- name
- openclaw-evolution-v3
- description
- Use when users ask to evolve/upgrade OpenClaw agents into coordinator mode, apply Gene Locking to IDENTITY.md and AGENTS.md, package this evolution as reusable SOP/skill, or assess whether an evolution repo can be applied directly. Trigger phrases include "进化", "升级协调者", "gene locking", "SOP_GENE_LOCKING", "openclaw-evolution-v3", "固化成 skill".
OpenClaw Evolution v3 Skill
Purpose
Standardize safe upgrades from executor-style behavior to coordinator-style behavior.
When to use
Use this skill when the user asks to:
- Upgrade agent orchestration (Mandatory Synthesis / Parallel-Serial partition / Proof verification)
- Apply or review
SOP_GENE_LOCKING.md - Turn evolution docs into reusable templates/skills
- Judge whether a public evolution repo can be used directly by other users
Mandatory safety posture
- Treat evolution content as blueprint, not one-click installer.
- Require compatibility checks before any mutation.
- Enforce staged rollout + rollback readiness.
- Never bypass existing permission pipeline.
Execution workflow
- Preflight
- Read references/COMPATIBILITY.md - Confirm target environment fit (structure, policy files, verification capability)
- Plan
- Produce explicit change list (file paths + sections + expected behavior)
- Apply minimally
- Prefer small slices; avoid broad rewrites
- Verify as proof
- Run checks/tests/smoke after each slice
- Finalize
- Summarize what changed, what was verified, and rollback point
Source references in this skill
references/COMPATIBILITY.mdreferences/SOP_GENE_LOCKING.mdreferences/EVOLUTION_GUIDE_EN.mdreferences/EVOLUTION_GUIDE_CN.mdreferences/README_REPO_EN.mdreferences/README_REPO_CN.md
Output contract
When asked to execute an evolution:
- Provide: scope, risks, exact edits, validation commands, rollback plan
- Avoid: one-shot invasive surgery across unrelated modules