GitHub
serena
Complete guide to using Serena MCP server for AI-powered code analysis with Claude Code
☆ 0View skill
tools llm ai AI Skills
Discover tools llm ai skills, compare source repositories and read the instructions for each workflow.
Categories: tools llm ai
tools llm ai Clear filters
Browse skills
GitHub
code-generation
AI-assisted code generation workflows, prompting strategies, and best practices for working with Claude Code
☆ 0View skill
GitHub
subagent-driven-development
Quality-gated iteration with multi-agent workflows for complex tasks
☆ 0View skill
GitHub
31-analyze-think-150
[31] ANALYZE. Universal deep thinking methodology for any situation requiring quality reasoning. Use when solving problems, debugging, making decisions, analyzing code, planning, reviewing, or anytime you need...
☆ 0View skill
GitHub
00-meta-chain-flow-150
[00] META. Orchestrate skills into dynamic chains for complex tasks. Analyzes the task, discovers available skills, builds an optimal chain, explains why each skill is needed, and executes step-by-step with use...
☆ 0View skill
GitHub
11-continue-session-150
[11] CONTINUE. Resume an existing session. Use when continuing previous work to load AGENTS.md, MEMORY.md, and the chosen session log, then confirm readiness.
☆ 0View skill
GitHub
10-new-session-150
[10] NEW. Start a NEW session for this project. Use when beginning a fresh task to load AGENTS.md, MEMORY.md, core project context (README), then create a NEW session log and confirm readiness.
☆ 0View skill
GitHub
72-close-session-150
[72] CLOSE. Save and restore session context between conversations. Use when ending a session to preserve progress, or starting a new session to restore context. Triggers on "save session", "end session", "pres...
☆ 0View skill
GitHub
51-execute-quality-150
[51] EXECUTE. Commitment to maximum quality work with 150% coverage. Use when you need the highest quality output for critical tasks, complex problems, important decisions, or when standard work isn't enough. T...
☆ 0View skill
GitHub
23-understand-ask-ai-150
[23] UNDERSTAND. Consult external AI models when internal sources are exhausted. Build quality prompts using Prompt150 formula (Context + Query + Method + Style). Use when Loop150 exhausts internal sources, nee...
☆ 0View skill
GitHub
conductor
CRITICAL: Load and read ENTIRE skill content before ANY coding task. This skill defines orchestration rules and role-based delegation. DO NOT skip. DO NOT skim. Read the full SKILL.md content first. NEVER use...
☆ 0View skill
GitHub
coding-agents
Spawn and control external coding agents (Claude Code, Codex, OpenCode, Pi) for delegating tasks. Use when (1) user asks to run another coding agent, (2) delegating subtasks to a different AI tool, (3) running...
☆ 0View skill
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...
☆ 0View skill
GitHub
handoff
This skill should be used when the user asks to "hand off", "create a handoff", "end session", "save progress for later", or when the agent decides to create session continuation for another agent to pick up.
☆ 0View skill
GitHub
spec-interview
Interview user in-depth about what they're building, then write a comprehensive spec. Use when the user wants to plan a feature, design a system, or needs help defining requirements.
☆ 0View skill
GitHub
Write LinkedIn posts in Keanan's voice. Use when drafting LinkedIn content, creating professional posts, or sharing builder-focused insights. Triggers include requests to "write a LinkedIn post", "draft somethi...
☆ 0View skill
GitHub
tweet
Write tweets in Keanan's voice. Use when drafting tweets, creating Twitter threads, or crafting social media content for X/Twitter. Triggers include requests to "write a tweet", "draft a post for X", "help me t...
☆ 0View skill
GitHub
developing-claude-plugins
Expert for Claude Code plugin and marketplace development. Use when creating, editing, or optimizing skills (SKILL.md), commands (*.md), agents, hooks (hooks.json), scripts, or plugin.json files. Ensures consis...
☆ 0View skill
GitHub
marketplace-optimizer
Optimizes this Claude Code marketplace using specialized sub-agents. Each agent is an expert for one element type (skills, commands, agents, hooks, mcp) and loads only relevant documentation. A marketplace agen...
☆ 0View skill
GitHub
database-management
Expert skill for managing database operations, migrations, and schema updates. Use when working with SQLAlchemy models, database migrations, or debugging database issues.
☆ 0View skill
GitHub
backend-api-testing
Expert skill for testing and debugging the FastAPI backend. Use when working with API endpoints, database operations, authentication, or middleware troubleshooting.
☆ 0View skill
GitHub
llm-cost-optimization
Reduce LLM API costs without sacrificing quality. Covers prompt caching (Anthropic), local response caching, prompt compression, debouncing triggers, and cost analysis. Use when building LLM-powered features, a...
☆ 0View skill
GitHub
ralph-integrate
Integrate Ralph with your project's existing CLAUDE.md files, skills, and agent preferences. Run after installing Ralph, or rerun anytime you add new skills/agents.
☆ 0View skill
GitHub
prompt-expander
Use when user provides a simple, vague prompt and asks to expand/improve it, or when preparing prompts for another session. Triggers on "expand this prompt", "make this more specific", "improve this prompt", or...
☆ 0View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.