Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
Write or trim habit-hooks documentation under docs/. An agent skill from habit-hooks/habit-hooks.
Install Writing Docs
$ npx skills add habit-hooks/habit-hooks --skill writing-docs -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install habit-hooks/habit-hooks writing-docs --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/habit-hooks/habit-hooks.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/writing-docs .claude/skills/writing-docs && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "writing-docs" agent skill from https://github.com/habit-hooks/habit-hooks/tree/main/skills/writing-docs into .claude/skills/writing-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-docs", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/habit-hooks/habit-hooks/tree/main/skills/writing-docsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add habit-hooks/habit-hooks --skill writing-docs -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install habit-hooks/habit-hooks writing-docs --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/habit-hooks/habit-hooks.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/writing-docs .agents/skills/writing-docs && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "writing-docs" agent skill from https://github.com/habit-hooks/habit-hooks/tree/main/skills/writing-docs into .agents/skills/writing-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-docs", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add habit-hooks/habit-hooks --skill writing-docs -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install habit-hooks/habit-hooks writing-docs --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/habit-hooks/habit-hooks.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/writing-docs .cursor/skills/writing-docs && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "writing-docs" agent skill from https://github.com/habit-hooks/habit-hooks/tree/main/skills/writing-docs into .cursor/skills/writing-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-docs", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/habit-hooks/habit-hooks.git --path skills/writing-docs--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add habit-hooks/habit-hooks --skill writing-docs -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install habit-hooks/habit-hooks writing-docs --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/habit-hooks/habit-hooks.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/writing-docs .gemini/skills/writing-docs && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "writing-docs" agent skill from https://github.com/habit-hooks/habit-hooks/tree/main/skills/writing-docs into .gemini/skills/writing-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-docs", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install habit-hooks/habit-hooks writing-docsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add habit-hooks/habit-hooks --skill writing-docs -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/habit-hooks/habit-hooks.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/writing-docs .github/skills/writing-docs && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "writing-docs" agent skill from https://github.com/habit-hooks/habit-hooks/tree/main/skills/writing-docs into .github/skills/writing-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-docs", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add habit-hooks/habit-hooks --skill writing-docs -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install habit-hooks/habit-hooks writing-docs --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/habit-hooks/habit-hooks.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/writing-docs .opencode/skills/writing-docs && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "writing-docs" agent skill from https://github.com/habit-hooks/habit-hooks/tree/main/skills/writing-docs into .opencode/skills/writing-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-docs", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
writing-docs- GitHub stars
- 222
- Token cost
- ~1.4k tokens
- SKILL.md length
- 833 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Write or trim habit-hooks documentation under docs/. An agent skill from habit-hooks/habit-hooks.
- Works in 5 steps: Decide who the audience is. One doc, one… → Phrase the reader's expectation on… → Make the headlines deliver on those… → …
- Cutting any doc in this repo — keeps docs user-facing
- SKILL.md covers Properties of a doc, The process — writing or…, Cutting an existing doc and Before handing over
- Calls git
What it does
Writing Docs is an agent skill from habit-hooks/habit-hooks. Write or trim habit-hooks documentation under docs/. Use when creating, editing, reviewing or cutting any doc in this repo — keeps docs user-facing, short, and example-first. Exemplar of a finished cut commit f79594fd.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. The repository describes itself as: Automated quality checks that nudge AI coding agents toward better habits. The licence is MIT.
When your agent uses it
- Cutting any doc in this repo — keeps docs user-facing
Example prompts
- “/writing-docs”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Decide who the audience is. One doc, one reader, one job. Signal it by talking to that reader — never announce who the doc is for, and…
- Phrase the reader's expectation on opening it — one sentence: "I will find out how to disable a rule I don't agree with." If it takes two…
- Make the headlines deliver on those expectations. Name the problem being solved, never the mechanism — not the design name (## Advanced…
- Make the first paragraph summarise the content and place the doc in context. The summary itself tells the right reader they are in the…
- Write each section to deliver on the promise of its headline — and only that promise. Deliver with executable examples; reference data is…
What it can do on your machine
Read from SKILL.md and the folder at commit 5603331. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Writing Docs loads about 1.4k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 833 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from habit-hooks/habit-hooks at commit 5603331, republished under its MIT licence (© habit-hooks). 833 words, ~1,392 tokens.
Download SKILL.mdSave it as
.claude/skills/writing-docs/SKILL.md (or your agent's skills folder).- name
- writing-docs
- description
- Write or trim habit-hooks documentation under docs/. Use when creating, editing, reviewing or cutting any doc in this repo — keeps docs user-facing, short, and example-first. Exemplar of a finished cut commit f79594fd.
Writing habit-hooks docs
Everything in docs/ is user-facing: it onboards a user (install → run → interpret output → configure) or a contributor extending the system. Short, extremely clear, executable examples as the main communication device.
The finished-cut exemplar: git show f79594fd — docs/smell-vocabulary.md went from 211 lines to 13. What survived: the catalogue table, severity semantics, how to propose a smell. What went: per-plugin translation tables, design rationale, edge-case essays.
Properties of a doc
Audience and purpose
- One doc, one reader, one job — user onboarding or contributor extension. A doc serving both does neither well.
- Answers "what do I do", never "how did we decide". Rationale lives in PRs, commit messages and tests; mechanism walk-throughs live with the doc that owns them (architecture.md for the pipeline).
- Contribution sections state acceptance criteria ("name the smell by the problem it creates, not the tool"), not the reasoning behind them.
Examples are the message
- The executable example carries the meaning; prose between examples only supplies concepts and context the example can't show. A paragraph that re-explains what the example demonstrates gets deleted.
- Examples run as written — the spec harness enforces it, which is why examples are the safest device: they can't rot, prose can.
*.spec.mdfiles are documentation first, tests as a side effect. Trimming prose around cases is a docs change; deleting or editing cases changes test coverage and goes through normal test review, not a docs cut.
Stays true
- Contains nothing code can answer. State inventories — which tool maps to which smell, which plugins ship which sensors — go stale the release after they're written; link to where the truth lives instead of copying it.
- Each fact stated once. Cross-reference instead of restating; duplicated explanations drift apart.
Length
- Every sentence carries a fact the reader acts on. First cut: history, edge-case essays, "deliberate exception" narratives.
- Lead with the organising fact as a definition, in the fewest words. Never advertise what the doc lets you do — that restates the sections and reads as a sales pitch.
- One sitting per doc. A doc that needs a table of contents wants to be two docs — or its headlines to carry their promises, not an index table to carry them.
Format
- No hard newlines inside a paragraph; let the editor soft-wrap.
Boundaries
- Core docs are plugin-agnostic, same rule as the core code (see AGENTS.md). Per-plugin detail lives in the plugin.
- Concepts defined before first use. "Sensor", "mapper", "smell" mean the same thing in every doc.
Show full SKILL.md (427 more words)Show less
The process — writing or fixing any doc
Run these in order, before writing prose or cutting it. A doc that skips a step is why a reader bounces off it (docs/config.md before its 2026-09 rework: no audience, no promise, mechanism-named sections).
- Decide who the audience is. One doc, one reader, one job. Signal it by talking to that reader — never announce who the doc is for, and never narrate what the reader just did ("you open this page to…").
- Phrase the reader's expectation on opening it — one sentence: "I will find out how to disable a rule I don't agree with." If it takes two sentences, the doc has two jobs: split it.
- Make the headlines deliver on those expectations. Name the problem being solved, never the mechanism — not the design name (
## Advanced configuration) and not the syntax ([smells.<name>]):## Silence or demote a smell. If a headline can't carry its promise, rename the headline — don't paper over it with a task index. - Make the first paragraph summarise the content and place the doc in context. The summary itself tells the right reader they are in the right place.
- Write each section to deliver on the promise of its headline — and only that promise. Deliver with executable examples; reference data is a bullet list,
- **key**: description, never a table and never prose.
Cutting an existing doc
Fix structure first with the process (audience → expectation → headlines → first paragraph → sections), then cut prose.
- Delete every sentence whose absence changes nothing the reader does or understands.
- Delete state inventories code already answers; link to the truth instead.
- Move per-plugin detail to the plugin, and mechanism walk-throughs to the doc that owns them.
- If two distinct readers or jobs remain, split into two docs.
- Keep: reference tables the reader looks up, acceptance criteria, executable examples.
Check: read only the examples — does the doc still teach its job? Then read the prose; anything the examples already said is gone.
Cross-reference other docs with a link, never a summary.
Before handing over
For every line, ask as the reader with a task in hand, not the writer who wrote it: does the user need this — and is this the one place it is said? Repeated anywhere else, or nothing the user does depends on it → delete.
Intuitive rules (precedence, who-wins) are stated once, at the end, for the reader checking their intuition — never inline at each point of possible conflict.
Examples that demonstrate a default show nothing; the default is already stated. Delete them.
© habit-hooks, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/writing-docs of habit-hooks/habit-hooks.
Open the folder on GitHubat commit 5603331
Compare with similar skills
Writing Docs next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Writing Docs this skillhabit-hooks/habit-hooks | 222 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 4 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from habit-hooks/habit-hooks
Release Habit Hooks
habit-hooks/habit-hooks
Cut a new release of the habit-hooks packages. An agent skill from habit-hooks/habit-hooks.
Habit Hooks Prompting
habit-hooks/habit-hooks
Write or revise a habit-hooks coaching prompt. An agent skill from habit-hooks/habit-hooks.
Habit Hooks Review
habit-hooks/habit-hooks
Spawn a reviewer sub-agent to assess a change set against habit-hooks's coding principles.
Related
Categories
Questions about Writing Docs
What does Writing Docs do?
Write or trim habit-hooks documentation under docs/. An agent skill from habit-hooks/habit-hooks. Writing Docs is an agent skill from habit-hooks/habit-hooks. Write or trim habit-hooks documentation under docs/.
When should I use Writing Docs?
Writing Docs fits situations like: cutting any doc in this repo — keeps docs user-facing.
How do I install Writing Docs in Claude Code?
Run `npx skills add habit-hooks/habit-hooks --skill writing-docs -a claude-code`. Or copy the skill folder (skills/writing-docs in habit-hooks/habit-hooks) into .claude/skills/writing-docs in your project. Claude Code loads it when a task matches its description.
How do I install Writing Docs in Codex?
Run `npx skills add habit-hooks/habit-hooks --skill writing-docs -a codex`. Or copy the skill folder (skills/writing-docs in habit-hooks/habit-hooks) into .agents/skills/writing-docs in your project. Codex loads it when a task matches its description.
Can I use Writing Docs in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add habit-hooks/habit-hooks --skill writing-docs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-docs, .gemini/skills/writing-docs, .github/skills/writing-docs and .opencode/skills/writing-docs in your project.
What does Writing Docs need to run?
Going by SKILL.md and its folder, Writing Docs needs the command-line tools its instructions call (git).
Does Writing Docs access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Writing Docs safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Writing Docs use?
Writing Docs is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Writing Docs use?
About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Writing Docs?
Skills that share tags, products or a category with Writing Docs: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Writing Docs?
habit-hooks (a GitHub organization) maintains it in habit-hooks/habit-hooks, which has 222 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 2, 2026.
Source: habit-hooks/habit-hooks on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.