Expecho/Agent42 / .claude/skills/sync-docs
sync-docs
VerifiedAfter a code change, sweep the diff for documentation impact — stale gotchas/exemplars, decisions that need an ADR, specs to complete — and fix them in the same MR.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.2 KB |
SKILL.md
View on GitHub---
name: sync-docs
description: After a code change, sweep the diff for documentation impact — stale gotchas/exemplars, decisions that need an ADR, specs to complete — and fix them in the same MR.
user-invocable: true
disable-model-invocation: false
---
# Sync docs with the current diff
Merged from the workspace `/temper` doc-sync half and `/sync-docs`, retargeted from
expertise YAMLs to this template's ADRs + gotchas model. Run before creating an MR
(or when asked). Principle: **the diff pays its doc debt in the same MR.**
## Step 1 — Get the diff
`git diff <integration-branch>...HEAD` (fall back to `git diff` + `git status` for
uncommitted work).
## Step 2 — Sweep for impact (checklist)
For each changed file, check:
1. **Gotcha constraints** — does any `.agentic/gotchas.md` entry cite a changed file
as `evidence:`, or make a claim this diff invalidates? → correct or delete the
entry; bump `verified:`.
2. **Exemplars** — did the diff change (or delete) a file listed in the exemplars
table? If the canonical shape evolved, update the pointer or re-verify the entry.
3. **Decisions** — does the diff contradict an active ADR? That's an undocumented
supersession → `/decide`. Does it *embody* a new decision with real alternatives?
→ `/decide`.
4. **Specs** — does the diff complete a plan in `.agentic/specs/`? → move it to
`completed/`.
5. **CLAUDE.md** — did commands, ports, or hard-rule-relevant facts change? → update
the table (and verify the new command runs). A new ADR gets a number in the
"Feature map" row for its area, and a new secret or manual step gets a row in
"Manual prerequisites". Never add a per-feature write-up to CLAUDE.md: that
belongs in the ADR and in gotchas.
## Step 3 — Anti-bloat rule
While sweeping, do NOT add documentation that restates the diff. New docs are
justified only by the `/gotcha` admission test (code can't express it, agents would
trip, concrete evidence). When in doubt, write nothing — the code is the doc.
## Step 4 — Report
List what was updated, what was deleted, and what was deliberately not documented
(with the reason). Zero updates is a valid outcome for most diffs.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |