Add keyword cleanup governance workflow

2026-03-27 16:59:52 +08:00
parent 100044e1f7
commit 32ad584348
25 changed files with 1915 additions and 18 deletions
@@ -0,0 +1,102 @@
+---
+name: keyword-cleanup-review
+description: Review and curate this repository's daily keyword index and frequency stats. Use when the user wants to inspect `data/term_index/term_stats.json`, recent `data/term_index/daily/*.json`, `configs/term_aliases.json`, `configs/term_stopwords.json`, or `configs/filter_context.personal.json` to propose alias merges, stopwords, watch terms, or `interest_keywords` updates without directly modifying configs.
+---
+
+# Keyword Cleanup Review
+
+Use this skill to turn the repository's keyword statistics into reviewable cleanup suggestions.
+
+## Workflow
+
+1. Build a compact review bundle:
+
+```bash
+python skills/keyword-cleanup-review/scripts/build_review_bundle.py
+```
+
+Optional knobs:
+
+- `--days 7`
+- `--top 50`
+- `--output outputs/term_index/review/keyword-cleanup-bundle.json`
+
+2. Read the generated bundle and the suggestion schema:
+
+- `outputs/term_index/review/keyword-cleanup-bundle.json`
+- `skills/keyword-cleanup-review/references/suggestion-schema.md`
+
+3. Produce two outputs:
+
+- A short Markdown review for humans
+- A JSON suggestion file matching the schema
+
+4. Keep the boundary strict:
+
+- Suggest changes to `configs/term_aliases.json`
+- Suggest changes to `configs/term_stopwords.json`
+- Suggest additions to `configs/filter_context.personal.json`
+- Do not directly edit these files unless the user explicitly asks
+- Do not suggest direct edits to `configs/filter_rules.json` unless the user asks for rule logic changes
+
+## Review Heuristics
+
+Prioritize these decisions:
+
+- Alias suggestion
+  - Same concept with different naming, casing, abbreviation, or Chinese/English variants
+- Stopword suggestion
+  - Too generic, too broad, or too noisy to help filtering
+- Interest keyword suggestion
+  - High-frequency and aligned with the user's backend engineering, AI-agent, and frontier-tech focus
+- Watch term
+  - Recent and potentially important, but evidence is still weak
+
+Prefer conservative suggestions. If confidence is low, put the term into `watch_terms`.
+
+## Inputs
+
+Primary inputs:
+
+- `data/term_index/term_stats.json`
+- `data/term_index/daily/*.json`
+- `configs/term_aliases.json`
+- `configs/term_stopwords.json`
+- `configs/filter_context.personal.json`
+- `configs/term_cleanup_policy.json`
+- `configs/term_watchlist.json`
+- `configs/term_change_log.json`
+
+The bundled script already compacts these into a single review bundle.
+
+## Output Expectations
+
+The Markdown output should:
+
+- Summarize the current state briefly
+- List the top terms worth acting on
+- Separate alias, stopword, interest-keyword, and watch-term recommendations
+- Explain reasoning in short, concrete sentences
+
+The JSON output should follow:
+
+- `references/suggestion-schema.md`
+
+## Repository Notes
+
+Current repository behavior:
+
+- Keyword stats are program-maintained, not LLM-maintained
+- Stats are built from `keywords`, not `topics`
+- Stats only include non-`drop` candidates
+- `data/term_index/term_stats.json` is rebuilt from daily files, so reruns overwrite the same day instead of double-counting
+- cleanup policy, watchlist, and change log are repository-managed governance inputs and should be respected during review
+
+Keep suggestions aligned with that design.
+
+## Resources
+
+- Script:
+  - `scripts/build_review_bundle.py`
+- Reference:
+  - `references/suggestion-schema.md`