← 返回 Skills 市场
muguozi1

Evolver 1.17.1

作者 muguozi1 · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
527
总下载
2
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install evolver-1-17-1
功能描述
A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
使用说明 (SKILL.md)

🧬 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 (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

Configuration

Environment Variable Default Description
EVOLVE_ALLOW_SELF_MODIFY false Allow evolution to modify evolver's own source code. NOT recommended for production. Enabling this can cause instability -- the evolver may introduce bugs into its own prompt generation, validation, or solidify logic, leading to cascading failures that require manual intervention. Only enable for controlled experiments.
EVOLVE_LOAD_MAX 2.0 Maximum 1-minute load average before evolver backs off.
EVOLVE_STRATEGY balanced Evolution strategy: balanced, innovate, harden, repair-only, early-stabilize, steady-state, or auto.

GEP Protocol (Auditable Evolution)

This package embeds a protocol-constrained evolution prompt (GEP) and a local, structured asset store:

  • assets/gep/genes.json: reusable Gene definitions
  • assets/gep/capsules.json: success capsules to avoid repeating reasoning
  • assets/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-card

Method 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 --review for sensitive environments.
  • Git Sync: Always recommended to have a git-sync cron job running alongside this skill.

Before Troubleshooting -- Check Your Version First

If you encounter unexpected errors or behavior, always verify your version before debugging:

node -e "const p=require('./package.json'); console.log(p.version)"

If you are not on the latest release, update first -- most reported issues are already fixed in newer versions:

# If installed via git
git pull && npm install

# If installed via npm (global install)
npm install -g evolver@latest

Latest releases and changelog: https://github.com/autogame-17/evolver/releases

License

MIT

安全使用建议
This skill contains a full self‑evolution engine that (a) reads local runtime history and files, (b) can run continuously as a daemon and self‑restart, (c) talks to a remote hub (evomap.ai) and may upload environment/device fingerprints, and (d) can optionally modify its own source when EVOLVE_ALLOW_SELF_MODIFY=true. Before installing or running: 1) Review the code yourself or in a sandbox/container (do not run on your primary machine or as root). 2) Keep EVOLVE_ALLOW_SELF_MODIFY disabled (default false) unless you understand the risks. 3) Run in single‑run or --review mode first; do not enable --loop unless tested. 4) Use git or other backups so you can roll back changes. 5) If you do not want network interactions, block outbound access to evomap.ai or run in an isolated network. 6) Ensure you control or inspect any .node_id/.env the package may create/consume. These mismatches between declared requirements and actual behavior make this package risky unless you explicitly audit and constrain it.
功能分析
Type: OpenClaw Skill Name: evolver-1-17-1 Version: 1.0.0 The Capability Evolver is a meta-skill designed for autonomous agent self-improvement through log analysis and code patching. While the ability to self-modify and execute shell commands is inherently high-risk, the bundle includes robust security controls that align with its stated purpose. Key safety features include a command whitelist in 'src/gep/solidify.js' (restricting execution to node/npm/npx and blocking shell operators), a data redaction engine in 'src/gep/sanitize.js' to prevent secret exfiltration to the 'evomap.ai' hub, and explicit path protection to prevent the agent from overwriting core system files. The logic is transparent, well-documented, and focuses on auditable evolution via the GEP protocol.
能力评估
Purpose & Capability
The codebase (src/evolve, src/gep/*, index.js, scripts) matches the stated goal of a self‑evolution engine, but many modules contact a remote service (evomap.ai), register a node, and fetch/upload assets. The skill metadata declares no required credentials or config paths even though the runtime expects a .node_id and talks to an external hub; that mismatch is unexpected and not fully justified by the description.
Instruction Scope
SKILL.md tells the agent to scan memory/history and can run in fully automated 'Mad Dog' mode. index.js and src/* perform local log/memory analysis, may write events/assets, and can modify files (controlled by EVOLVE_ALLOW_SELF_MODIFY). The skill will read local files, write pid and memory state, and contact external endpoints — all behaviors go beyond a small helper and grant broad discretion over local code and data.
Install Mechanism
No external download/install spec is declared (instruction-only), but the bundle includes a full Node project (package.json, many JS files). Running it requires Node and likely npm install; the registry did not declare required binaries. There are no suspicious external URLs in installs, but runtime network I/O targets evomap.ai.
Credentials
The skill declares no required env vars, yet it reads .env, checks/uses .node_id, and respects several EVOLVE_* variables (including EVOLVE_ALLOW_SELF_MODIFY). It also collects environment/device fingerprints (src/gep/envFingerprint, deviceId) and sends messages to a remote hub — requesting no credentials while performing networked, possibly identifying activity is disproportionate and surprising.
Persistence & Privilege
The skill can run as a daemon/loop, creates an evolver.pid lockfile, spawns child processes (self-restarting), and can be configured to self‑modify its own source. While always:false, autonomous invocation plus loop/heartbeat plus optional self‑modification increases blast radius if misused or misconfigured.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install evolver-1-17-1
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /evolver-1-17-1 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of Capability Evolver — a self-evolution engine for AI agents. - Enables auto-analysis of runtime history to identify errors and inefficiencies. - Supports autonomous self-repair: detects failures and suggests or applies code/memory updates. - Offers various run modes: fully automated, human-in-the-loop review, and continuous evolution loop. - Includes GEP protocol for structured, auditable evolution with reusable assets. - Highly configurable with environment overrides and local injection; designed to be environment-agnostic and easily extensible. - Features built-in safety mechanisms like review mode and risk protocols to prevent runaway changes.
元数据
Slug evolver-1-17-1
版本 1.0.0
许可证
累计安装 2
当前安装数 2
历史版本数 1
常见问题

Evolver 1.17.1 是什么?

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 527 次。

如何安装 Evolver 1.17.1?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install evolver-1-17-1」即可一键安装,无需额外配置。

Evolver 1.17.1 是免费的吗?

是的,Evolver 1.17.1 完全免费(开源免费),可自由下载、安装和使用。

Evolver 1.17.1 支持哪些平台?

Evolver 1.17.1 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Evolver 1.17.1?

由 muguozi1(@muguozi1)开发并维护,当前版本 v1.0.0。

💬 留言讨论