/tidy-docs
Mechanical documentation hygiene. Spawns a doc-maintainer agent to audit all project documentation and fix correctness, completeness, freshness, and consistency issues autonomously within its authority. Surfaces anything requiring user judgment for approval.
$ npx -y skills add chrisallenlane/claude-swe-workflows --skill tidy-docs --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.
- You can call itInvoke it directly when you want it.
- Slash command
/tidy-docs
Context preview
The summary Claude sees to decide when to auto-load this skill.
Mechanical documentation hygiene. Spawns a doc-maintainer agent to audit all project documentation and fix correctness, completeness, freshness, and consistency issues autonomously within its authority. Surfaces anything requiring user judgment for approval.
SKILL.md
tidy-docs.SKILL.mdname: tidy-docs
description: Mechanical documentation hygiene. Spawns a doc-maintainer agent to audit all project documentation and fix correctness, completeness, freshness, and consistency issues autonomously within its authority. Surfaces anything requiring user judgment for approval.
model: opus
Tidy-Docs - Documentation Hygiene
Spawns a `doc-maintainer` agent to comprehensively audit all project documentation and fix the issues it finds. The find→fix seam is small — typos, stale code examples, broken links, freshness drift — so the skill runs as a tidy rather than a review.
Workflow
1. Spawn doc-maintainer agent
Spawn a `DOC - Maintainer` agent with the following prompt:
Perform a comprehensive review of ALL project documentation. This is a
standalone audit — do NOT scope to git diff. Instead, review every
documentation file in the project.
Steps:
1. Discover all documentation files (README.md, CLAUDE.md, CONTRIBUTING.md,
CHANGELOG.md, doc/, docs/, adr/, and any other .md files)
2. Review each for correctness, completeness, and freshness using your
full quality checklist (code-documentation consistency, completeness,
link validation, style consistency, freshness)
3. Fix issues you find autonomously (within your authority)
4. Report what you changed and any issues requiring user approval
If no documentation issues are found, report that and exit.
2. Report results
After the agent completes, present its findings to the user:
- What was reviewed
- What was changed (if anything)
- Issues requiring user approval (if any)
3. Commit (optional)
If changes were made, ask the user if they want to commit. If yes:
git add [specific files]
git commit -m "$(cat <<'EOF'
docs: tidy project documentation
[Brief description of changes made]
EOF
)"
Read more
name: tidy-docs description: Mechanical documentation hygiene. Spawns a doc-maintainer agent to audit all project documentation and fix correctness, completeness, freshness, and consistency issues autonomously within its authority. Surfaces anything requiring user judgment for approval. model: opus
Tidy-Docs - Documentation Hygiene
Spawns a `doc-maintainer` agent to comprehensively audit all project documentation and fix the issues it finds. The find→fix seam is small — typos, stale code examples, broken links, freshness drift — so the skill runs as a tidy rather than a review.
Workflow
1. Spawn doc-maintainer agent
Spawn a `DOC - Maintainer` agent with the following prompt:
Perform a comprehensive review of ALL project documentation. This is a standalone audit — do NOT scope to git diff. Instead, review every documentation file in the project. Steps: 1. Discover all documentation files (README.md, CLAUDE.md, CONTRIBUTING.md, CHANGELOG.md, doc/, docs/, adr/, and any other .md files) 2. Review each for correctness, completeness, and freshness using your full quality checklist (code-documentation consistency, completeness, link validation, style consistency, freshness) 3. Fix issues you find autonomously (within your authority) 4. Report what you changed and any issues requiring user approval If no documentation issues are found, report that and exit.
2. Report results
After the agent completes, present its findings to the user:
- What was reviewed
- What was changed (if anything)
- Issues requiring user approval (if any)
3. Commit (optional)
If changes were made, ask the user if they want to commit. If yes:
git add [specific files] git commit -m "$(cat <<'EOF' docs: tidy project documentation [Brief description of changes made] EOF )"
A system of composable software engineering workflows for Claude Code. Plan projects, implement tickets, and run quality passes — from a single ticket to a multi-batch project, using the same layered architecture.
Repo: chrisallenlane/claude-swe-workflows
Other skills on claude-swe-workflows.
- /bug-fix
Bug-fixing workflow that coordinates diagnosis, test-driven reproduction, root-cause analysis, and targeted fixes. Use when the user wants to fix a bug with thorough investigation and regression testing.
Open skill - /bug-hunt
Proactive bug-hunting workflow. Assesses codebase risk through complexity, coverage, and structural analysis, then spawns focused investigators that write reproducing tests to validate suspected bugs. Thoroughness over speed. Advisory only — produces findings and proposes
Open skill - /implement-batch
Multi-ticket batch workflow. Takes a batch of tickets, plans execution order, implements each via /implement in autonomous mode, runs cross-cutting quality passes, and presents results for final review.
Open skill - /implement-project
Full-lifecycle project workflow. Takes batched tickets, implements via /implement-batch, runs smoke tests, then executes a comprehensive quality pipeline (refactor, review-arch, review-test, tidy-docs, review-release). Maximizes autonomy with andon cord escape.
Open skill - /implement
Iterative development workflow that coordinates implementation, refactoring, QA, and documentation agents to complete features systematically. Use when the user wants a full development workflow with quality checks.
Open skill - /lead-bug-hunt
Autonomous bug-elimination loop. Iteratively invokes /bug-hunt and /implement-batch until findings converge below an operator-specified severity floor. At termination, runs /review-test scoped to the run's new reproducing tests and fixes quality issues above the floor.
Open skill

