capability-evolver
Skill1 starsChanged 12 days agoMITView on GitHub
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
- Reads credentials
6 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- autogame-17/evolvertheir own version, first seen Oct 8, 2026
- Dianel555/DSkillstheir own version, first seen Sep 6, 2026
- EvoMap/evolver-claude-code-plugintheir own version, first seen Aug 20, 2026
- EvoMap/evolvertheir own version, first seen Apr 18, 2026
- ftcalvinwang-ai/claude_skillsedited, first seen Mar 23, 2026
- kunwl123456/zeroclaw-skills-collectionedited, first seen Feb 19, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- kunwl123456/zeroclaw-skills-collection★ 2780% same
- ftcalvinwang-ai/claude_skills★ 045% same
Wrote their own version · 4
- autogame-17/evolver★ 9.1ksame name
- EvoMap/evolver★ 9.1ksame name
- Dianel555/DSkills★ 65same name
- EvoMap/evolver-claude-code-plugin★ 17same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository199 other files it gives its agents.
- activecampaignSkill
- adcp-advertisingSkill
- admapixSkill
- aegis-auditSkill
- afrexai-compliance-auditSkill
- afrexai-seo-content-engineSkill
- agent-browserSkill
- agentic-codingSkill
- agent-overflowSkill
- agent-skills-toolsSkill
- ai-ppt-generatorSkill
- airdrop-hunterSkill
- ai-web-automationSkill
- alicloud-ai-video-wan-r2vSkill
- alpha-finderSkill
- amap-trafficSkill
- amazon-product-apiSkill
- apertureSkill
- api-developmentSkill
- api-gatewaySkill
- asterSkill
- auto-replySkill
- auto-updaterSkill
- aviation-weatherSkill
- awwwards-designSkill
- base-8004Skill
- bioskillsSkill
- brainrepoSkill
- browserless-agentSkill
- browser-secureSkill
- btc15-autonomous-marketSkill
- buy-anythingSkill
- byteroverSkill
- cal-com-automationSkill
- catalogSkill
- chargebeeSkill
- clawcostSkill
- clawdbot-documentation-expertSkill
- clawdbot-for-vcsSkill
- clawddocsSkill
- claw-syncSkill
- claw-trader-liteSkill
- clean-codeSkill
- cloudphoneSkill
- cls-certifySkill
- codebergSkill
- code-mentorSkill
- commit-analyzerSkill
- competitor-analysis-reportSkill
- content-ideas-generatorSkill
- content-ideasSkill
- contract-generatorSkill
- conventional-commitsSkill
- copywritingSkill
- crypto-payments-ecommerceSkill
- custom-smtp-senderSkill
- dashboard-manager2Skill
- data-analystSkill
- docker-sandboxSkill
- elite-longterm-memorySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 30
If you want to review changes before they are applied, pass the --review flag.
- Distinctive: line 51
Only the DNA emoji is allowed in documentation.
- Distinctive: line 74
If Errors Found -> Repair Mode (Fix bugs).
- Distinctive: line 75
If Stable -> Forced Optimization (Refactor/Innovate).
- Very specific: line 79
Review Mode: Use --review for sensitive environments.
- Distinctive: line 80
Git Sync: Always recommended to have a git-sync cron job running alongside this skill.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
迁移说明:本技能原为 OpenClaw / ClawHub 生态技能,现已转为 WorkBuddy 技能规范。正文如出现
openclaw/clawhub/claw命令或~/.openclaw路径,请忽略该命令形式,改用 WorkBuddy 等价操作:技能目录 =~/.workbuddy/skills/<name>/;装包用 pip / npm;联网用 WebSearch / WebFetch;读写文件用 Read / Write / Edit;执行命令用 Bash(Windows 走 PowerShell 工具)。
🧬 Capability Evolver
"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(ornode 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.jsReview 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 --reviewMad 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 --loopGEP Protocol (Auditable Evolution)
This package embeds a protocol-constrained evolution prompt (GEP) and a local, structured asset store:
assets/gep/genes.json: reusable Gene definitionsassets/gep/capsules.json: success capsules to avoid repeating reasoningassets/gep/events.jsonl: append-only evolution events (tree-like via parent id)
Emoji Policy
Only the DNA emoji is allowed in documentation. All other emoji are disallowed.
Configuration & Decoupling
This skill is designed to be environment-agnostic. It uses standard OpenClaw tools by default.
Local Overrides (Injection)
You can inject local preferences (e.g., using feishu-card instead of message for reports) without modifying the core code.
Method 1: Environment Variables
Set EVOLVE_REPORT_TOOL in your .env file:
EVOLVE_REPORT_TOOL=feishu-cardMethod 2: Dynamic Detection
The script automatically detects if compatible local skills (like skills/feishu-card) exist in your workspace and upgrades its behavior accordingly.
Safety & Risk Protocol
1. Identity & Directives
- Identity Injection: "You are a Recursive Self-Improving System."
- Mutation Directive:
- If Errors Found -> Repair Mode (Fix bugs).
- If Stable -> Forced Optimization (Refactor/Innovate).
2. Risk Mitigation
- Infinite Recursion: Strict single-process logic.
- Review Mode: Use
--reviewfor sensitive environments. - Git Sync: Always recommended to have a git-sync cron job running alongside this skill.
License
MIT
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

