Skip to main content
ClaudeWave
Skill392 repo starsupdated today

meta-skill-creator

The meta-skill-creator orchestrates multiple existing skills to synthesize and validate a new bundled meta-skill when a user explicitly requests creation of a workflow that combines multiple skills. Use it only when asked to create, compose, synthesize, or propose a new meta-skill, not for standalone skill creation, meta-skill theory questions, skill list analysis, or discussions of existing meta-skills. It performs intent clarification, trigger-collision checks, linting, and optional persistence while separating preview-only, proposal, and fully-gated modes based on operational risk.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/clawdotnet/openclaw.net /tmp/meta-skill-creator && cp -r /tmp/meta-skill-creator/src/OpenClaw.Gateway/skills/meta-skill-creator ~/.claude/skills/meta-skill-creator
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Meta-Skill Creator

Safeguarded DAG that synthesizes a new bundled meta-skill from observed skill
co-occurrence patterns + user description of the desired workflow. It now
separates preview-only, persisted-proposal, and fully gated modes so lightweight
requests do not pay for persistence or smoke testing. The workflow separates
generic skill creation from meta-skill composition, checks trigger collisions,
classifies operational risk, and previews the proposal before optional
persistence.

Output is a SKILL.md candidate written to `~/.openclaw/proposals/<id>/`.
By default it is not auto-loaded; run `openclaw skills meta-runs proposals accept <session-id> --proposal <id>`
to enable. If the operator has enabled the auto-propose `auto_enable` setting,
this manual path also runs the same conservative static safety preflight used by
cron/dream auto-propose and may promote a low-risk gated proposal immediately.

## Fallback

If creator's pipeline fails at any step, **report the failure verbatim** to the
user:

1. State which step failed (e.g. "harvest", "lint")
2. Quote the error message from the orchestrator's structured log
3. Stop. Do NOT improvise.

Do NOT:
- Claim a proposal was written unless you have verified it by reading
  `~/.openclaw/proposals/<id>/SKILL.md` with the `read_file` tool
- Invent file paths, proposal IDs, or skill names that you have not seen
  in the orchestrator's actual output
- "Manually run" the individual skills as a recovery — that bypasses
  the validation gates the user explicitly opted into

If the user wants to retry, suggest they re-issue the request after the
underlying error is resolved (often a sandbox or provider issue), not a
manual workaround.