self-improving-agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
SKILL.md
text/markdown · 21606 字节
assets/FEATURE_REQUESTS.md
text/markdown · 84 字节
assets/ERRORS.md
text/markdown · 75 字节
assets/SKILL-TEMPLATE.md
text/markdown · 3407 字节
assets/LEARNINGS.md
text/markdown · 1152 字节
scripts/activator.sh
text/x-sh · 680 字节
scripts/extract-skill.sh
text/x-sh · 5293 字节
scripts/error-detector.sh
text/x-sh · 1317 字节
hooks/openclaw/handler.js
text/javascript · 1620 字节
hooks/openclaw/HOOK.md
text/markdown · 589 字节
hooks/openclaw/handler.ts
application/typescript · 1872 字节
references/examples.md
text/markdown · 8291 字节
references/openclaw-integration.md
text/markdown · 6061 字节
references/hooks-setup.md
text/markdown · 5141 字节
Security Scan
状态
clean
OpenClaw
gpt-5-mini
OpenClaw 分析
The skill's code, hooks, and instructions are coherent with its stated purpose of capturing learnings and reminders; it doesn't ask for unrelated credentials or download arbitrary remote code, but you should review and opt-in to the hooks before enabling them.
置信度: high
VirusTotal
Type: OpenClaw Skill Name: self-improving-agent Version: 3.0.13 The 'self-improving-agent' skill bundle is designed to help AI agents track errors, corrections, and new insights by logging them to local markdown files. The bundle includes shell scripts (e.g., `extract-skill.sh`, `error-detector.sh`) and OpenClaw hooks (`handler.js`) that facilitate this workflow by providing reminders and scaffolding new skill directories. The instructions in `SKILL.md` explicitly advise against logging secrets or sensitive data, and the provided scripts contain basic path validation to prevent directory traversal. No evidence of data exfiltration, malicious execution, or unauthorized persistence was found.