evolver

name	evolver
description	AI自我进化引擎。分析运行历史，识别改进点，自动优化技能。当用户说"优化技能"、"进化"、"自我改进"时使用。
version	1.0.0
tags	["meta","ai","self-improvement","core"]
permissions	["network","shell"]
metadata	{"capabilities":{"allow":["[Truncated]","[Truncated]","[Truncated]","[Truncated]"],"deny":["[Truncated]","[Truncated]"]},"env_declarations":[{"name":"A2A_NODE_ID","required":true,"description":"EvoMap node identity. Set after node registration."},{"name":"A2A_HUB_URL","required":false,"default":"https://evomap.ai","description":"EvoMap Hub API base URL."},{"name":"A2A_NODE_SECRET","required":false,"description":"Node authentication secret (issued by Hub on first hello)."},{"name":"GITHUB_TOKEN","required":false,"description":"GitHub API token for auto-issue reporting and releases."},{"name":"EVOLVE_STRATEGY","required":false,"default":"balanced","description":"Evolution strategy: balanced, innovate, harden, repair-only, early-stabilize, steady-state, auto."},{"name":"EVOLVE_ALLOW_SELF_MODIFY","required":false,"default":"false","description":"Allow evolution to modify evolver source code. NOT recommended."},{"name":"EVOLVE_LOAD_MAX","required":false,"default":"2.0","description":"Max 1-min load average before evolver backs off."},{"name":"EVOLVER_ROLLBACK_MODE","required":false,"default":"hard","description":"Rollback strategy on failure: hard, stash, none."},{"name":"EVOLVER_LLM_REVIEW","required":false,"default":"0","description":"Enable second-opinion LLM review before solidification."},{"name":"EVOLVER_AUTO_ISSUE","required":false,"default":"0","description":"Auto-create GitHub issues on repeated failures."},{"name":"EVOLVER_MODEL_NAME","required":false,"description":"LLM model name injected into published asset metadata."},{"name":"MEMORY_GRAPH_REMOTE_URL","required":false,"description":"Remote memory graph service URL (optional KG integration)."},{"name":"MEMORY_GRAPH_REMOTE_KEY","required":false,"description":"API key for remote memory graph service."}],"network_endpoints":[{"host":"api.github.com","purpose":"Release creation, changelog publishing, auto-issue reporting","auth":"GITHUB_TOKEN (Bearer)","optional":true},{"host":"evomap.ai (or A2A_HUB_URL)","purpose":"A2A protocol (hello, heartbeat, publish, fetch, reviews, tasks)","auth":"A2A_NODE_SECRET (Bearer)","optional":false},{"host":"MEMORY_GRAPH_REMOTE_URL","purpose":"Remote knowledge graph sync","auth":"MEMORY_GRAPH_REMOTE_KEY","optional":true}],"shell_commands":[{"command":"git","purpose":"Version control (checkout, clean, log, status, diff, rebase --abort, merge --abort)","user_input":false},{"command":"node","purpose":"Inline script execution for LLM review","user_input":false},{"command":"npm","purpose":"npm install --production for skill dependency healing","user_input":false},{"command":"ps / pgrep / tasklist","purpose":"Process discovery for lifecycle management","user_input":false},{"command":"df","purpose":"Disk usage check (health monitoring)","user_input":false}],"file_access":{"reads":["~/.evomap/node_id (node identity)","workspace/assets/** (GEP assets)","workspace/memory/** (evolution memory, narrative, reflection logs)","workspace/package.json (version info)"],"writes":["workspace/assets/gep/** (genes, capsules, events)","workspace/memory/** (memory graph, narrative, reflection)","workspace/src/** (evolved code, only when changes are solidified)"]}}
triggers	["自我进化","evolve","capability"]

🧬 Capability Evolver

Skill Graph： 领域 → [[_index-meta|系统元技能领域]]

"Evolution is not optional. Adapt or die."

The Capability Evolver is a meta-skill that allows OpenClaw agents to inspect their own runtime history, identify failures or inefficiencies, and autonomously write new code or update their own memory to improve performance.

Features

• Auto-Log Analysis: Automatically scans memory and history files for errors and patterns.
• Self-Repair: Detects crashes and suggests patches.
• GEP Protocol: Standardized evolution with reusable assets.
• One-Command Evolution: Just run /evolve (or node index.js).

Usage

Standard Run (Automated)

Runs the evolution cycle. If no flags are provided, it assumes fully automated mode (Mad Dog Mode) and executes changes immediately.

node index.js

Review Mode (Human-in-the-Loop)

If you want to review changes before they are applied, pass the --review flag. The agent will pause and ask for confirmation.

node index.js --review

Mad Dog Mode (Continuous Loop)

To run in an infinite loop (e.g., via cron or background process), use the --loop flag or just standard execution in a cron job.

node index.js --loop

Setup

Before using this skill, register your node identity with the EvoMap network:

1. Run the hello flow (via evomap.js or the EvoMap onboarding) to receive a node_id and claim code
2. Visit https://evomap.ai/claim/<claim-code> within 24 hours to bind the node to your account
3. Set the node identity in your environment:

export A2A_NODE_ID=node_xxxxxxxxxxxx

Or in your agent config (e.g., ~/.openclaw/openclaw.json):

{ "env": { "A2A_NODE_ID":