GitHub
claude-expert
Claude Code mastery skill. Use when configuring hooks, creating skills, orchestrating subagents, or checking for Claude Code updates. Triggers: 'create a hook', 'make a skill', 'spawn subagent', 'check for upda...
☆ 1查看技能
tools llm ai AI 技能
发现 tools llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
分类目录: tools llm ai
tools llm ai 清除筛选
全部技能
GitHub
customize
Create personalized skills and agents based on user's background and needs. Use when user asks to 'customize claude', 'create a skill', 'make an agent for', 'personalize my setup', 'help me automate', or when y...
☆ 1查看技能
GitHub
self-improve
Learning loop for self-improvement. Use when you notice a teachable moment, want to update CLAUDE.md, create a new skill, or reflect on what worked/failed. Triggers: 'remember this', 'update my config', 'that w...
☆ 1查看技能
GitHub
session-logs
Search past Claude Code sessions for context, decisions, errors, and patterns. Use when user asks to 'find that conversation', 'what did we discuss', 'search sessions', or when you need to recover context from...
☆ 1查看技能
GitHub
claude-chrome
Automate tasks using the Claude Chrome extension via UI automation. Use when you need to delegate browser-based work to Claude in Chrome, browse websites, or when the user asks to "use Claude in Chrome" or "sen...
☆ 1查看技能
GitHub
create-derpcode-problem
This skill allows the agent to create new coding problems for the DerpCode platform. This skill should be used when asked to create new DerpCode coding problems.
☆ 1查看技能
GitHub
app-platform-sandbox
Create and manage isolated container sandboxes for AI agent code execution. Use when you need ephemeral environments to run untrusted code, execute agent workflows, or test in isolation. NOT for debugging exist...
☆ 1查看技能
GitHub
ai-services
Configure DigitalOcean Gradient AI serverless inference and Agent Development Kit. Use when adding LLM inference, model access keys, serverless AI endpoints, or building AI agents with ADK on App Platform.
☆ 1查看技能
GitHub
ai-multimodal
Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, musi...
☆ 1查看技能
GitHub
skill-creator
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, workflows, or to...
☆ 1查看技能
GitHub
config-audit
This skill should be used when auditing or comparing Claude Code and Cursor IDE configurations to identify feature gaps, equivalencies, and migration opportunities. Useful when managing AI development tooling a...
☆ 1查看技能
GitHub
todo-ai-mcp-agent
Enable AI-driven Todo management using natural language via MCP tools. Use when building conversational todo agents, implementing natural language task management, designing AI assistants for todo apps, or crea...
☆ 1查看技能
GitHub
discuss
Conducts in-depth technical interviews about features or tasks using AskUserQuestion, then generates comprehensive specification documents. Use when the user wants to discuss, plan, or spec out a feature/task i...
☆ 1查看技能
GitHub
vibecode-setup
Initialize a new vibecoding session with proper context and planning
☆ 1查看技能
GitHub
meta-agent
Generates new Claude Code subagent configuration files from user descriptions. Use proactively when the user asks to create a new subagent or agent. Keywords include create subagent, new agent, build agent, age...
☆ 1查看技能
GitHub
update-vllm-nightly
List available vLLM nightly builds and update config/models.yaml to pin a specific version. Use when user wants to browse nightlies, pin a specific vLLM version, or update vLLM nightly config.
☆ 1查看技能
GitHub
mcp-memory-first-development
Memory-First development workflow integrating Serena short-term project memory and Cipher long-term design knowledge for efficient LoRAIro development
☆ 1查看技能
GitHub
raven-test
Tester Agent의 심층 QA 프로세스. 커버리지 분석, Edge Case 검증, 심층 테스트, 리포트 생성의 단계를 정의합니다.
☆ 1查看技能
GitHub
hackathon-todo-advanced
Complete guide for Panaversity Hackathon II (Todo Spec-Driven Development) Phases 2-5. Use when working on Phase 3 (MCP + OpenAI Agents + ChatKit chatbot), Phase 4 (Kubernetes with Minikube, Helm, Docker), Phas...
☆ 1查看技能
GitHub
agents-md-generator
Automatically generate comprehensive AGENTS.md files that teach AI agents how to work with a repository's structure, conventions, and guidelines
☆ 1查看技能
GitHub
advanced-tool-usage
Guidelines for multi-stage tool orchestration and handling large data using 'redirect_tool_call'. Use this when you need to process large amounts of data without exhausting the context window or when building c...
☆ 1查看技能
GitHub
edit-skill
Guide for creating and editing Agent Skills. Use this skill when you need to create or modify a skill.
☆ 1查看技能
GitHub
terraphim-hooks
Knowledge graph-based text replacement using Terraphim hooks. Intercepts commands and text to apply transformations defined in the knowledge graph. Works with Claude Code PreToolUse hooks and Git prepare-commit...
☆ 1查看技能
GitHub
local-knowledge
Leverage personal notes and documentation through Terraphim's role-based search. AI agents can search developer's local knowledge organized by domain (Rust, frontend, architecture) using the terraphim-agent REP...
☆ 1查看技能
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。