Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

skill-creator · openclaw — Claude skill: build and validate SKILL.md files

A skill for writing, repairing and reviewing other skills. It splits behaviour into branches, sets the frontmatter and sorts resources into folders. Useful once your skill folder gets crowded.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add openclaw/openclaw --skill skill-creator -a claude-code
Open on GitHub

What skill-creator does

skill-creator walks you through five steps. First you pin down the contract: every branch needs a trigger, an expected outcome and somewhere to persist. Then you pick how the skill gets invoked — model-discoverable through a written description, manual-only with disable-model-invocation: true, or a direct tool command using command-dispatch: tool.

Next comes structure. The shared ordered procedure lives in SKILL.md, and each step ends with a completion criterion you can actually check. Branch-only detail goes to references/, repeatable helpers to scripts/, output files to assets/, optional UI metadata to agents/. Routing conditions stay in description; the body opens with execution.

Validation closes the loop: python {baseDir}/scripts/quick_validate.py plus a focused test run for every helper you touched. Required frontmatter is name and description; add the optional fields only when they change runtime behaviour or discovery. Worth installing if you hand-write skills and keep chasing broken resource pointers. For a single throwaway skill, skip it.

What it helps with

  • turn scattered process notes into a working SKILL.md
  • fix a skill the model no longer discovers
  • move branch detail into references and scripts
  • check frontmatter and resource pointers before committing
  • restructure someone else's skill to match your folder layout

Example prompts for the agent

  • Create a skill that builds release notes from git log
  • Review my SKILL.md: frontmatter, resource pointers, step completion criteria
  • Split this skill into branches and move the detail into references/

How to install skill-creator

1Skills CLI (Vercel)

npx skills add openclaw/openclaw --skill skill-creator -a claude-code

2Manually: put the files in place

~/.claude/skills/skill-creator/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/skill-creator/

From the same set45

The whole set →
summarize openclaw Runs a CLI tool to summarize or transcribe web articles, YouTube videos, podcasts, and local PDF documents directly within your AI assistant. Claude Code CX Codex Cursor +1 26,900installs weather openclaw This skill fetches current conditions and forecasts for a city, region, airport code, or coordinates. Use it to check rain and temperature or plan a trip. Claude Code CX Codex Cursor +1 9,300installs gog openclaw Guides an agent using the gog CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. Use it when Google Workspace tasks need to run from a terminal. Claude Code CX Codex Cursor +1 8,500installs tmux openclaw Lets an agent work with live tmux sessions: read pane output, send keys and text, wait for a prompt line to show up. Claude Code CX Codex Cursor +1 8,400installs openai-whisper openclaw This skill lets your agent call the Whisper CLI to transcribe audio on your own machine. No API key needed. Claude Code CX Codex Cursor +1 7,100installs nano-pdf openclaw Edit PDF pages with plain text instructions through the nano-pdf CLI. Useful when you need to fix a typo or swap a heading without leaving your terminal. Claude Code CX Codex Cursor +1 7,100installs coding-agent openclaw This skill sends large coding tasks to Codex, Claude Code, or OpenCode as background workers. Use it for refactors, PR reviews, and issue-to-PR work. Claude Code CX Codex Cursor +1 6,500installs obsidian openclaw Interacts with Obsidian vaults through the official obsidian CLI. It helps agents read, search, and update notes or tasks without leaving the chat. Claude Code CX Codex Cursor +1 6,400installs

Other versions of skill-creator

skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs skill-creator official openai Official guide for drafting and updating agent skills. It structures procedures, bundled scripts, and documentation while keeping token overhead low. Claude Code CX Codex Cursor +1 4,900installs skill-creator langchain-ai Guides agents in scaffolding, validating, and structuring custom skills. It cuts token overhead by separating scripts, docs, and assets. Claude Code CX Codex Cursor +1 1,300installs skill-creator microsoft A guide for creating and updating AI coding skills, with a focus on Azure SDKs and Microsoft Foundry. Use it when a skill needs a clear structure. Claude Code GitHub Copilot 106installs

