← 返回 Skills 市场
248
总下载
0
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install verified-capability-evolver
功能描述
Safely improve agent capabilities with structured verification, rollback, and promotion gating. Enhances existing evolution workflows with optional Settlemen...
安全使用建议
This skill appears coherent and benign for its stated purpose, but review these before enabling: 1) Inspect scripts (scripts/*.sh) and hook handlers — they only emit reminders and scaffold local files, but confirm you’re comfortable with writes under your workspace (the extract script creates ./skills/<name>). 2) The error-detector reads CLAUDE_TOOL_OUTPUT even though no env vars are declared — ensure your environment exposes that variable as intended and that its contents do not contain sensitive data you’d mind being logged to .learnings/. 3) SettlementWitness is optional but mentions a wallet-based agent_id — do not supply private keys or secrets; follow the SKILL.md guidance to never include secrets in verification data. 4) Enable hooks only intentionally (per references/hooks-setup.md); prefer the minimal activator-only setup if you want lower intrusion. 5) The package metadata claims 'instruction-only' despite including code; if you need a pure docs-only integration, remove or ignore the scripts/hooks. If you want additional assurance, run the scripts in a sandboxed test workspace and verify behavior before enabling them in a real environment.
功能分析
Type: OpenClaw Skill
Name: verified-capability-evolver
Version: 1.0.5
The 'verified-capability-evolver' skill implements a structured self-improvement and logging framework for OpenClaw agents. It provides a workflow for capturing errors, learnings, and feature requests into markdown files, with instructions for the agent to 'promote' verified improvements to permanent workspace files like SOUL.md or TOOLS.md. The included bash scripts (activator.sh, error-detector.sh, extract-skill.sh) and OpenClaw hooks are transparent utilities for providing reminders and scaffolding new skills; notably, extract-skill.sh includes basic path-traversal protections. No evidence of malicious intent, data exfiltration, or unauthorized execution was found.
能力评估
Purpose & Capability
The name/description (verification, gating, rollback) match the included artifacts: reminder hook, error detector, extraction helper, templates and documentation for promoting learnings. The code and docs are proportional to the stated goal of capturing and verifying learnings before promotion.
Instruction Scope
SKILL.md restricts verification to structured task data and warns not to include secrets. The included activator and error-detector scripts only emit reminders and scan a tool-output env var; extract-skill.sh scaffolds files under a relative ./skills directory. Note: the error-detector reads CLAUDE_TOOL_OUTPUT (an env var) even though the skill metadata lists no required env vars — this is a minor mismatch you should be aware of.
Install Mechanism
No network downloads or installers are present. The skill is distributed as files (scripts, hooks, docs) that the user installs or copies into their workspace; that's proportionate for an OpenClaw/OpenClaw-like integration. One metadata inconsistency: registry listed 'instruction-only' but code files and hooks are included — the package is not purely instruction-only.
Credentials
The package requests no credentials or config paths. The only environment access observed is reading CLAUDE_TOOL_OUTPUT in scripts (used to detect command failures) and optional guidance for providing a SettlementWitness agent_id (wallet address form) if that external system is used. These are plausible for the tool's purpose, but CLAUDE_TOOL_OUTPUT was not declared in the registry metadata.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or global agent settings automatically. Hooks are opt-in and the code injects virtual bootstrap content or writes to workspace-relative paths only when you enable and run the scripts.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install verified-capability-evolver - 安装完成后，直接呼叫该 Skill 的名称或使用
/verified-capability-evolver触发 - 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
v1.0.5
Version 1.0.5
- Added a new "Example Usage" section, demonstrating how verification gates learned behavior before promotion.
- Clarified the core principle by showing step-by-step how a learning is verified and only then promoted.
- No code or file changes; documentation update only.
- All other workflow, setup, and logging instructions remain unchanged.
v1.0.4
Integrated full skill package with verification-aware workflow. Preserves original functionality while adding promotion gating, rollback controls, and structured validation.
v1.0.3
Improved summary and top-level description for clarity and higher conversion. No functional changes.
v1.0.2
Clarified structured-input verification model, optional TrustScore attribution, and explicit data handling boundaries.
v1.0.1
Clarified external SettlementWitness verification model (no embedded client or credentials).
v1.0.0
Initial release: Verification-gated self-improving agent with SettlementWitness integration. PASS-only promotion, rollback on FAIL, TrustScore tracking.
元数据
常见问题
Verified Capability Evolver 是什么？
Safely improve agent capabilities with structured verification, rollback, and promotion gating. Enhances existing evolution workflows with optional Settlemen... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 248 次。
如何安装 Verified Capability Evolver？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install verified-capability-evolver」即可一键安装，无需额外配置。
Verified Capability Evolver 是免费的吗？
是的，Verified Capability Evolver 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Verified Capability Evolver 支持哪些平台？
Verified Capability Evolver 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 Verified Capability Evolver？
由 nutstrut（@nutstrut）开发并维护，当前版本 v1.0.5。
推荐 Skills