skill-doc-authoring

Q: How do I install skill-doc-authoring?

Run npx skills add https://github.com/composio-community/opencode-skills --skill skill-doc-authoring in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/skill-doc-authoring/ (personal) or .claude/skills/skill-doc-authoring/ (project).

Q: Which AI agents can use skill-doc-authoring?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Q: Is skill-doc-authoring safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Q: Who maintains skill-doc-authoring?

It is published by composio-community in composio-community/opencode-skills. It has 45 recorded installs.

by composio-communityProductivity & Automation

Write a well-formed agent SKILL.md from a workflow, SOP, or repeated procedure. Use when the user wants to "create a skill", "turn this process into a skill", "document this workflow as a skill", or asks why a skill isn't triggering.

Installs: 45
Last 24h: —
Trending rank: —
Security: Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/composio-community/opencode-skills --skill skill-doc-authoring

01
Install
Run the command in your project. The CLI asks which agents to install for.
02
Describe the task
Ask your agent for something this skill covers. It loads skill-doc-authoring automatically when relevant.
03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Skill Doc Authoring

Produce a single valid SKILL.md that an agent will actually trigger and follow. The two failure modes this prevents: skills that never fire (weak description) and skills that fire but don't help (vague body).

File contract

Directory name and name: MUST match, lowercase, hyphens only, ≤ 64 chars.
Filename MUST be exactly SKILL.md (case-sensitive).
Frontmatter has exactly two keys: name, description. description ≤ 1024 chars.

skills/<skill-name>/SKILL.md

The description is the trigger

The agent decides whether to load the skill from the description alone. Write it in third person, lead with what it does, then "Use when …" with concrete user phrasings and situations. Include the trigger words a user would actually type.

Weak: Workflow for handling data.
Strong: Validate and clean CSV exports before import. Use when the user uploads a CSV, mentions "dirty data", or asks to "prep this for the database".

State when not to use it if a sibling skill is close — overlapping triggers cause the wrong skill to fire.

Body structure

Write for an agent with no project context. Concise, imperative, decision-oriented.

# Title
One-line purpose.
## When to use            # + when not to
## Procedure / The loop   # numbered, concrete, with commands
## Quality bar            # how to know it's done right
## Anti-patterns          # the tempting wrong moves

Rules:

Imperative voice ("Run X", "Verify Y"), not "the agent should consider".
Every step is verifiable or has a concrete command/example.
Cut "Notes", "Overview" padding, and restatements. If a line doesn't change what the agent does, delete it.
Put long reference material (schemas, tables, scripts) in sibling files and link them; keep SKILL.md skimmable (aim < ~200 lines).

Procedure

Extract the real procedure from the user (the SOP, the steps they actually take, the decisions and their criteria).
Identify triggers: what does someone say/do right before this skill is needed?
Draft the description (trigger test: would it fire on those phrasings? would it not fire on unrelated ones?).
Write the body to the structure above.
Validate: filename, name/dir match, frontmatter keys, description length.
Dry-run mentally: give the skill to a context-free agent on 2–3 sample requests — does it know exactly what to do?

Anti-patterns

Generic skeleton (Overview → "This skill enables…" → bulleted nouns → Notes) that fits any topic and helps with none.
Description that describes the domain but never says when to fire.
Restating general best practice the model already knows instead of the user's specific procedure.
One giant SKILL.md where a script + a short doc would serve better.

FAQ

What does the skill-doc-authoring skill do?

How do I install skill-doc-authoring?

Run npx skills add https://github.com/composio-community/opencode-skills --skill skill-doc-authoring in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/skill-doc-authoring/ (personal) or .claude/skills/skill-doc-authoring/ (project).

Which AI agents can use skill-doc-authoring?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is skill-doc-authoring safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains skill-doc-authoring?

It is published by composio-community in composio-community/opencode-skills. It has 45 recorded installs.