ai-docs
$
npx mdskill add arcasilesgroup/ai-engineering/ai-docsUnified documentation skill covering the full project documentation lifecycle. Seven handlers manage changelogs, READMEs, solution intent documents, external documentation portals, and documentation quality verification.
SKILL.md
.github/skills/ai-docsView on GitHub ↗
--- name: ai-docs description: "Manages the documentation lifecycle: CHANGELOG, README, solution-intent architecture docs, external docs portals, and documentation quality gates. Auto-invoked by /ai-pr. Trigger for 'update the changelog', 'the README is stale', 'document this feature', 'docs portal needs updating', 'did we document all changes'. Not for blog or pitch content; use /ai-prose instead. Not for marketing collateral; use /ai-marketing instead." effort: mid argument-hint: "changelog|readme|solution-intent-init|solution-intent-sync|solution-intent-validate|docs-portal|docs-quality-gate" mode: agent tags: [documentation, architecture, governance] model_tier: sonnet mirror_family: copilot-skills generated_by: ai-eng sync canonical_source: .claude/skills/ai-docs/SKILL.md edit_policy: generated-do-not-edit --- # Documentation ## Purpose Unified documentation skill covering the full project documentation lifecycle. Seven handlers manage changelogs, READMEs, solution intent documents, external documentation portals, and documentation quality verification. ## When to Use - Changelog needs updating after code changes -> `changelog` - README files need updating to reflect project state -> `readme` - New project needs a solution intent document -> `solution-intent-init` - Architectural changes require solution intent sync -> `solution-intent-sync` - Pre-release or periodic health check on solution intent -> `solution-intent-validate` - External documentation portal needs updating -> `docs-portal` - Verify all documentation outputs cover semantic changes -> `docs-quality-gate` - Automatically invoked by `/ai-pr` via parallel subagent dispatch ## Process 1. **Detect handler** from arguments: one of the 7 handlers listed below 2. **Check gate** -- read `documentation.auto_update` flags from `.ai-engineering/manifest.yml` 3. **Execute handler** -- follow the matching handler in `handlers/` 4. **Report** -- present summary of actions taken ## Routing Table | Argument | Handler | Gate Flag | | -------------------------- | -------------------------------------- | ------------------------------------------- | | `changelog` | `handlers/changelog.md` | `documentation.auto_update.changelog` | | `readme` | `handlers/readme.md` | `documentation.auto_update.readme` | | `solution-intent-init` | `handlers/solution-intent-init.md` | none (manual invocation) | | `solution-intent-sync` | `handlers/solution-intent-sync.md` | `documentation.auto_update.solution_intent` | | `solution-intent-validate` | `handlers/solution-intent-validate.md` | none (read-only) | | `docs-portal` | `handlers/docs-portal.md` | `documentation.external_portal.enabled` | | `docs-quality-gate` | `handlers/docs-quality-gate.md` | none (always runs when dispatched) | If no argument is provided, display the routing table above and ask the user which handler to use. ## Quick Reference ``` /ai-docs changelog # update CHANGELOG.md from semantic diff /ai-docs readme # diff-aware README updates /ai-docs solution-intent-init # scaffold .ai-engineering/solution-intent.md /ai-docs solution-intent-sync # diff-aware sync from project state /ai-docs solution-intent-validate # completeness and freshness scorecard /ai-docs docs-portal # update external documentation portal /ai-docs docs-quality-gate # verify doc coverage of all changes ``` ## Examples ### Example 1 — sync the changelog before a release User: "update the changelog with everything since v1.2" ``` /ai-docs changelog ``` Reads recent commits + closed PRs since the last tagged release, drafts a Keep-a-Changelog formatted entry, opens for review. ### Example 2 — verify doc coverage before merge User: "did we document all the changes in this PR?" ``` /ai-docs docs-quality-gate ``` Diffs changed surfaces against documentation; flags un-documented public APIs or feature flags. ## Integration Called by: `/ai-pr` (step 7, parallel subagent dispatch). Calls: `handlers/changelog.md`, `handlers/readme.md`, `handlers/solution-intent-*.md`, `handlers/docs-portal.md`, `handlers/docs-quality-gate.md`. Reads: `manifest.yml`, `.ai-engineering/solution-intent.md`, `decision-store.json`. See also: `/ai-prose` (prose content), `/ai-marketing` (outreach). ## Governance Notes **Visual priority**: diagrams > tables > text. Every solution intent section MUST have at least one Mermaid diagram or table. Text accompanies but does not substitute visual representation. **TBD policy**: if a section's data is not defined, implemented, or in scope, mark it explicitly as TBD. NEVER invent data. **Ownership**: `.ai-engineering/solution-intent.md` is project-managed. Sync updates data but never removes user-authored content. `ai-eng update` does not touch this file. **Writing**: use `/ai-prose` patterns for document generation. Handlers define WHAT sections and data to gather; `/ai-prose` defines HOW to write them. ## References - `.github/skills/ai-pr/SKILL.md` -- PR workflow that dispatches documentation subagents - `.github/skills/ai-prose/SKILL.md` -- documentation writing patterns - `.ai-engineering/manifest.yml` -- documentation flags and portal config $ARGUMENTS
More from arcasilesgroup/ai-engineering
- ai-adviseProactive governance advisor — checks standards, decisions, and quality trends during development. Always advisory, NEVER blocks. Three modes: `advise` (post-edit), `gate` (pre-dispatch), `drift` (on-demand decision audit). Trigger for 'governance check', 'advise on this change', 'check for drift', 'is this aligned with active decisions', 'shift-left advisory'. Not for blocking gates — use /ai-verify. Not for narrative code review — use /ai-review.
- ai-analyze-permissionsUse when Claude Code keeps asking to approve commands you have already approved, when settings.local.json has grown large, or when you want to consolidate permission grants into wildcard patterns. Trigger for 'too many permission prompts', 'clean up permissions', 'audit my settings', 'consolidate allow rules'. Claude Code only — not available in GitHub Copilot, Antigravity, or Codex.
- ai-animationDesigns motion, transitions, and micro-interactions for UI components: spring animations, gestures, easing, staggers — taste-driven detail compounding. Trigger for 'animate this', 'add transitions', 'micro-interactions for', 'gesture design', 'swipe to dismiss', 'easing for this', 'stagger the'. Not for design systems; use /ai-design instead. Not for visual art; use /ai-visual instead. Not for testing animation code; use /ai-test instead.
- ai-autopilotDelivers large multi-concern specs and backlog runs autonomously: decomposes specs into sub-specs (or normalizes work items into a backlog DAG), deep-plans with parallel agents, builds a dependency DAG, implements in waves, runs a single final quality loop with one bounded quality-remediation pass (verify+guard+review on full changeset), delivers via PR. Trigger for 'implement spec-NNN end to end', 'autopilot this', 'autonomous delivery', 'decompose and ship', 'run the backlog', 'execute these GitHub issues', 'process the sprint backlog'. Invocation is the approval gate. Not for small or single-concern tasks; use /ai-build instead. Not for ambiguous requirements; use /ai-brainstorm first.
- ai-boardOperates the project board (GitHub Projects v2 or Azure DevOps): discovers configuration after install (fields, state mappings, process templates) and syncs work-item state at lifecycle transitions. Trigger for 'set up the board', 'configure our ADO board', 'discover board fields', 'move this issue to in-review', 'update the board', 'mark as in progress', 'sync the work item state'. Two subcommands: `discover` (post-install configuration write) and `sync` (lifecycle state transitions). Auto-invoked via `sync` by /ai-brainstorm, /ai-build, and /ai-pr; fail-open. Not for backlog execution; use /ai-autopilot --backlog instead.
- ai-brainstormForces rigorous design interrogation BEFORE any code: explores approaches, surfaces ambiguity, gathers evidence, produces an approved spec that becomes the contract for /ai-plan. Trigger for 'lets add X', 'how should we handle Y', 'whats the best approach', 'I am thinking about', 'what should we build for'. Not for existing approved specs; use /ai-plan instead. Not for execution; use /ai-build instead.
- ai-branch-cleanupCleans branches safely: switches to the default branch, prunes merged and squash-merged branches, syncs to remote, sweeps stale specs, rotates `.ai-engineering/runtime/` per retention policy. Trigger for 'tidy up', 'tidy branches', 'sync to main', 'delete old branches', 'start fresh', 'rotate runtime'. Auto-invoked by /ai-pr after merge. Not for committing changes; use /ai-commit instead. Not for code-level dead-code removal; use /ai-simplify instead.
- ai-buildCanonical implementation gateway: reads approved plan.md, resolves stack from manifest, deterministic-routes each task to its adapter, dispatches the build agent in an isolated worktree, runs TDD self-validation per task, then a single final quality loop with one bounded quality-remediation pass on the full changeset before /ai-pr. Trigger for 'go', 'start building', 'execute the plan', 'implement it', 'lets do this', 'build the plan', 'resume', 'continue'. Not without an approved plan; run /ai-plan first. Not for multi-concern specs needing decomposition; use /ai-autopilot instead. Not for a single function or subcomponent; use /ai-code.
- ai-codeWrites production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks, lightweight self-review. Trigger for 'implement this', 'write the code for', 'add X to Y', 'build this function', 'make this work'. Not for tests; use /ai-test instead. Not for debugging; use /ai-debug instead. Not for refactoring; use /ai-simplify instead. Not for executing an approved plan end-to-end; use /ai-build (the gateway).
- ai-commitRuns the governed commit pipeline: auto-branches from protected, stages selectively, formats and lints, scans for secrets, gates docs, composes a conventional message, pushes. Trigger for 'commit my changes', 'save my work', 'push this to remote', 'stage these files', 'ship it'. Not for opening a PR; use /ai-pr instead. Not for branch hygiene; use /ai-branch-cleanup instead.