Clean docs

Skill urmzd/dotfiles/dot_agents/skills/clean-docs

Cross-platform dotfiles managed by Chezmoi with Homebrew/apt and per-language version managers. One-command bootstrap for macOS and Linux with Neovim, Tmux, Zsh, and AI agent skills.

Install

npx -y skills add urmzd/dotfiles --skill clean-docs

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Clean 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.

SKILL.md

4.7 KB, as published. Nobody here has run it

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. Edit dot_agents/skills/ in the source tree.