📦 Metaskill — 智能体进化
v1.3.0通过深度纠错、迁移学习与主动模式识别，让 AI 智能体在出错后自我迭代，持续优化决策与泛化能力。
0· 456·1 当前·1 累计
by @fahrulalwan下载技能包
最后更新
2026/4/22
安全扫描
OpenClaw
可疑
medium confidenceNULL
评估建议
Key points to consider before installing or running Metaskill:
- Metadata mismatch: The registry says no env vars are required, but the code expects API keys (ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY) or a local Ollama server. Ask the publisher to correct the metadata or be prepared to set these env vars if you want full LLM functionality.
- Data sent to external LLMs: When the scripts run in LLM mode they send error descriptions and excerpts of your LEARNINGS.md to third-party servic...详细分析 ▾
ℹ 用途与能力
The skill claims to implement self-correction, transfer, and success-capture using LLMs; the included scripts implement exactly that and therefore the provider API keys and a local workspace are reasonable requirements. However, the registry metadata declares no required environment variables or primary credential while the code clearly expects provider API keys (ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY) or a local Ollama instance. This metadata mismatch is important and unexplained.
ℹ 指令范围
Runtime instructions and scripts operate on a workspace detected via git or OPENCLAW_WORKSPACE (or $HOME/.openclaw/workspace), read and append to LEARNINGS.md / WINS.md / ERRORS.md, and perform LLM calls for extraction/transfer. That behavior aligns with the stated purpose. The scripts will write into skills/self-improving-agent/.learnings/ if present — i.e., they may read/write another skill's learning files — which is related to purpose but expands the scope beyond a purely local, isolated skill.
✓ 安装机制
No install spec; skill is instruction+scripts only (no downloads or external installers). That lowers install-time risk — nothing is fetched or executed during install. Runtime does invoke local Python and network libraries as needed.
⚠ 凭证需求
Metadata lists no required env vars, but scripts/llm_provider.py expect environment API keys for providers (ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY) or a local Ollama service. The skill also uses OPENCLAW_WORKSPACE if set. Requesting LLM keys is proportionate to LLM use, but the omission from registry metadata is an incoherence. Additionally, using remote providers means user content (error descriptions, learnings) may be sent to third-party LLM endpoints — a privacy/exfiltration consideration that the metadata does not warn about.
ℹ 持久化与权限
The skill does not request 'always: true' and is user-invocable only. At runtime it creates and writes .learnings/ files under the workspace and will write into skills/self-improving-agent/.learnings/ if present. It does not modify other skills' configuration files, but it does read/write another skill's data area when available — this cross-skill file access is meaningful and should be acceptable only if you trust the skill and backups of that data exist.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.3.02026/2/28
NULL
● 可疑
安装命令
点击复制官方npx clawhub@latest install metaskill
镜像加速npx clawhub@latest install metaskill --registry https://cn.longxiaskill.com