要求;不确定项已标记。 +- 所有已知冲突已修正或等待用户决策。 + +**输出**: +- Draft OpenSpec:按 `references/scales.md` 的当前分档要求生成 proposal、设计、specs 和 tasks。 +- `brief.md`,以及按需创建的 `prd.md`。 +- cross-artifact 对齐检查表(写入 checkpoint 或 decisions.md)。 +- 必要的 OpenSpec 修正。 + +## audit — 架构审计 + +**进入条件**:specify 已退出,完整 OpenSpec 产物已存在。 + +**能力来源**:优先使用 `zoom-out`;不可用时使用 `references/fallbacks.md#audit-内置协议`,并在 `decisions.md` 标注 fallback。 + +**动作**: +- 画出输入 → 处理 → 输出的模块链路。 +- 识别跨模块依赖、数据所有权、生命周期和耦合风险。 +- 检查是否与既有架构、ADR、OpenSpec design 冲突。 +- 用不超过五句话写出架构风险评估。 +- 如果审计结果影响实现,必须回写 OpenSpec design/tasks;只写入 devflow design 不够。 +- 审计结论写入 `decisions.md`。 + +**退出条件**: +- 架构风险已被接受,或流程返回 grill/specify 修正 OpenSpec。 +- OpenSpec 设计产物/tasks 已反映会影响实现的架构审计结论。 + +**输出**: +- 架构审计记录,写入 `decisions.md`;复杂架构审计可拆出 `design.md`。 +- 必要的 OpenSpec 设计产物/tasks 修正。 + +**Human checkpoint**: +- 用不超过五句话向用户说明架构风险、OpenSpec 修正点和实现计划。 +- 作为 Commit checkpoint 的中间状态汇报;询问是否继续完成 commit gate。 + +## commit — Commit OpenSpec + +**进入条件**: +- grill 已满足 `references/scales.md` 中当前分档要求。 +- 所有 `user-interview` 问题都已获得用户显式确认。 +- audit 已经完成,或快速模式下已记录跳过原因;快速模式定义见 `references/operating-rules.md#快速模式`。 +- Draft OpenSpec 已回写所有会影响实现的澄清、接口影响和架构审计结论。 + +**动作**: +- 检查 proposal 是否说明为什么做、做什么、范围和非目标。 +- 检查 design 是否记录上下文约束、关键技术决策、架构风险和接口影响。 +- 检查 specs 是否表达外部可观察行为,并覆盖验收口径。 +- 检查 tasks 是否是可执行的纵向切片,而不是泛泛描述。 +- 复核 cross-artifact 对齐:`brief/prd → proposal → 设计产物 → specs → tasks` 是否闭环,没有把字段、范围项、验收行为或实现切片丢在上游产物里。 +- 检查 `decisions.md` 中所有影响实现的发现,是否已回写到 proposal、design、specs 或 tasks。 +- 接口影响分级定义见 `references/operating-rules.md#接口影响分级`。 +- 检查接口影响是否已按 L1/L4 判级;L3/L4 是否有独立接口文档或等价独立章节。 +- 检查没有未汇报的 evidence-driven 结论,没有未确认的 user-interview 问题,没有 devflow/OpenSpec 冲突。 +- 如果检查失败,返回 propose、grill、specify 或 audit 修正 Draft OpenSpec。 + +**退出条件**: +- Draft OpenSpec 已达到可执行状态,并记录为 Committed OpenSpec。 +- **文件完整性检查**(按 `references/scales.md` 的当前分档要求执行): + - [ ] proposal 存在,且足以说明问题、建议方案、范围和非目标。 + - [ ] 设计产物存在,形式符合当前分档要求。 + - [ ] specs 存在,且表达用户可观察行为。 + - [ ] tasks 存在,且任务可执行、验收标准可验证。 +- **一致性检查**(必须通过): + - [ ] proposal 中的核心概念在设计产物中有对应设计 + - [ ] 设计产物中的关键决策在 tasks 中有对应实现任务 + - [ ] tasks 的验收标准可验证(不是"正确实现""完成功能"这类模糊描述) +- **标记文件**:检查通过后,创建 `openspec/changes/{slug}/.committed` 文件标记为 Committed OpenSpec +- 所有 preflight 风险已消除或明确记录为已接受。 + +**输出**: +- Committed OpenSpec 状态说明。 +- preflight 检查结果,写入 `decisions.md` 或 `acceptance.md`。 + +**Human checkpoint**: +- 用不超过五句话说明 Committed OpenSpec 的范围、接口影响、剩余风险和执行计划。 +- 汇报 Commit checkpoint 完成情况,并询问是否进入 Apply checkpoint;除非用户在启动时明确要求"全自动执行",必须等待用户明确说出进入 apply、开始实现、执行修改或等价授权。 +- 不得把 grill 的单个决策确认当作本 checkpoint 的授权。 + +## apply — OpenSpec 执行 + +**进入条件**: +- `openspec/changes/{slug}/` 中 proposal、设计产物、specs、tasks 已通过 commit,成为 Committed OpenSpec。 +- **前置门控检查**(硬约束): + - 检查 `openspec/changes/{slug}/.committed` 文件是否存在 + - 如不存在,执行以下流程: + 1. 汇报:Draft OpenSpec 未通过 commit 检查 + 2. 列出缺失的 checkpoint 项(文件完整性、一致性检查) + 3. 询问用户:是否补做 commit 检查;如用户要求不补做,则中止 apply 或标记为 `emergency-bypass`,且本次流程不得视为合规 sm-flow apply +- commit 后已获得用户明确的 apply 授权,除非用户在启动时要求"全自动执行"。 +- devflow 与 OpenSpec 没有未解决冲突。 +- 没有未解决的 user-interview 问题、未判级接口影响、未汇报 evidence-driven 结论或未接受架构风险。 + +**能力来源**:优先使用 `openspec-apply-change`;不可用时使用 `references/fallbacks.md#openspec-apply-内置协议`,并在 `decisions.md` 标注 fallback。遇到 bug/不确定行为时优先使用 `diagnose`;需要测试驱动时优先使用 `tdd`。不可用时执行对应最小协议并记录原因,不得静默跳过。 + +**动作**: + +### Pre-apply Checkpoint + +**触发条件**:当 OpenSpec 涉及以下任一情况时必须执行 +- design 或 tasks 中提到"参考 XXX 实现" +- 需要调用项目现有基础设施(MQ/统一请求结构/工具类等) +- 技术栈不熟悉或第一次在该项目实现类似功能 + +**执行步骤**: +1. **阅读所有参考实现** + - 从 OpenSpec design 或 tasks 中定位参考实现文件 + - 如果路径不明确,通过 Grep 搜索关键类名或模式 + - 理解关键逻辑,提取可复用代码片段和模式 + +2. **Grep 关键技术栈** + - 请求/响应结构模式(如 `RequestMsg`、`ResponseMsg`、DTO 规范) + - 消息队列模式(如 `@KafkaListener`、`@YkMsg`、发送模板) + - 统一工具类(如 `XxxUtil`、`XxxHelper`、加密/验签工具) + - 异常处理和日志记录标准 + +3. **形成技术栈清单并写入 decisions.md** + - 项目使用的请求/响应结构标准 + - MQ 消息定义和发送标准 + - Consumer 标准位置和写法 + - 加密/验签/工具类的标准用法 + - 识别需要新建的工具类或基础设施 + +**输出要求**: +- 技术栈清单已写入 `decisions.md` 的 "Pre-apply Research" 章节。 +- 已列出所有参考实现的文件路径。 +- 已识别需要新建的工具类/基础设施。 + +**按风险执行**:执行深度按 `references/scales.md` 的当前分档和实现风险决定;退出判断以清单是否足以指导实现为准。 + +### 实现过程 + +- 优先调用 `openspec-apply-change`。 +- 执行依据是 OpenSpec specs/tasks;devflow 只能作为上下文参考。 +- 按 OpenSpec tasks 的纵向切片实现。 +- **分步实现**:建议按 Controller → Service → MQ/异步组件 → Consumer/下游 顺序,每完成一层验证后再继续。 +- 进入实现前先汇报本阶段的 capability 来源、当前 task 进度和本轮要推进的切片;否则 apply 不算真正开始。 +- **首模块完成后对齐检查**:完成第一个接口/模块后,对比 OpenSpec design/tasks,标记"已完成/TODO";核心功能(加密/验签/核心业务逻辑)不允许空实现或纯 TODO 注释。 +- 当用户质疑、用户要求修改、代码检查、测试失败或运行行为与 OpenSpec 冲突时,做三类判断: + - OpenSpec 不准(规格遗漏、边界未覆盖、验收口径缺失)→ 暂停 apply,修正 OpenSpec 后重新提交。 + - 代码偏离(实现没按 OpenSpec 做)→ 修正代码,不改 OpenSpec。 + - 不确定根因、涉及设计方向、用户改变目标或范围 → 暂停并等待用户确认。 +- 判断结果、证据、用户确认和 OpenSpec 回写状态必须记录到 `decisions.md`。 +- **快速失败**:连续返工 ≥ 2 次时,暂停并重新执行 pre-apply checkpoint 或向用户汇报。 +- 当用户要求、行为复杂或回归风险高时使用 TDD。 +- 当测试失败、行为意外或原因不确定时使用 diagnose。 +- 如果 diagnose 发现根因是 OpenSpec 不准确,先修正 OpenSpec,再继续 apply。 +- 修改文件前遵守仓库指令,例如 `AGENTS.md`。 + +**退出条件**: +- 已完成 pre-apply checkpoint(如触发条件满足),技术栈清单已写入 `decisions.md`。 +- OpenSpec tasks 已完成,或剩余 tasks 已明确记录。 +- 核心功能已实现或明确标注"待联调",无纯 TODO 占位。 +- 所有实现期冲突已分类并处理;没有未确认的规格遗漏、设计冲突或用户变更。 +- 已运行验证,或记录了未验证原因。 +- 已列出已知限制。 + +**输出**: +- 代码变更、必要测试和实现说明。 +- 更新后的 OpenSpec task 状态。 +- 冲突记录写入 `decisions.md`。 + +## archive — 回填 + 归档 + +**进入条件**:实现或规划工作已经达到可交接状态。 + +**能力来源**:`openspec-archive-change` 在用户确认 archive 后优先调用;不可用时使用 `references/fallbacks.md#openspec-archive-内置协议`,并在 `acceptance.md` 标注 fallback。archive 回填由 `sm-flow` 执行。 + +**动作**: +- 遵循 `references/archive-rules.md`。 +- 从 `decisions.md`(过程日志)+ OpenSpec 产物提炼完整 devflow 档案: + - `brief.md`:从 proposal.md 提取背景、目标、范围、非目标。 + - `evidence.md`:按 `references/scales.md` 和 `references/archive-rules.md` 的当前分档要求处理。 + - `decisions.md`:保持为最终版,整理格式。 + - `acceptance.md`:从实现结果和验证结果提取。 +- 只在复杂场景按需拆出 PRD/research/design/tasks/alignment。 +- 写入或更新验收记录,并区分静态验证、脚本验证、浏览器/人工验证、未验证。 +- 如果本次流程产生可复用经验,写入 compound knowledge。 +- 更新 `devflow/index.md`,记录日期、slug、领域、关键词、关联 OpenSpec 和状态。 +- 询问用户是否要 archive OpenSpec change;不要默认执行归档。 + +**退出条件**: +- `devflow/projects/YYYY-MM-DD-{slug}/` 包含 `references/scales.md` 和 `references/archive-rules.md` 要求的当前分档档案;archive checkpoint 必须列出所有已创建的文件路径,验证文件实际存在于磁盘。 +- `devflow/index.md` 已包含或更新本项目条目。 +- 用户已被询问是否 archive OpenSpec change。 + +**输出**: +- 完整 devflow 档案。 +- 归档交接清单:创建或更新了哪些文件、验证分类、剩余风险、是否 archive。 diff --git a/.agents/skills/sm-flow/references/scales.md b/.agents/skills/sm-flow/references/scales.md new file mode 100644 index 0000000..e4bf9f9 --- /dev/null +++ b/.agents/skills/sm-flow/references/scales.md @@ -0,0 +1,42 @@ +# 分档规则 + +本文件是 `micro / standard / complex` 的唯一规则源。其它文件只引用本文件,不重复定义分档细节。 + +## standard 基准 + +standard 是默认分档,适用于普通功能、明确但有一定实现范围的变更。 + +- 用户可见 checkpoint:Discover → Commit → Apply → Archive。 +- OpenSpec 产物:`proposal.md`、独立 `design.md`、`specs/`、`tasks.md`。 +- grill:解决术语、边界、验收三个维度的高价值问题。 +- commit gate:检查 proposal、design、specs、tasks 的完整性和一致性。 +- devflow 档案:`brief.md`、`evidence.md`、`decisions.md`、`acceptance.md`。 + +## micro 覆盖 + +micro 适用于小改动、低风险、需求明确的变更。micro 是 standard 的减法,不是跳过流程。 + +- checkpoint 可合并:Discover + Commit 可在无阻塞时合并汇报。 +- micro 内部流程压缩为:clarify+context 合并 checkpoint → 轻量 propose → grill → specify+commit 合并 checkpoint。 +- context 保留最小收集:至少检查 glossary 和相关 ADR。 +- grill 保留最小澄清:至少解决一个高价值问题,并记录术语、边界、验收三类是否明确;不明确项必须补问或标记风险。 +- OpenSpec 仍需要 `proposal.md`、`specs/`、`tasks.md`。 +- `design.md` 可不独立创建;允许在 `proposal.md` 或 `tasks.md` 中写等价设计小节。 +- `specs/` 和 `tasks.md` 可轻量,但必须表达可观察行为和可执行任务。 +- commit gate 仍必须通过,并创建 `.committed`。 +- devflow 档案至少包含 `brief.md`、`decisions.md`、`acceptance.md`;证据少时可并入 `brief.md` 或 `decisions.md`。 +- apply 仍只能依据 Committed OpenSpec。 +- archive 仍要轻量回填 devflow,并询问是否归档 OpenSpec。 + +micro 不适用于接口影响不清、跨团队消费者、迁移/回滚、复杂状态机、长期架构决策或需求边界不清的变更;遇到这些情况应升级为 standard 或 complex。 + +## complex 增量 + +complex 适用于高风险、跨模块、需求不清、多人协作或长期架构影响明显的变更。complex 是 standard 的加法。 + +- 需要更完整的 Discover:增加需求澄清、证据查证、范围确认和风险接受。 +- checkpoint 内可补充关键内部阶段结果,但不要把内部阶段名当作用户操作入口。 +- 按需创建 `prd.md`、`research.md`、`alignment.md`、接口文档、ADR 或 compound knowledge。 +- 接口影响、迁移、灰度、回滚、兼容性和消费者边界必须显式记录。 +- audit 需要覆盖模块链路、数据所有权、生命周期、耦合风险和 ADR 冲突。 +- archive 在 standard 档案基础上按需提炼长期 design、research、tasks、ADR 和 compound knowledge。 diff --git a/.agents/skills/sm-flow/references/templates.md b/.agents/skills/sm-flow/references/templates.md new file mode 100644 index 0000000..1ac4cb8 --- /dev/null +++ b/.agents/skills/sm-flow/references/templates.md @@ -0,0 +1,386 @@ +# 模板 + +这些是最小模板。只有在能提升未来可读性时,才增加额外章节。保留 PRD、ADR、OpenSpec、slug 等行业术语,其余说明尽量使用中文。 + +## Brief 模板 + +```markdown +# {标题} Brief + +## 背景 + +- 用户目标:{goal} +- 当前问题:{problem} +- 关联 OpenSpec:`openspec/changes/{slug}/` +- devflow 分档:micro | standard | complex + +## 范围 + +- 本次要做:{in scope} +- 本次不做:{out of scope} +- 影响区域:{modules/files if known} + +## OpenSpec 对齐 + +- proposal 覆盖状态:已覆盖 / 待修正 / 不适用 +- specs 覆盖状态:已覆盖 / 待修正 / 不适用 +- tasks 覆盖状态:已覆盖 / 待修正 / 不适用 +``` + +## Evidence 模板 + +```markdown +# {标题} Evidence + +## 证据 + +| 来源 | 证据 | 结论 | 是否已汇报 | +| --- | --- | --- | --- | +| {file/doc/test/ADR} | {evidence summary} | {conclusion} | 是 / 否 | + +## Evidence-driven 结论 + +- 结论:{conclusion} + - 证据:{evidence} + - 风险:{risk if any} + - 用户确认:需要 / 不需要 / 已确认 +``` + +## Decisions 模板 + +```markdown +# {标题} Decisions + +## Question Pool + +| # | 维度 | 问题 | 模式 | 状态 | +|---|---|---|---|---| +| Q1 | 术语 | {question} | evidence-driven / user-interview | 已解决 / 未解决 | +| Q2 | 边界 | {question} | evidence-driven / user-interview | 已解决 / 未解决 | +| Q3 | 验收 | {question} | evidence-driven / user-interview | 已解决 / 未解决 | + +## Evidence-driven + +| 结论 | 证据来源 | 是否已汇报用户 | +|---|---|---| +| {conclusion} | {file/doc/test/ADR} | 已汇报 / 待汇报 | + +## User-interview + +| 问题原文 | 用户原话 | 确认状态 | OpenSpec 回写 | +|---|---|---|---| +| {question} | {user's exact words} | 已确认 / 未确认 | 已回写 / 不影响 / 待回写 | + +## 关键取舍 + +- 决策:{decision} + - 原因:{why} + - 影响:{impact} + - 风险接受:{accepted by whom/when} +``` + +## 接口影响记录模板 + +```markdown +# {标题} 接口影响记录 + +## 分级 + +- 级别:L1 内部实现 / L2 内部接口 / L3 协作接口 / L4 破坏性接口 +- 判级原因:{why this level} +- 是否需要独立接口文档:是 / 否 + +## 变更对象 + +- 接口/字段/DTO/事件/回调/数据库契约: +- 判断逻辑变化: +- 可观察行为变化:返回数据 / 状态 / 错误码 / 权限结果 / 过滤排序 / 幂等性 / 时序 / 副作用 / 无 + +## 影响范围 + +- 调用方/消费者: +- 是否跨模块/跨服务/跨团队: +- 旧调用方是否需要改动: + +## 兼容与迁移 + +- 是否向后兼容: +- 迁移/灰度/回滚要求: +- 风险接受: + +## 验收方式 + +- 如何证明新行为正确: +- 如何证明旧行为未破坏: +- 需要用户确认的问题: +``` + +## 实现期冲突记录模板 + +```markdown +# {标题} 实现期冲突记录 + +## 冲突摘要 + +- 触发来源:用户质疑 / 用户变更 / 代码发现 / 测试失败 / 运行行为 +- 冲突对象:proposal / design / specs / tasks / ADR / 代码行为 +- 分类:OpenSpec 不准 / 代码偏离 / 不确定 + +## 证据 + +- OpenSpec 依据: +- 代码或测试证据: +- 用户反馈: + +## 处理 + +- 决策: +- 是否需要用户确认:是 / 否 +- OpenSpec 回写:不需要 / 已回写 / 待回写 / 等待用户确认 +- 代码处理: +- 验证方式: +``` + +## PRD 模板 + +```markdown +# {标题} PRD + +## 问题陈述 + +用用户视角描述问题。 + +## 解决方案 + +用用户视角描述预期解决方案。 + +## 用户故事 + +1. 作为{角色},我希望{能力},以便{收益}。 + +## 实现决策 + +- 决策:{decision} + - 原因:{why} + - 影响:{affected modules or behavior} + +## 测试决策 + +- 好测试应该通过{public interface}验证{observable behavior}。 +- 必须覆盖:{critical paths} +- 不测试:{explicit exclusions} + +## 非目标 + +- {excluded behavior} + +## 补充说明 + +- {open question or useful context} +``` + +## 词汇表模板 + +```markdown +# 上下文词汇表 + +## 术语 + +### {术语} + +- 定义:{precise definition} +- 使用场景:{feature/module/context} +- 备注:{ambiguities, synonyms, or rejected meanings} + +## 业务规则 + +- {rule}: {meaning and source} +``` + +## ADR 模板 + +```markdown +# ADR-{编号}: {决策标题} + +**状态**:提议中 | 已接受 | 已废弃 +**日期**:YYYY-MM-DD + +## 背景 + +是什么情况迫使我们做这个决策? + +## 决策 + +我们选择了什么? + +## 替代方案 + +| 方案 | 拒绝原因 | +| --- | --- | +| {option} | {reason} | + +## 后果 + +### 正面 + +- {benefit} + +### 负面 + +- {cost or risk} +``` + +## 技术调研模板 + +```markdown +# {标题} 技术调研 + +## 摘要 + +- 变更原因:{reason} +- 变更范围:{scope} +- 主要技术方案:{approach} + +## 源产物 + +- OpenSpec change: `openspec/changes/{slug}/` +- 关联 PRD: `prd.md` 或 `brief.md` + +## 关键发现 + +- {finding} + +## 假设 + +- {assumption and validation status} +``` + +## 设计模板 + +```markdown +# {标题} 设计 + +## 架构摘要 + +描述输入 → 处理 → 输出。 + +## 关键决策 + +- {decision}: {reason} + +## 模块地图 + +| 模块 | 职责 | 备注 | +| --- | --- | --- | +| {module} | {responsibility} | {notes} | + +## 架构审计 + +- 风险:{risk} +- 缓解:{mitigation} +``` + +## 任务模板 + +```markdown +# {标题} 任务 + +## 需求追踪 + +| 需求 | 状态 | 备注 | +| --- | --- | --- | +| {requirement} | 已完成 / 待处理 / 部分完成 | {notes} | + +## 实现任务 + +- [ ] {task} +``` + +## 验收模板 + +```markdown +# {标题} 验收 + +## 结果 + +已接受 / 部分接受 / 未接受。 + +## 验证 + +### 静态验证 + +- 命令/检查:`{command or check}` +- 结果:{passed/failed/not run} +- 备注:{important output or reason not run} + +### 脚本验证 + +- 命令:`{command}` +- 结果:{passed/failed/not run} +- 备注:{important output or reason not run} + +### 浏览器/人工验证 + +- 步骤:{manual steps} +- 结果:{passed/failed/not run} +- 备注:{observations or reason not run} + +## 已完成范围 + +- {completed behavior} + +## 已知限制 + +- {limitation} + +## Bug 修复和诊断 + +- {bug}: {diagnosis summary and regression coverage} + +## 交接 + +- 下一步:{archive, deploy, review, or follow-up} +- OpenSpec 归档确认:{已询问/用户确认归档/用户暂不归档/不适用} +``` + +## Cross-Artifact 对齐检查表模板 + +specify 阶段的 checkpoint 必须包含此检查表。每项标记"已对齐"或"存在 gap"。 + +```markdown +## Cross-Artifact 对齐检查 + +| 上游 → 下游 | 检查内容 | 状态 | +|---|---|---| +| brief/prd → proposal | 目标、范围、非目标、验收预期是否进入 proposal | 已对齐 / 存在 gap | +| proposal → 设计产物 | 范围、约束、关键承诺是否进入 design.md 或等价设计小节 | 已对齐 / 存在 gap | +| 设计产物 → specs/tasks | 影响实现的约束、接口影响、架构结论是否进入 specs 或 tasks | 已对齐 / 存在 gap | +| specs → tasks | 可观察行为是否被 tasks 覆盖为可执行切片 | 已对齐 / 存在 gap | + +### Gap 详情(如有) + +- gap 1:{描述哪个字段/约束/行为/切片只停留在上游,未进入下游} + - 修复:{如何修正 OpenSpec} +``` + +## 复合知识模板 + +```markdown +# {标题} + +**类型**:learning | trick | decision | explore +**日期**:YYYY-MM-DD + +## 背景 + +这条经验来自哪里? + +## 经验 + +未来代理应该复用什么经验? + +## 适用性 + +什么时候适用?什么时候不适用? +``` + diff --git a/.agents/skills/tdd/SKILL.md b/.agents/skills/tdd/SKILL.md new file mode 100644 index 0000000..7a98941 --- /dev/null +++ b/.agents/skills/tdd/SKILL.md @@ -0,0 +1,109 @@ +--- +name: tdd +description: Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development. +--- + +# Test-Driven Development + +## Philosophy + +**Core principle**: Tests should verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't. + +**Good tests** are integration-style: they exercise real code paths through public APIs. They describe _what_ the system does, not _how_ it does it. A good test reads like a specification - "user can checkout with valid cart" tells you exactly what capability exists. These tests survive refactors because they don't care about internal structure. + +**Bad tests** are coupled to implementation. They mock internal collaborators, test private methods, or verify through external means (like querying a database directly instead of using the interface). The warning sign: your test breaks when you refactor, but behavior hasn't changed. If you rename an internal function and tests fail, those tests were testing implementation, not behavior. + +See [tests.md](tests.md) for examples and [mocking.md](mocking.md) for mocking guidelines. + +## Anti-Pattern: Horizontal Slices + +**DO NOT write all tests first, then all implementation.** This is "horizontal slicing" - treating RED as "write all tests" and GREEN as "write all code." + +This produces **crap tests**: + +- Tests written in bulk test _imagined_ behavior, not _actual_ behavior +- You end up testing the _shape_ of things (data structures, function signatures) rather than user-facing behavior +- Tests become insensitive to real changes - they pass when behavior breaks, fail when behavior is fine +- You outrun your headlights, committing to test structure before understanding the implementation + +**Correct approach**: Vertical slices via tracer bullets. One test → one implementation → repeat. Each test responds to what you learned from the previous cycle. Because you just wrote the code, you know exactly what behavior matters and how to verify it. + +``` +WRONG (horizontal): + RED: test1, test2, test3, test4, test5 + GREEN: impl1, impl2, impl3, impl4, impl5 + +RIGHT (vertical): + RED→GREEN: test1→impl1 + RED→GREEN: test2→impl2 + RED→GREEN: test3→impl3 + ... +``` + +## Workflow + +### 1. Planning + +When exploring the codebase, use the project's domain glossary so that test names and interface vocabulary match the project's language, and respect ADRs in the area you're touching. + +Before writing any code: + +- [ ] Confirm with user what interface changes are needed +- [ ] Confirm with user which behaviors to test (prioritize) +- [ ] Identify opportunities for [deep modules](deep-modules.md) (small interface, deep implementation) +- [ ] Design interfaces for [testability](interface-design.md) +- [ ] List the behaviors to test (not implementation steps) +- [ ] Get user approval on the plan + +Ask: "What should the public interface look like? Which behaviors are most important to test?" + +**You can't test everything.** Confirm with the user exactly which behaviors matter most. Focus testing effort on critical paths and complex logic, not every possible edge case. + +### 2. Tracer Bullet + +Write ONE test that confirms ONE thing about the system: + +``` +RED: Write test for first behavior → test fails +GREEN: Write minimal code to pass → test passes +``` + +This is your tracer bullet - proves the path works end-to-end. + +### 3. Incremental Loop + +For each remaining behavior: + +``` +RED: Write next test → fails +GREEN: Minimal code to pass → passes +``` + +Rules: + +- One test at a time +- Only enough code to pass current test +- Don't anticipate future tests +- Keep tests focused on observable behavior + +### 4. Refactor + +After all tests pass, look for [refactor candidates](refactoring.md): + +- [ ] Extract duplication +- [ ] Deepen modules (move complexity behind simple interfaces) +- [ ] Apply SOLID principles where natural +- [ ] Consider what new code reveals about existing code +- [ ] Run tests after each refactor step + +**Never refactor while RED.** Get to GREEN first. + +## Checklist Per Cycle + +``` +[ ] Test describes behavior, not implementation +[ ] Test uses public interface only +[ ] Test would survive internal refactor +[ ] Code is minimal for this test +[ ] No speculative features added +``` diff --git a/.agents/skills/tdd/deep-modules.md b/.agents/skills/tdd/deep-modules.md new file mode 100644 index 0000000..0d9720c --- /dev/null +++ b/.agents/skills/tdd/deep-modules.md @@ -0,0 +1,33 @@ +# Deep Modules + +From "A Philosophy of Software Design": + +**Deep module** = small interface + lots of implementation + +``` +┌─────────────────────┐ +│ Small Interface │ ← Few methods, simple params +├─────────────────────┤ +│ │ +│ │ +│ Deep Implementation│ ← Complex logic hidden +│ │ +│ │ +└─────────────────────┘ +``` + +**Shallow module** = large interface + little implementation (avoid) + +``` +┌─────────────────────────────────┐ +│ Large Interface │ ← Many methods, complex params +├─────────────────────────────────┤ +│ Thin Implementation │ ← Just passes through +└─────────────────────────────────┘ +``` + +When designing interfaces, ask: + +- Can I reduce the number of methods? +- Can I simplify the parameters? +- Can I hide more complexity inside? diff --git a/.agents/skills/tdd/interface-design.md b/.agents/skills/tdd/interface-design.md new file mode 100644 index 0000000..a0a20ca --- /dev/null +++ b/.agents/skills/tdd/interface-design.md @@ -0,0 +1,31 @@ +# Interface Design for Testability + +Good interfaces make testing natural: + +1. **Accept dependencies, don't create them** + + ```typescript + // Testable + function processOrder(order, paymentGateway) {} + + // Hard to test + function processOrder(order) { + const gateway = new StripeGateway(); + } + ``` + +2. **Return results, don't produce side effects** + + ```typescript + // Testable + function calculateDiscount(cart): Discount {} + + // Hard to test + function applyDiscount(cart): void { + cart.total -= discount; + } + ``` + +3. **Small surface area** + - Fewer methods = fewer tests needed + - Fewer params = simpler test setup diff --git a/.agents/skills/tdd/mocking.md b/.agents/skills/tdd/mocking.md new file mode 100644 index 0000000..71cbfee --- /dev/null +++ b/.agents/skills/tdd/mocking.md @@ -0,0 +1,59 @@ +# When to Mock + +Mock at **system boundaries** only: + +- External APIs (payment, email, etc.) +- Databases (sometimes - prefer test DB) +- Time/randomness +- File system (sometimes) + +Don't mock: + +- Your own classes/modules +- Internal collaborators +- Anything you control + +## Designing for Mockability + +At system boundaries, design interfaces that are easy to mock: + +**1. Use dependency injection** + +Pass external dependencies in rather than creating them internally: + +```typescript +// Easy to mock +function processPayment(order, paymentClient) { + return paymentClient.charge(order.total); +} + +// Hard to mock +function processPayment(order) { + const client = new StripeClient(process.env.STRIPE_KEY); + return client.charge(order.total); +} +``` + +**2. Prefer SDK-style interfaces over generic fetchers** + +Create specific functions for each external operation instead of one generic function with conditional logic: + +```typescript +// GOOD: Each function is independently mockable +const api = { + getUser: (id) => fetch(`/users/${id}`), + getOrders: (userId) => fetch(`/users/${userId}/orders`), + createOrder: (data) => fetch('/orders', { method: 'POST', body: data }), +}; + +// BAD: Mocking requires conditional logic inside the mock +const api = { + fetch: (endpoint, options) => fetch(endpoint, options), +}; +``` + +The SDK approach means: +- Each mock returns one specific shape +- No conditional logic in test setup +- Easier to see which endpoints a test exercises +- Type safety per endpoint diff --git a/.agents/skills/tdd/refactoring.md b/.agents/skills/tdd/refactoring.md new file mode 100644 index 0000000..8a44439 --- /dev/null +++ b/.agents/skills/tdd/refactoring.md @@ -0,0 +1,10 @@ +# Refactor Candidates + +After TDD cycle, look for: + +- **Duplication** → Extract function/class +- **Long methods** → Break into private helpers (keep tests on public interface) +- **Shallow modules** → Combine or deepen +- **Feature envy** → Move logic to where data lives +- **Primitive obsession** → Introduce value objects +- **Existing code** the new code reveals as problematic diff --git a/.agents/skills/tdd/tests.md b/.agents/skills/tdd/tests.md new file mode 100644 index 0000000..ff22f80 --- /dev/null +++ b/.agents/skills/tdd/tests.md @@ -0,0 +1,61 @@ +# Good and Bad Tests + +## Good Tests + +**Integration-style**: Test through real interfaces, not mocks of internal parts. + +```typescript +// GOOD: Tests observable behavior +test("user can checkout with valid cart", async () => { + const cart = createCart(); + cart.add(product); + const result = await checkout(cart, paymentMethod); + expect(result.status).toBe("confirmed"); +}); +``` + +Characteristics: + +- Tests behavior users/callers care about +- Uses public API only +- Survives internal refactors +- Describes WHAT, not HOW +- One logical assertion per test + +## Bad Tests + +**Implementation-detail tests**: Coupled to internal structure. + +```typescript +// BAD: Tests implementation details +test("checkout calls paymentService.process", async () => { + const mockPayment = jest.mock(paymentService); + await checkout(cart, payment); + expect(mockPayment.process).toHaveBeenCalledWith(cart.total); +}); +``` + +Red flags: + +- Mocking internal collaborators +- Testing private methods +- Asserting on call counts/order +- Test breaks when refactoring without behavior change +- Test name describes HOW not WHAT +- Verifying through external means instead of interface + +```typescript +// BAD: Bypasses interface to verify +test("createUser saves to database", async () => { + await createUser({ name: "Alice" }); + const row = await db.query("SELECT * FROM users WHERE name = ?", ["Alice"]); + expect(row).toBeDefined(); +}); + +// GOOD: Verifies through interface +test("createUser makes user retrievable", async () => { + const user = await createUser({ name: "Alice" }); + const retrieved = await getUser(user.id); + expect(retrieved.name).toBe("Alice"); +}); +``` diff --git a/.agents/skills/to-prd/SKILL.md b/.agents/skills/to-prd/SKILL.md new file mode 100644 index 0000000..47a01d4 --- /dev/null +++ b/.agents/skills/to-prd/SKILL.md @@ -0,0 +1,76 @@ +--- +name: to-prd +description: Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context. +--- + +This skill takes the current conversation context and codebase understanding and produces a PRD. Do NOT interview the user — just synthesize what you already know. + +The issue tracker and triage label vocabulary should have been provided to you — run `/setup-matt-pocock-skills` if not. + +## Process + +1. Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the PRD, and respect any ADRs in the area you're touching. + +2. Sketch out the major modules you will need to build or modify to complete the implementation. Actively look for opportunities to extract deep modules that can be tested in isolation. + +A deep module (as opposed to a shallow module) is one which encapsulates a lot of functionality in a simple, testable interface which rarely changes. + +Check with the user that these modules match their expectations. Check with the user which modules they want tests written for. + +3. Write the PRD using the template below, then publish it to the project issue tracker. Apply the `ready-for-agent` triage label - no need for additional triage. + + + +## Problem Statement + +The problem that the user is facing, from the user's perspective. + +## Solution + +The solution to the problem, from the user's perspective. + +## User Stories + +A LONG, numbered list of user stories. Each user story should be in the format of: + +1. As an , I want a , so that + + +1. As a mobile bank customer, I want to see balance on my accounts, so that I can make better informed decisions about my spending + + +This list of user stories should be extremely extensive and cover all aspects of the feature. + +## Implementation Decisions + +A list of implementation decisions that were made. This can include: + +- The modules that will be built/modified +- The interfaces of those modules that will be modified +- Technical clarifications from the developer +- Architectural decisions +- Schema changes +- API contracts +- Specific interactions + +Do NOT include specific file paths or code snippets. They may end up being outdated very quickly. + +Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it within the relevant decision and note briefly that it came from a prototype. Trim to the decision-rich parts — not a working demo, just the important bits. + +## Testing Decisions + +A list of testing decisions that were made. Include: + +- A description of what makes a good test (only test external behavior, not implementation details) +- Which modules will be tested +- Prior art for the tests (i.e. similar types of tests in the codebase) + +## Out of Scope + +A description of the things that are out of scope for this PRD. + +## Further Notes + +Any further notes about the feature. + + diff --git a/.agents/skills/zoom-out/SKILL.md b/.agents/skills/zoom-out/SKILL.md new file mode 100644 index 0000000..1e7a5dc --- /dev/null +++ b/.agents/skills/zoom-out/SKILL.md @@ -0,0 +1,7 @@ +--- +name: zoom-out +description: Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture. +disable-model-invocation: true +--- + +I don't know this area of code well. Go up a layer of abstraction. Give me a map of all the relevant modules and callers, using the project's domain glossary vocabulary.