urmzd/dotfiles / dot_agents/skills/clean-docs
clean-docs
UnverifiedClean and modernize documentation in place. Enforce no em dashes, readable structure, proper Markdown formatting, accurate commands, current examples, resolved internal links, and user-focused guidance. Use when the user invokes /clean-docs, asks to clean docs, make docs up to date, improve README/AGENTS prose, remove AI-looking punctuation, or make docs easier for users to act on.
Clean Docs
Clean documentation so users can act on it quickly and agents can parse it reliably.
When to Use
- The user invokes
/clean-docs. - The user asks to clean, polish, modernize, or tighten docs.
- The user asks for docs to be accurate, up to date, readable, or user-focused.
- The user asks to remove em dashes, AI-looking prose, stale examples, or formatting drift.
- The task touches README, AGENTS.md, llms.txt, docs/, skill files, or agent files.
Default Workflow
-
Inventory docs. Find Markdown and text docs with
rg --files -g '*.md' -g '*.mdx' -g '*.txt'. -
Run the hygiene gate. Prefer the bundled checker:
checker="${CLAUDE_SKILL_DIR:-$HOME/.agents/skills}/sync-docs/scripts/check-doc-hygiene.sh" "$checker" .In a chezmoi source tree before apply, use:
dot_agents/skills/sync-docs/scripts/executable_check-doc-hygiene.sh . -
Verify claims before editing. Check commands with
--help, manifests, source files, tests, and existing configuration. Do not preserve claims that cannot be verified. -
Edit in place. Improve structure, wording, examples, and links. Keep the existing document's purpose and do not invent unsupported features.
-
Rerun the gate. Fix failures until text hygiene, embedded examples, and agentspec validation pass.
-
Report changes. Summarize files changed, facts verified, and any items that still need a human decision.
Cleanup Rules
| Rule | Standard |
|---|---|
| No em dashes | Do not use U+2014 anywhere in text, comments, help output, or docs. Use periods, colons, commas, or indexed bullets. |
| User-first | Lead with what the user can do, then prerequisites, then edge cases. |
| Accurate | Commands, paths, flags, and tool names must match current source or CLI help. |
| Focused | Remove filler, repeated setup prose, trailing summaries, and unsupported claims. |
| Scannable | Prefer short sections, tables for matrices, bullets for steps, and fenced code with language tags. |
| Actionable | Every major section should help users install, configure, run, verify, troubleshoot, or extend. |
File-Specific Owners
Use these standards when the file type appears:
| Artifact | Standard |
|---|---|
README.md | Read write-readme for structure, section order, quick start, examples, and Agent Skill placement. |
AGENTS.md | Read configure-ai for agent instructions and the skills-vs-docs boundary. |
llms.txt | Read create-llms-txt for LLM index structure. |
dot_agents/skills/*/SKILL.md | Read create-oss-skill for frontmatter, trigger descriptions, and progressive disclosure. |
| Multi-file docs trees | Use technical-documentation-architect for information architecture decisions. |
Editing Pattern
- Before: Long paragraphs, vague claims, stale commands, hidden prerequisites.
- After: Short purpose statement, exact command, expected result, next step.
Prefer this shape:
## Task
One sentence stating when to use this task.
```sh
command --flag value
```
Expected result: what success looks like.
Troubleshooting: one or two common failures with fixes.
Verification Checklist
- No em dash characters remain in tracked text files.
- Commands and flags match current CLI help or project manifests.
- Internal links point to existing files or anchors.
- Examples are runnable or clearly marked as illustrative.
- README and AGENTS.md agree on project purpose and key commands.
- Skill and agent files validate with
agentspec manage validate. - New or changed local skills are managed with
agentspec manage add "$(pwd)/dot_agents" --all-tools. - Local skill and agent hashes are accepted with
agentspec manage verify --accept --name <name>.
Gotchas
- Do not rewrite docs into marketing copy. Keep docs operational.
- Do not add placeholder links or sections.
- Do not use the checker as proof of accuracy by itself. It catches hygiene drift; factual claims still need source evidence.
- Do not edit deployed copies under
~/.agents/skills/for chezmoi-managed skills. Editdot_agents/skills/in the source tree.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 467k | Updated | Claude CodeCodex | Verified | Install |
| 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: 196k | Updated | Claude CodeCodex | Verified | Install |
| 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: 196k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 196k | Updated | Claude CodeCodex | Verified | Install |