Similar

typesafe-ai typesafe-ai Guides agents on integrating TypeSafe Decision Models like Jev, answering typed questions about state with calibrated probabilities instead of brittle prompts. Claude Code CX Codex Cursor +1 95,600installs watch bradautomates Analyzes a video from a URL or local path, collects frames and a transcript, then lets the agent answer questions about the footage. Useful for video review inside an IDE. Claude Code CX Codex Cursor +1 17,100installs gemini-api-dev official google-gemini Guides coding agents to write Gemini API code in Python and TypeScript using current SDKs, interaction endpoints, and active models. Claude Code CX Codex Cursor +1 25,100installs hindsight-docs vectorize-io This skill gives AI agents Hindsight documentation for architecture, APIs, configuration, and SDKs. Use it when adding Hindsight memory to an agent. Claude Code CX Codex Cursor +1 9,100installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. Claude Code CX Codex Cursor +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. Claude Code Claude.ai 130,949installs

Questions about skill-creator

How do I install skill-creator in Claude?

Run npx skills add openclaw/openclaw --skill skill-creator -a claude-code. The skill lands at ~/.claude/skills/skill-creator/SKILL.md.

What does skill-creator do?

It helps you author a new skill or rework an existing one: map behaviour into branches, choose the invocation mode, lay out resources, then validate the result.

Which frontmatter fields are required?

name and description. The rest — metadata, homepage, license, allowed-tools, user-invocable, disable-model-invocation, command-dispatch, command-tool, command-arg-mode — are worth adding only when they change how the skill runs or how it is found.

Source text

SKILL.md · MIT 
---
name: skill-creator
description: "Author or review AgentSkills: create, repair, validate, or restructure SKILL.md files and bundled resources."
---

# Skill Creator

## Workflow

1. Establish the contract.
   - Read the existing skill and its resources, or collect concrete requests for a new skill.
   - Separate actual workflow branches from synonyms for the same branch.
   - **Done when:** every branch has a concrete trigger, expected outcome, and persistence target.

2. Choose invocation.
   - Model-discoverable: write a model-facing `description`; omit `disable-model-invocation`.
   - Manual-only: set `disable-model-invocation: true`; write a human-facing summary.
   - Direct tool command: add `command-dispatch: tool`, `command-tool`, and `command-arg-mode` only when the command bypasses the model.
   - **Done when:** frontmatter matches how the skill will actually be reached.

3. Structure the skill.
   - Map shared ordered procedure to `SKILL.md`; end every step with a checkable completion criterion and finish with verification.
   - Keep routing conditions in `description`; start the body with execution.
   - Map branch-only detail to `references/`, repeatable helpers to `scripts/`, output resources to `assets/`, and optional UI metadata to `agents/`.
   - **Done when:** every planned resource has one purpose and a direct pointer from `SKILL.md`.

4. Draft and persist.
   - Live workspace skill: use `skill_workshop` to create or revise a pending proposal; keep live files unchanged until apply.
   - Repository-owned skill source: use the repository's normal edit and review workflow.
   - **Done when:** the proposal or source diff implements every branch from step 1 and contains every resource from step 3.

5. Validate.
   - Run `python {baseDir}/scripts/quick_validate.py <skill-directory>` and execute every touched helper's focused test.
   - **Done when:** frontmatter passes, resource pointers resolve, and every touched helper passes its focused test.

## Frontmatter

Required: `name`, `description`.

OpenClaw also supports `metadata`, `homepage`, `license`, `allowed-tools`, `user-invocable`, `disable-model-invocation`, `command-dispatch`, `command-tool`, and `command-arg-mode`. Add optional fields only when they change runtime behavior or discovery.

© openclaw · MIT · openclaw/openclaw

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor