canonical-doc-sync
Syncs implementation changes back into canonical documentation. Use when code changes are understood and handoff has not closed, above all when several doc surfaces must change together.
- License 许可
- MIT
- 所属仓库
- Eliyce/paqad-ai
- 最近更新
- 2026-11-13
- Stars
- ★ 8
- Forks
- 0
01 前言 Front Matter
- name
- canonical-doc-sync
- metadata
- { "cacheable": "true", "model_tier": "medium", "paqad-meta": "skill.meta.yaml", "output_format": "markdown" }
- description
- Syncs implementation changes back into canonical documentation. Use when code changes are understood and handoff has not closed, above all when several doc surfaces must change together.
02 资源文件 6
- 参考文档agents/openai.yaml137 B
- 资产文件assets/output.template.md340 B
- 参考文档references/drift-triage.md254 B
- 脚本scripts/lint-output.sh1.3 KB
- 脚本scripts/list-canonical-docs.sh647 B
- 参考文档skill.meta.yaml387 B
03 SKILL.md 正文
What It Does
Updates canonical project documentation after implementation changes so specs, module docs, and registries remain aligned with the actual behavior that shipped or is about to ship.
Use This When
After code changes are understood and before handoff closes, especially when multiple doc surfaces must be updated together to avoid drift.
Inputs
- Read the changed files, existing canonical docs, and any generated inventories for the affected area.
- Read the module docs and global registries that should reflect the change.
- Read
references/drift-triage.mdbefore deciding what to update immediately versus defer explicitly.
Procedure
- Run
scripts/list-canonical-docs.shto enumerate the canonical doc surfaces that exist in this project. - Identify which of those are now stale relative to the implementation change.
- Update behavior docs, module docs, and registries together: never patch only one surface.
- Prefer generated inventories or script output for routes, events, and error codes when available.
- Format per
assets/output.template.mdand validate withscripts/lint-output.sh.
Output Contract
- Match
assets/output.template.md:## Updated Docs(backticked .md paths + summary) and## Known Drift(backticked paths + reason, or the literalnone). - Output must pass
scripts/lint-output.sh(exit 0).
Escalate / Stop Conditions
- Ask when docs disagree with implementation and the product decision is unclear.
- Warn when generated sources are missing and a manual sync would be speculative.
- Do not silently skip a stale canonical doc that is still user-facing or operationally important.
Resources
references/drift-triage.mdscripts/list-canonical-docs.shscripts/lint-output.shassets/output.template.mdruntime/templates/runner-scripts/extract-events.sh.hbsagents/openai.yaml
04 同仓库更多 Skills
sample-skill
Sample bundled skill fixture
processing-invoices
Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.
processing-invoices
Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.
understand-idea
Chat and Claude Code: Step 1 of the discover journey: clarifies the goal, who benefits, success and constraints into the idea block. Use when the journey directs it to step 1, not directly.
size-work
Chat and Claude Code: Suggest a size for a ticket from comparable finished work, as a labelled suggestion the team still owns. Use it when someone asks "how big is this?", "roughly how much work is ABC-12?", or wants a backlog item sized. It finds the team's sizing scale at first use, picks two to five of the closest finished tickets with links, and gives a size or range with the drivers behind it and a confidence of low, medium or high, lowered and explained when the area's documents are template text. Every result is labelled a suggested size, never a date or a commitment. It writes nothing into the size field unless the user says "set it", and it refuses to overwrite an existing size unless the user asks to replace it. Produces the sizing block of the record.
refine-ticket
Chat and Claude Code: Improve one or more existing tracker tickets without losing the author's intent. Use it when someone wants a ticket read, diagnosed and tidied up ("this ticket is vague", "fix up ABC-12", "split this, it's too big"). It reads each ticket in full and snapshots it with its last-updated time, says what is wrong with evidence, and proposes a field-by-field before and after change set limited to summary, description, labels, parent, links and new child tickets on a split. It writes nothing until an explicit "apply it" bound to that exact change set, re-checks the ticket for conflicting edits just before writing, never replaces rich descriptions with plain text, never deletes or closes a ticket, and reads each ticket back after applying. Produces the existing and changes blocks of the record.