ai-integration
Use when integrating LLMs (OpenAI, Qwen, Claude), extracting structured data from text, building prompts, parsing AI responses, handling JSON output, or implementing multi-step AI workflows
Skills correspondant au nom, à la description ou à l’auteur GitHub.
Use when integrating LLMs (OpenAI, Qwen, Claude), extracting structured data from text, building prompts, parsing AI responses, handling JSON output, or implementing multi-step AI workflows
當使用 test 開頭的 command、skill、agent 時,在執行過程中使用者提出改善建議,立即調整 .claude 目錄中對應的 md 檔案
Expert prompt engineering for Claude 4 models (Sonnet 4.5). Use when crafting prompts, optimizing AI responses, implementing chain-of-thought, or improving prompt clarity and effectiveness. Specializes in Claud...
Guide for creating valid skills. This skill should be ALWAYS used when users want to create a new skill or update an existing skill that extends Claude's capabilities with specialized knowledge, workflows, or t...
効果的なスキルを作成するためのガイド。ユーザーが専門知識、ワークフロー、ツール統合でClaudeの能力を拡張する新しいスキルを作成(または既存のスキルを更新)したい場合に使用します。
Phase 2-5 autonomous execution guidance - Activate when Claude needs to decide technical choices during implementation/testing/review/release phases
Comprehensive overview of Claude Code features, architecture, and capabilities. Learn about hooks, skills, commands, permissions, and best practices for configuring Claude Code as your AI development assistant....
効果的なスキルを作成するためのガイド。ユーザーがClaudeの機能を専門知識、ワークフロー、ツール統合で拡張する新しいスキルを作成(または既存のスキルを更新)したい場合に使用すべきスキルです。
Create, modify, and manage Claude Code subagents with specialized expertise. Use when you need to "work with agents", "create an agent", "modify an agent", "set up a specialist", "I need an agent for [task]", o...
Persistent memory for the skills project - auto-generates Claude Code skills from conversation transcripts
Reference for creating Claude-executable plans (PLAN.md)
Bootstraps a repository with project skills from the trusted internal skillregistry. Detect stack, install baseline + language skills into .codex/skills and .claude/skills, generate project-specific overlay ski...
Analyze Claude Code session transcripts (JSONL files) for context window content, token usage, and decision analysis. NOT for application logs (use analyze-logs instead). Use when debugging Claude behavior, inv...
Multi-agent collaboration. Use when working with other Claude Code sessions, coordinating work, or needing to communicate with teammates.
Authoritative & opinionated way for creating, updating, validating, and managing skills. Enforces the contextual framework and YAML frontmatter standards required by Claude Code.
Expert intégration IA/ML dans applications web - LLMs, RAG, vector databases, embeddings. Utilise ce skill quand: (1) intégration API OpenAI/Claude/Mistral, (2) mise en place RAG, (3) vector databases, (4) prom...
MiniMax MCP server integration with token-efficient AI delegation. Use for web search, image analysis, MCP server integration in terminal/desktop Claude, and Claude-MiniMax collaboration patterns. Provides work...
Replace with description of the skill and when Claude should use it.
自动监控 Claude Code 性能指标,包括操作耗时、失败率、效率评分,并提供语义化洞察
Set up and orchestrate parallel Claude Code agents using git worktrees. Use this skill when the user wants to parallelize a feature across multiple agents, spawn worktrees, or merge agent work back together.
Build production-ready AI agents using Claude Agent SDK (Python). Use when implementing agent workflows, SDK integration, one-shot queries, interactive conversations, custom MCP tools, permission control, CLAUD...
Run Claude Code programmatically via CLI (-p flag), Python SDK, or TypeScript SDK. For automation, CI/CD, session chaining, headless execution, and orchestrating multiple Claude instances. Triggers: programmati...
This skill should be used when managing the file-based todo tracking system in the .claude/todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and in...
Surface Claude's assumptions about a phase approach before planning
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.