Agent skill
YOLO Permissions — 工具调用安全分类器
YOLO权限分类器 — 工具调用前的AI辅助安全判断，参考Claude Code的auto mode设计
OpenClawDevelopment & Engineering
Ghenghis0
Agent skills
Reusable instructions for compatible AI agents.
Explore by field
Loading catalog totals…Field counts come from the latest full-catalog snapshot. A resource can belong to several fields and platforms.
Resources
Search resultsAgent skill
SafeExec - Safe Command Execution
Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agents need to execute shell commands that may be dangerous (rm -rf, dd, fork bombs, system directory modifications) or require human oversight....
OpenClawDevelopment & Engineering
Ghenghis0
Agent skill
evolve
OpenClaw × Claude Code 精华整合 — 记忆系统、提示词架构、熔断机制
OpenClawData & Analytics
Ghenghis0
Agent skill
Cache Monitor — 静态层 Hash 追踪
追踪静态层文件 hash，检测 prompt cache 失效。注册为 PreAgentStart 钩子，每次 session 启动时自动运行。有变更时输出警告，无变更静默通过。
OpenClawDevelopment & Engineering
Ghenghis0
Agent skill
memory-compaction
OpenClaw × Claude Code 精华整合 — 记忆系统、提示词架构、熔断机制
OpenClawDevelopment & Engineering
Ghenghis0
Agent skill
Smart Compact — 智能压缩策略选择
智能压缩决策 skill。根据当前 session 上下文类型自动选择压缩策略（BDX量化/代码开发/日常对话/混合），分析后报告预计保留率，等 Boss 确认后再执行。注册为 /smart-compact 命令。
OpenClawData & Analytics
Ghenghis0
Agent skill
compact-guardian
OpenClaw × Claude Code 精华整合 — 记忆系统、提示词架构、熔断机制
OpenClawDevelopment & Engineering
Ghenghis0
Agent skill
Compact Guardian — 压缩熔断守护
压缩熔断守护。当 memory-lancedb-pro 自动压缩（auto compaction）连续失败 3 次时，熔断机制触发，停止当前 session 的自动压缩并通过 Telegram 通知用户手动 /compact 处理。在记忆压缩失败后，激活此 skill 进行熔断检查。
OpenClawDevelopment & Engineering
Ghenghis0
No matching resources
Try a broader search or clear some filters.
Platform labels describe intended use. Read each resource's author credits, requirements and available access methods.