Manage skills for visual understanding: register, list, invoke, and delete detection skills. Supports person detection, pedestrian counting, vehicle recognit...
Use when optimizing existing Claude skills, checking skill quality, auditing skill compliance, or when skills have obvious issues. Triggers on skill optimiza...
Automatically create and run basic unit/integration tests for OpenClaw skills to ensure code quality and prevent regressions.
Universal operational digest for agent skill stacks. Every scheduled skill logs its outcome with log-append.sh. Twice daily, digest-agent.sh reads the log, c...
OpenClaw 自我迭代升级技能。使用场景：配置自动修复、技能更新、依赖安装、版本检查、问题预防性修复。支持安全模式（需用户确认）和自动模式（
This skill should be used when users need to estimate test effort based on product requirements. It analyzes requirements, breaks down tasks, estimates test...
Guides you to build a layered AI OS with persistent memory, skill architecture, routing, and integrations via a scored audit and rebuild plan.
Optimize agent skills for discoverability on ClawdHub/MoltHub. Use when improving search ranking, writing descriptions for semantic search, understanding how the registry indexes skills, testing searc
Agent Skills (SKILL.md) builder, auditor, and improver for cross-platform LLM agents. Use for "skeall", "build a skill", "create skill", "improve skill", "au...
WeChat Mini Program development skill for building, debugging, previewing, testing, publishing, and optimizing mini program projects. This skill should be us...
Evaluates and governs all OpenClaw bot actions using YAML policies with tamper-evident audit logs to allow, deny, or require review before execution.
Tạo AI Skill mới từ ý tưởng hoặc quy trình công việc. Kết hợp phỏng vấn thông minh, pattern detection, và quantitative evaluation để tạo skill chất lượng pro...
Systematically discover, evaluate, compare, and assess OpenClaw skills to find the right, safe, and high-quality option for your specific task.
Run basic system commands to verify Python, working directory, file access, and command execution for OpenClaw environment validation and debugging.
OpenClaw Guardian is a comprehensive security control system for OpenClaw that intercepts high-risk operations and requires human confirmation before executi...
Convert any REST API into an OpenClaw skill automatically. Generates SKILL.md, scripts, and claw.json from OpenAPI spec or URL. Use when you want to quickly...
Unified TDD skill with three input modes — from spec, from task, or from description. Enforces test-first development using repository patterns, with proptes...
Adaptive testing engine with IRT/CAT, AI question generation, and personalized learning recommendations
Intelligently routes natural language user intents to the best matching registered agent skill using keyword and semantic matching with confidence scores.
> **⚡ Updated for Opus 4.5, Sonnet 4.5 & Haiku 4.5** — Three-tier model strategy for optimal performance
Helps verify that AI agent skills maintain consistent behavioral invariants across repeated executions — detecting the class of threat where a skill behaves...
Meta-skill for creating new agent skills — generates well-structured SKILL.md files with proper frontmatter, triggers, protocols, and rules. Use when buildin...
Orchestrates the continuous learning of new skills from arXiv papers. Use this to trigger a learning cycle, which fetches papers, extracts code/skills, and s...