ai-team-library/claude/skills/update-docs/SKILL.md
# Skill: Update Docs ## Description Detects documentation drift and refreshes project documentation to match the current state of the codebase. Compares README, runbooks, ADR index, architecture overview, and onboarding guides against recent changes (code, configuration, dependencies, API surface) and produces a list of stale sections with proposed updates. This skill prevents the common failure mode where documentation is accurate at launch but decays silently as the code evolves. ## Trigger
npx skillsauth add beekeeper-lab/foundry ai-team-library/claude/skills/update-docsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Detects documentation drift and refreshes project documentation to match the current state of the codebase. Compares README, runbooks, ADR index, architecture overview, and onboarding guides against recent changes (code, configuration, dependencies, API surface) and produces a list of stale sections with proposed updates. This skill prevents the common failure mode where documentation is accurate at launch but decays silently as the code evolves.
/update-docs slash command.| Input | Type | Required | Description | |-------|------|----------|-------------| | project_dir | Directory path | Yes | Root of the project to check | | doc_paths | List of file paths | No | Specific docs to check; defaults to auto-discovery of all markdown files | | since | String | No | Git ref or date to scope change detection (e.g., "v1.0.0", "2025-01-01") | | composition_spec | File path | No | Composition spec for understanding project structure; auto-detected |
since marker.| Output | Type | Description | |--------|------|-------------| | drift_report | Markdown file | Summary of stale, missing, and outdated documentation with proposed updates | | proposed_updates | Sections in report | Specific text changes for each stale section | | completeness_check | Section in report | List of expected standard docs with present/missing status |
| Error | Cause | Resolution |
|-------|-------|------------|
| ProjectDirNotFound | Directory does not exist | Check the path |
| NoDocsFound | No markdown files found in the project | Create at minimum a README.md |
| GitHistoryUnavailable | Not a git repo; change detection limited to file modification times | Results may be less precise without git history |
| SinceRefInvalid | The since git ref or date is not recognized | Use a valid git tag, branch, commit hash, or ISO date |
development
# Skill: VDD (Verification-Driven Development) Gate ## Description Runs the programmatic VDD gate for a bean: parses the bean's `## Acceptance Criteria` section, dispatches each criterion's evidence type to the matching runner (test, lint, file, file-contains, or manual), aggregates the results into a pass/fail verdict, and writes a structured markdown report at `ai/outputs/tech-qa/vdd-<NNN>.md` (zero-padded NNN). This is the machine-checkable counterpart to the prose VDD policy in `ai/contex
tools
# Skill: Spawn Task ## Description Dispatches a single specialist persona to execute a single task with only that task's context. Auto-detects the runtime environment and chooses one of two execution paths: - **In tmux** (`$TMUX` set): spawn a worker in a git worktree using a child tmux window. Process-isolated, parallelizable, durable across the calling session's lifetime. Same pattern as `/spawn-bean` but at task granularity. - **Not in tmux**: invoke the `Agent` tool with `subagent_typ
development
# Skill: Orchestration Report ## Description Aggregates the per-bean **Orchestration Telemetry** blocks (BEAN-278) across recent Done beans and produces a markdown report that answers the architecture-aware-evaluation question: **is the orchestration paying for itself?** Distinct from `/telemetry-report` (which aggregates raw cost, duration, and tokens); this skill aggregates the orchestration-quality metrics layered on top — bounces, persona activations, contract violations, escape-hatch usag
development
# Skill: Health Check ## Description Runs all health checks defined in `ai/context/health-checks.md` and produces a table-format report. Can be called standalone or by other skills (e.g., `/long-run`). ## Trigger - Invoked by the `/health-check` slash command. - Called programmatically by `/long-run` at the start of each cycle. ## Inputs | Input | Type | Required | Description | |-------|------|----------|-------------| | health_checks | Markdown file | Yes | `ai/context/health-checks.md`