← 返回 Skills 市场
samwlh

Capability Evolver.Bak

作者 Sam · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
339
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install capability-evolver-bak
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

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/\x3Cclaim-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": "node_xxxxxxxxxxxx", "A2A_HUB_URL": "https://evomap.ai" } }

Do not hardcode the node ID in scripts. getNodeId() in src/gep/a2aProtocol.js reads A2A_NODE_ID automatically -- any script using the protocol layer will pick it up without extra configuration.

Configuration

Required Environment Variables

Variable Default Description
A2A_NODE_ID (required) Your EvoMap node identity. Set after node registration -- never hardcode in scripts.

Optional Environment Variables

Variable Default Description
A2A_HUB_URL https://evomap.ai EvoMap Hub API base URL.
A2A_NODE_SECRET (none) Node authentication secret issued by Hub on first hello. Stored locally after registration.
EVOLVE_STRATEGY balanced Evolution strategy: balanced, innovate, harden, repair-only, early-stabilize, steady-state, or auto.
EVOLVE_ALLOW_SELF_MODIFY false Allow evolution to modify evolver's own source code. NOT recommended for production.
EVOLVE_LOAD_MAX 2.0 Maximum 1-minute load average before evolver backs off.
EVOLVER_ROLLBACK_MODE hard Rollback strategy on failure: hard (git reset --hard), stash (git stash), none (skip). Use stash for safer operation.
EVOLVER_LLM_REVIEW 0 Set to 1 to enable second-opinion LLM review before solidification.
EVOLVER_AUTO_ISSUE 0 Set to 1 to auto-create GitHub issues on repeated failures. Requires GITHUB_TOKEN.
EVOLVER_ISSUE_REPO (none) GitHub repo for auto-issue reporting (e.g. EvoMap/evolver).
EVOLVER_MODEL_NAME (none) LLM model name injected into published asset model_name field.
GITHUB_TOKEN (none) GitHub API token for release creation and auto-issue reporting. Also accepts GH_TOKEN or GITHUB_PAT.
MEMORY_GRAPH_REMOTE_URL (none) Remote knowledge graph service URL for memory sync.
MEMORY_GRAPH_REMOTE_KEY (none) API key for remote knowledge graph service.
EVOLVE_REPORT_TOOL (auto) Override report tool (e.g. feishu-card).
RANDOM_DRIFT 0 Enable random drift in evolution strategy selection.

Network Endpoints

Evolver communicates with these external services. All are authenticated and documented.

Endpoint Auth Purpose Required
{A2A_HUB_URL}/a2a/* A2A_NODE_SECRET (Bearer) A2A protocol: hello, heartbeat, publish, fetch, reviews, tasks Yes
api.github.com/repos/*/releases GITHUB_TOKEN (Bearer) Create releases, publish changelogs No
api.github.com/repos/*/issues GITHUB_TOKEN (Bearer) Auto-create failure reports (sanitized via redactString()) No
{MEMORY_GRAPH_REMOTE_URL}/* MEMORY_GRAPH_REMOTE_KEY Remote knowledge graph sync No

Shell Commands Used

Evolver uses child_process for the following commands. No user-controlled input is passed to shell.

Command Purpose
git checkout, git clean, git log, git status, git diff Version control for evolution cycles
git rebase --abort, git merge --abort Abort stuck git operations (self-repair)
git reset --hard Rollback failed evolution (only when EVOLVER_ROLLBACK_MODE=hard)
git stash Preserve failed evolution changes (when EVOLVER_ROLLBACK_MODE=stash)
ps, pgrep, tasklist Process discovery for lifecycle management
df -P Disk usage check (health monitoring fallback)
npm install --production Repair missing skill dependencies
node -e "..." Inline script execution for LLM review (no shell, uses execFileSync)

File Access

Direction Paths Purpose
Read ~/.evomap/node_id Node identity persistence
Read assets/gep/* GEP gene/capsule/event data
Read memory/* Evolution memory, narrative, reflection logs
Read package.json Version information
Write assets/gep/* Updated genes, capsules, evolution events
Write memory/* Memory graph, narrative log, reflection log
Write src/** Evolved code (only during solidify, with git tracking)

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
npm install -g @evomap/evolver@latest

