Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...
Create effective Claude Code skills and agents. Covers official frontmatter spec, global vs project scope, and the formula - references activate dormant knowledge, pet hates stop bad defaults,...
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...
Automatic support for (Claude) Skills for any coding agent that supports AGENTS.md
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable -...
Download and install Claude Code skills from various sources. Supports GitHub repositories, compressed archives (.zip, .tar.gz, .skill), and direct URLs. Use when user wants to download, install,...
Replace with description of the skill and when Claude should use it.
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...
Meta-skill for optimizing skill descriptions using SDS standard and seven core techniques. Use when refining skill descriptions for improved trigger rates (examples include optimizing existing...
Use when the user wants to find NEW external skills for a project, build a skill stack from external registries, or compare external options against project needs. Do not use for questions about...
A test skill for validating the packager
安裝 Agent Skills 到本機。當用戶想要「安裝技能」、「新增 skill」、「從 GitHub 安裝 skill」、或「install skill from repo」時觸發此技能。
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than...
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than...
Interactive spec-driven development workflow with phase-by-phase confirmation. Each phase waits for user confirmation before proceeding. Trigger phrases include "spec-flow", "spec mode", "need a...
Meta-skill enforcing skill discovery and invocation discipline through mandatory workflows. Use when starting any conversation to check for relevant skills before any response, ensuring...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...