meta-skill-creator

name	meta-skill-creator
description	Use this meta-skill instead of answering directly only when the current user explicitly asks to create, compose, synthesize, or propose a new meta-skill that orchestrates multiple existing skills. It uses multi-skill orchestration for intent clarification, optional history mining, trigger-collision checks, linting, smoke/runtime gates, preview, and optional proposal persistence. Do not use it for creating a normal standalone skill, asking how meta-skills work, analyzing pasted skill lists, or discussing existing meta-skills.
kind	meta
meta_priority	90
always	false
final_text_mode	step:final_response
triggers	["新增 meta 技能","组合现有 skill 成 meta-skill","create a meta-skill","new meta-skill","orchestrates existing skills","compose existing skills","synthesize meta-skill","compose meta-skill"]
provenance	{"origin":"openclaw.net","license":"MIT"}
composition	{"steps":[{"id":"clarify_intent","kind":"llm_chat","with":"[Truncated]"},{"id":"creator_clarify","kind":"user_input","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower) and 'needs_clarification: yes' in (outputs.clarify_intent | lower)","clarify":"[Truncated]"},{"id":"normal_skill_exit","kind":"tool_call","depends_on":"[Truncated]","when":"'route: normal-skill' in (outputs.clarify_intent | lower)","tool":"emit_text","tool_args":"[Truncated]"},{"id":"creator_mode","kind":"llm_classify","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower)","output_choices":"[Truncated]","with":"[Truncated]"},{"id":"harvest","kind":"skill_exec","skill":"history-explorer","skill_exec_entrypoint":"scripts/explore.py","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower)","on_failure":"harvest_empty","skill_exec_stdin":"{\n \"id\": \"{{ inputs.session_id }}\",\n \"history\": {{ inputs.session_history | default('[]') }},\n \"metaRunHistory\": {{ inputs.session_meta_runs | default('[]') }}\n}\n","with":"[Truncated]"},{"id":"harvest_empty","kind":"tool_call","tool":"emit_text","tool_args":"[Truncated]"},{"id":"pick_pattern","kind":"llm_classify","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower)","output_choices":"[Truncated]","with":"[Truncated]"},{"id":"fill_slots","kind":"tool_call","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower)","tool":"meta_skill_fill_slots","tool_args":"[Truncated]"},{"id":"assemble","kind":"tool_call","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower)","tool":"meta_skill_assemble","tool_args":"[Truncated]"},{"id":"collision_check","kind":"llm_chat","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower)","with":"[Truncated]"},{"id":"lint","kind":"tool_call","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower)","tool":"meta_skill_lint_run","tool_args":"[Truncated]"},{"id":"risk_classify","kind":"llm_chat","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower)","with":"[Truncated]"},{"id":"single_model_baseline","kind":"llm_chat","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower) and outputs.creator_mode == 'FULL_GATED'","with":"[Truncated]"},{"id":"acceptance_compare","kind":"llm_chat","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower) and outputs.creator_mode == 'FULL_GATED'","with":"[Truncated]"},{"id":"smoke","kind":"tool_call","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower) and outputs.creator_mode != 'PREVIEW_ONLY'","tool":"meta_skill_smoke_run","tool_args":"[Truncated]"},{"id":"runtime_e2e","kind":"tool_call","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower) and outputs.creator_mode == 'FULL_GATED'","tool":"meta_skill_runtime_e2e_run","tool_args":"[Truncated]"},{"id":"preview","kind":"llm_chat","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower)","with":"[Truncated]"},{"id":"persist","kind":"tool_call","depends_on":"[Truncated]","when":"'route: meta-skill' in (outputs.clarify_intent | lower) and outputs.creator_mode != 'PREVIEW_ONLY'","tool":"meta_skill_persist_proposal","tool_args":"[Truncated]"},{"id":"final_response","kind":"tool_call","depends_on":"[Truncated]","tool":"emit_text","tool_args":"[Truncated]"}]}

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.