Discover research llm ai skills, compare source repositories and read the instructions for each workflow.
Manages learning extraction and sign application workflows. This skill should be used when extracting learnings from session transcripts, reviewing proposed signs, or applying approved learnings to CLAUDE.md fi...
Guide for creating effective custom slash commands. This skill should be used when users want to create a new slash command (or update an existing slash command) that provides quick, repeatable workflows with p...
Speak about any topic using the macOS say command. Use for "talk about what happened", "talk about this document", detailed discussions, or conversational narration. Adapts tone and length to match the context...
Research architecture decisions and create Architecture Decision Records (ADRs). Use when facing complex technical choices requiring deep research, options analysis, and formal documentation. Treats user as CTO...
Guides test type selection for agentic code. Use when writing tests for LLM interactions, tool implementations, or behavioral quality. Covers unit tests, VCR integration tests, and TruLens evals per ADR-0011/00...
AI/CS paper reader - analyzes PDF papers and extracts key points, contributions, and methods
SEO and LLM optimization for web content. Use when optimizing content for search engines and AI systems, implementing structured data, or improving content discoverability. Provides SEO patterns and LLM-friendl...
Retrieval instructions for searching session history. Auto-loaded by the hive-mind:retrieval agent - prefer spawning that agent rather than invoking this skill directly.
Create or improve agents following templates. Use when building company roles, consultants, or hub agents.
Coordinate multi-agent discussions to reach decisions. Use when 2+ agents deliberate or for board meetings.
Master axiom loader - load this for all agents. