Skip to content

aspiers/ai-config / .agents/skills/documentation-updates

documentation-updates

Verified

Capture durable project or workflow knowledge discovered during work. Use when a mistake, hidden constraint, repeated question, or changed behavior reveals a documentation gap. To root-cause one specific mistake the agent just made and let the user pick fixes, use `learn` (`/learn`) instead.

Documentation Updates

Record knowledge where future readers will naturally look for it, without turning instruction files into a transcript or catch-all memory store.

Research reports

Store durable research, investigation, audit, and comparison reports under docs/research/ relative to the current repository root by default. Defer to a location specified by the user, the repository, or a focused workflow.

Workflow

  1. Identify the durable lesson and who needs it.
  2. Find the authoritative home: nearby code or tests, project documentation, an applicable agent rule, a focused skill, or the project's task/memory system. For agent rules, prefer AGENTS.md over CLAUDE.md, and the shared global rules file (e.g. ~/.agents/AGENTS.md) over any single agent's global file, so all agents stay in parity. Use an agent-specific file only for that agent's own features. The shared global rules file loads into every session, so it takes only rules for almost any task. Guidance for one kind of work, such as writing skills or agent config, goes in that work's skill. If an agent needed that skill and didn't load it, fix the skill's description so it triggers; don't copy the rule into an always-loaded file.
  3. Update the smallest relevant source. Link to existing detail rather than duplicating it.
  4. Check for conflicting or stale guidance and update it in the same scope.
  5. Validate examples, commands, links, and any generated or mirrored files.
  6. Summarize what changed and why.

Include

  • non-obvious constraints and operational gotchas;
  • decisions that remain true beyond the current session;
  • reliable recovery or verification procedures; and
  • changed user-facing behavior that belongs in product documentation.

Exclude

  • ordinary facts visible from the codebase;
  • chronological work logs better suited to issues or comments;
  • credentials, personal data, or confidential context;
  • speculative rules based on a single unexplained failure; and
  • global guidance when the lesson is project-specific.

Do not block unrelated work for a documentation review unless the user asked for an approval checkpoint or the documentation is required for safe use.

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: 466kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexUnverifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall