/octocode-documentation
Use when writing or updating docs: README, API docs, runbooks, AGENTS.md, CLAUDE.md, ADRs, Diátaxis restructuring, or codebase documentation for humans or coding agents.
$ npx -y skills add bgauryy/octocode-mcp --skill octocode-documentation --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/octocode-documentation
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when writing or updating docs: README, API docs, runbooks, AGENTS.md, CLAUDE.md, ADRs, Diátaxis restructuring, or codebase documentation for humans or coding agents.
SKILL.md
octocode-documentation.SKILL.mdname: octocode-documentation
description: "Use when writing or updating docs: README, API docs, runbooks, AGENTS.md, CLAUDE.md, ADRs, Diátaxis restructuring, or codebase documentation for humans or coding agents."
Octocode Documentation
Evidence-backed docs for humans and agents. Classify first. Gate writes. Prefer durable cross-refs over code dumps.
Flow
`UNDERSTAND → RESEARCH → CLASSIFY → OUTLINE GATE → WRITE → VERIFY`
Compress when targets and type are named. Expand when claims need verification.
Hard rules
- MUST verify claims in the repo before asserting them.
- MUST pick one mode and load its routes before writing.
- MUST gate creates/overwrites unless the user already approved targets this turn.
- MUST treat `AGENTS.md` as a docs index (links + non-obvious rules), not a content dump.
- Prefer durable pointers (module path, contract name, doc link) over line numbers and pasted code.
- FORBIDDEN: inventing commands, paths, APIs, or env vars.
- Keep one Diátaxis type per page; link siblings instead of mixing.
- Do not copy README/CONTRIBUTING into `AGENTS.md`, or paste large code blocks — link the source.
Stop when: outline gate awaits answer; write+verify finishes; fact missing (report gap); user cancels.
Routes
Load only what the step needs:
- Read `references/modes.md` when choosing mode or audience.
- Read `references/evidence-research.md` when gathering or verifying repo facts.
- Read `references/diataxis.md` when writing or reviewing human-docs.
- Read `references/agents-md.md` when writing or updating agent instruction files.
- Read `references/adr.md` when recording a decision.
- Read `references/agent-readable.md` before WRITE (cross-refs, density, durability).
- Read `references/write-verify.md` for outline gate, write steps, and verify checklist.
- Skip `references/references.md` during normal tasks (creation audit only).
Related
- Pure code/repo evidence with no docs deliverable → `octocode-research`.
- Authoring a `SKILL.md` → `octocode-skills`.
- Full multi-file pack → `octocode-documentation-writer` if installed.
- Unclear mode → ask once: agent-docs / human-docs / adr / codebase-pack.
- Conflicting conventions → surface; do not add a second scheme.
- Missing command → omit or mark unverified. No Octocode → host search tools.
Read more
name: octocode-documentation description: "Use when writing or updating docs: README, API docs, runbooks, AGENTS.md, CLAUDE.md, ADRs, Diátaxis restructuring, or codebase documentation for humans or coding agents."
Octocode Documentation
Evidence-backed docs for humans and agents. Classify first. Gate writes. Prefer durable cross-refs over code dumps.
Flow
`UNDERSTAND → RESEARCH → CLASSIFY → OUTLINE GATE → WRITE → VERIFY`
Compress when targets and type are named. Expand when claims need verification.
Hard rules
- MUST verify claims in the repo before asserting them.
- MUST pick one mode and load its routes before writing.
- MUST gate creates/overwrites unless the user already approved targets this turn.
- MUST treat `AGENTS.md` as a docs index (links + non-obvious rules), not a content dump.
- Prefer durable pointers (module path, contract name, doc link) over line numbers and pasted code.
- FORBIDDEN: inventing commands, paths, APIs, or env vars.
- Keep one Diátaxis type per page; link siblings instead of mixing.
- Do not copy README/CONTRIBUTING into `AGENTS.md`, or paste large code blocks — link the source.
Stop when: outline gate awaits answer; write+verify finishes; fact missing (report gap); user cancels.
Routes
Load only what the step needs:
- Read `references/modes.md` when choosing mode or audience.
- Read `references/evidence-research.md` when gathering or verifying repo facts.
- Read `references/diataxis.md` when writing or reviewing human-docs.
- Read `references/agents-md.md` when writing or updating agent instruction files.
- Read `references/adr.md` when recording a decision.
- Read `references/agent-readable.md` before WRITE (cross-refs, density, durability).
- Read `references/write-verify.md` for outline gate, write steps, and verify checklist.
- Skip `references/references.md` during normal tasks (creation audit only).
Related
- Pure code/repo evidence with no docs deliverable → `octocode-research`.
- Authoring a `SKILL.md` → `octocode-skills`.
- Full multi-file pack → `octocode-documentation-writer` if installed.
- Unclear mode → ask once: agent-docs / human-docs / adr / codebase-pack.
- Conflicting conventions → surface; do not add a second scheme.
- Missing command → omit or mark unverified. No Octocode → host search tools.
Evidence-first code research for AI agents and developers. Octocode researches your local code and external code alike (GitHub repos, PRs, npm) with one toolset: ripgrep + AST search, trees, precise reads, and LSP.
Repo: bgauryy/octocode-mcp
Other skills on octocode.
- /octocode-benchmark
Use when planning, running, grading, or reporting the by-hand Octocode research benchmark — pairwise matchups (Octocode anchor vs one baseline: gh+RTK, gh+Headroom, or plain gh) over markdown questions, with a fresh isolated runner agent per (question, arm, pass), one blind
Open skill - /octocode-awareness
Use when coordinating work in a shared repo — multi-agent or solo across sessions: collision avoidance, handoffs, verification debt, durable memory/wiki, hooks setup/debug, and repo learning before planning, editing, reviewing, or testing.
Open skill - /octocode-brainstorming
Use when an idea needs disciplined exploration before building: generate options, test worth-building, map adjacent solutions, challenge assumptions, narrow scope, or choose Build RFC / Prototype / Narrow / Park — even without saying brainstorm.
Open skill - /octocode-chrome-devtools
Use when browser debugging, scraping a known URL efficiently, or running a multi-step page workflow needs real Chrome DevTools evidence: network, console, performance, DOM/CSS, screenshots/PDF, security, cookies/storage, click/fill/search flows, or auth-gated live pages via CDP
Open skill - /octocode-graph-eval
Use when measuring whether a change helped or looping until a target metric is hit — for one agent loop or a graph of loops (multi-agent workflow): ACCEPT/REVERT, keep/discard, goal→KPI contracts, eval suites, graders, held-out checks, benchmarks, TDD failing-case-first,
Open skill - /octocode-mannequin
Use when posing, animating, or explaining a 3D human skeleton, or driving a Three.js manikin as a live agent tool: anatomically-named bones/joints, range-of-motion-clamped movement, WebMCP-exposed pose tools — skeleton rig, joint constraints, forward kinematics, pose/animate a
Open skill

