From 1de4a08200fa2bdd88f5de3b0163ffd1b0e2c3ef Mon Sep 17 00:00:00 2001 From: root Date: Thu, 2 Apr 2026 10:25:27 +0800 Subject: [PATCH] tighten reader digest skill rules --- reader-digest-flow/SKILL.md | 20 +++++++++++ .../references/public-digest-example.md | 35 +++++++++++++++++++ 2 files changed, 55 insertions(+) create mode 100644 reader-digest-flow/references/public-digest-example.md diff --git a/reader-digest-flow/SKILL.md b/reader-digest-flow/SKILL.md index 5222826..6b3e471 100644 --- a/reader-digest-flow/SKILL.md +++ b/reader-digest-flow/SKILL.md @@ -14,11 +14,14 @@ Run the reader-based daily digest as a fixed SOP. Treat this skill as the orches - **Do not generate the daily digest from examples or placeholder data. Always require a real payload first.** - Generate the daily digest markdown from the payload in OpenClaw. - Split outputs into a **public digest** for Hugo and an **internal review digest** for chat / operator decision-making. +- **Public digest and internal review digest are orchestration-layer outputs, and by default are generated by the current OpenClaw session model rather than inheriting reader `LLM_*` settings.** - Publish only the public digest to Hugo. - Report the internal review digest back to the user in chat. - **Do not upload the full daily digest to IMA.** - **Do not upload any selected article summary to IMA until the user has explicitly confirmed the selection.** - Upload **only user-selected articles** to IMA as individual knowledge notes. +- **The formal IMA upload object must be the generated single-article summary content (Markdown note / note content), not the original article webpage URL.** +- **Importing original article URLs into IMA can be used only as temporary source collection, and does not count as completing the daily summary deposition flow.** - Default IMA target for daily single-article summaries is the `daily` knowledge base. - Resolve that default target from reader `.env` (`IMA_DAILY_KNOWLEDGE_BASE_ID`, `IMA_DAILY_KNOWLEDGE_BASE_NAME`) and verify it at runtime before upload. - If the configured daily knowledge base is missing, try to locate it by name; if still missing, create `daily` and continue. @@ -81,10 +84,15 @@ Public digest writing rules: - Use `digest-brief.json` as the default source when available. - Treat it as a public-only view that already excludes non-keep items. - Keep the tone suitable for public browsing and Hugo publishing. +- Style should follow `references/public-digest-example.md` as the default public-writing example. +- Public digest is a **public reading draft / editor-style public note**, not a workflow report. +- In `今日概览`, focus on the day’s topic lines, shared signals, and broader industry movement; do **not** describe filtering mechanics or internal selection process. - Do **not** expose internal workflow labels or operator language such as `待确认`, `建议沉淀到 IMA`, `keep/review/drop`, or `selection_decision`. +- Explicitly avoid wording such as `共筛出`, `候选`, `保留`, `入选`, `待确认`, `建议沉淀` in public digest. - Prefer concise but information-dense writing. - For each item under `今日重点`, include not only summary and highlights, but also one short editor-style value sentence, for example: `这篇内容更值得关注的原因在于……`. - When rendering highlights in public digest, prefer a short label such as `值得关注：` followed by one item per line, instead of packing multiple points into a single long sentence. +- In `延伸阅读`, every item must include source attribution in the form: `- [标题](url)｜来源`. Recommended **internal review digest** structure: @@ -164,6 +172,18 @@ Default target knowledge base for this phase: - Verify the target at runtime through IMA APIs / skill lookups before upload - If the configured target does not exist, try to find `daily` by name; if still absent, create it and continue +Completion criteria for this phase: + +- a selected article has been summarized from extracted content +- a single-article Markdown summary file has been generated +- the object uploaded into IMA is the summary content / note content derived from that Markdown +- the upload target is the `daily` knowledge base unless the user explicitly requests otherwise + +Do not treat the following as completion of summary deposition: + +- importing the original article webpage URL into IMA +- storing the original article only as source material without the generated summary content + Do not upload: - the full daily digest diff --git a/reader-digest-flow/references/public-digest-example.md b/reader-digest-flow/references/public-digest-example.md new file mode 100644 index 0000000..d7bd944 --- /dev/null +++ b/reader-digest-flow/references/public-digest-example.md @@ -0,0 +1,35 @@ ++++ +title = "AI 日报 · 示例" +date = 2026-04-01T16:55:00+08:00 +summary = "围绕 Agent 架构分层、Skills 标准化与桌面 Agent 工程实践的当日观察。" ++++ + +# 今日概览 + +今天的公开候选主要集中在 AI Agent 的架构演进、工具化落地与工程化实践三条线索上。相比早期偏概念展示的讨论，这一批内容更强调模块化能力栈、真实部署路径与系统可维护性，说明行业关注点正在从“模型能做什么”转向“系统如何稳定落地并持续复用”。 + +## 今日重点 + +### 1. 学习笔记：从 Agent 到 Skills — AI 智能体架构的范式转变 +来源：阿里云开发者 + +文章分析了 AI 智能体架构从单体 Agent 向模块化 Skills 的范式转变。Anthropic 先后推出 MCP 和 Agent Skills 开放标准，构建了知识、工具、协作和运行分层架构。文章通过一个自动化美化相册的真实项目，对比了 Claude Code 与 OpenClaw 两种实现方案，验证了新架构的可复用性与灵活性。 + +值得关注： +- Anthropic 在 14 个月内先后推出 MCP 和 Agent Skills 两个开放标准，推动 AI 智能体架构分层化。 +- 新范式核心是构建薄 Agent 引擎与可组合的 Skills 库，取代为每个用例定制单体 Agent。 +- 文章通过自动化美化相册项目，实操演示了 Skills、MCP、OpenClaw 和 A2A 协议如何协同工作。 + +这篇内容更值得关注的原因在于，它不只是提出了“Agent 要模块化”这个判断，而是把开放标准、分层架构和真实项目案例串成了一条完整论证链，能直接支撑今天日报的主线。 + +## 趋势观察 + +1. Agent 正在从单体能力转向可组合的模块化体系。无论是 Skills、MCP、记忆还是运行时编排，这批内容都在强调解耦与复用，而不是把智能体继续当成一个不可拆分的黑箱。 +2. 工程化正在变成 AI 应用竞争的主战场。桌面 Agent、企业级架构和部署实践类内容增多，说明真正的差异化开始落在接入现有流程、控制风险和提升可维护性上。 +3. AI 能力的竞争点正在上移。模型本身仍重要，但真正可持续的优势越来越来自系统设计、工作流整合和对业务场景的理解。 + +## 延伸阅读 + +- [学习笔记：从 Agent 到 Skills — AI 智能体架构的范式转变](https://example.com/a)｜阿里云开发者 +- [Agent Skills：打通可复用专业领域知识的最后一公里](https://example.com/b)｜阿里云开发者 +- [CoPaw深度解析：源码架构和功能实践](https://example.com/c)｜阿里云开发者