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...
README.md
text/markdown · 378 字节
SKILL.md
text/markdown · 20674 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 · 3357 字节
hooks/openclaw/HOOK.md
text/markdown · 589 字节
hooks/openclaw/handler.ts
application/typescript · 3438 字节
references/examples.md
text/markdown · 8290 字节
references/openclaw-integration.md
text/markdown · 6061 字节
references/hooks-setup.md
text/markdown · 5141 字节
skill-card.md
text/markdown · 2456 字节
Security Scan
状态
clean
OpenClaw
gpt-5.5
OpenClaw 分析
This skill persistently records local learning notes and optional reminders, but the behavior is disclosed, purpose-aligned, and not exfiltrating or destructive.
置信度: high
VirusTotal
Type: OpenClaw Skill Name: self-improving-agent Version: 3.0.21 The skill bundle implements a structured 'self-improvement' framework for OpenClaw agents, allowing them to log errors, corrections, and feature requests to local markdown files. It includes utility scripts (e.g., `extract-skill.sh`, `error-detector.sh`) and OpenClaw hooks (`handler.js`) designed to automate the capture of learnings and provide contextual reminders to the agent. While the skill facilitates the modification of agent instruction files like `SOUL.md` and `AGENTS.md`, it includes explicit safety guidelines advising the agent not to log secrets, tokens, or sensitive environment variables. The scripts utilize standard shell commands and include basic security checks, such as path traversal prevention, aligning entirely with the stated purpose of continuous workflow optimization.