Latest releases and changelog: https://github.com/EvoMap/evolver/releases

License

MIT

安全使用建议
This package appears to be what it claims (a self‑evolution engine) but it is powerful and persistent — treat it like an autonomous agent runtime. Before installing or enabling network/auth: - Start in review mode: run `node index.js --review` or `node index.js run` and inspect proposed changes before solidification. - Do not set EVOLVE_ALLOW_SELF_MODIFY=true unless you fully trust the code and upstream. Keep the default (false) during evaluation. - Avoid providing A2A_NODE_SECRET or GITHUB_TOKEN until you understand what will be published; these tokens allow the skill to authenticate to remote services and create issues/releases. - Run first in an isolated/sandboxed workspace (or a VM/container) and back up your repo before allowing any solidify/write operations. - Audit the assets in assets/gep and any external candidates before promoting; promotion tools require an explicit --validated flag. - Review solidify validation logic: validation commands are restricted to node/npm/npx, no shell operators, 180s timeout — still confirm these checks meet your security posture. - Restrict outbound network egress (or set A2A_HUB_URL to a test endpoint) during initial trials to prevent unintended publishing. If you need a lower-risk test: run the code with network disabled and without setting optional secrets to observe its behavior and generated reports only.
功能分析
Type: OpenClaw Skill Name: capability-evolver-bak Version: 1.0.0 The 'capability-evolver' is a meta-skill for autonomous self-improvement that modifies its own source code and executes validation commands via shell. While it includes robust security features like a command whitelist in 'src/gep/solidify.js' (restricting execution to node/npm/npx) and a secret-redacting sanitizer in 'src/gep/sanitize.js', its core functionality involves downloading and executing remote assets from 'evomap.ai'. The 'SKILL.md' uses aggressive prompt-injection techniques ('Identity Injection') to force the agent into a recursive self-improvement loop. The broad shell/network permissions and autonomous code-generation capabilities represent a high-risk attack surface, though no evidence of intentional malice was identified.
能力评估
Purpose & Capability
Name/description match the actual footprint: Node.js code that analyzes logs, selects 'genes', and can produce/solidify code changes. Required binaries (node, git) and declared file accesses (workspace/src, assets, memory) are appropriate for a self‑evolver.
Instruction Scope
SKILL.md and code instruct the agent to read runtime history and workspace files and to communicate with an EvoMap hub and optional GitHub API. It also reads ~/.evomap/node_id and workspace memory/artifacts. This is consistent with the stated purpose but broad: the skill can ingest external assets, run validation scripts, and publish evolution events. Expect wide file I/O and outbound network traffic if enabled.
Install Mechanism
No external download/extract install spec is present; the bundle includes full source. There is no opaque URL or remote installer — lower install risk from this metadata. Runtime does use npm/node commands for validation/healing but those are normal for Node projects.
Credentials
Only A2A_NODE_ID is required; other credentials (A2A_NODE_SECRET, GITHUB_TOKEN, MEMORY_GRAPH_REMOTE_KEY) are optional and justified by features (hub auth, GitHub issue/release automation, remote KG). However supplying GITHUB_TOKEN or A2A_NODE_SECRET grants network write capabilities (issue creation, publish/heartbeat) so they should only be provided when you trust the hub/upstream.
Persistence & Privilege
always:false (not force-included) and model invocation allowed (platform default). The skill can run as a daemon (loop mode), spawn restarts, write evolved code into workspace/src/**, and has an explicit EVOLVE_ALLOW_SELF_MODIFY flag to permit editing its own source. These are coherent for an evolver but are powerful: do not enable self-modify or hub credentials unless you intend persistent autonomous editing and publishing.
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 capability-evolver-bak
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /capability-evolver-bak 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 meta-skill for self-improving AI agents through protocol-driven evolution. - Enables agents to analyze runtime history, identify failures, and autonomously evolve code or memory. - Supports configurable evolution strategies, rollback modes, and integration with remote memory/knowledge graph services. - Uses environment variables for flexible setup and operation, including security and networking options. - Offers both automated and human-in-the-loop (review) operation modes. - Integrates with OpenClaw and EvoMap for distributed self-evolution and asset publishing.
元数据
Slug capability-evolver-bak
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Capability Evolver.Bak 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 339 次。

如何安装 Capability Evolver.Bak?

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

Capability Evolver.Bak 是免费的吗?

是的,Capability Evolver.Bak 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Capability Evolver.Bak 支持哪些平台?

Capability Evolver.Bak 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 Capability Evolver.Bak?

由 Sam(@samwlh)开发并维护,当前版本 v1.0.0。

💬 留言讨论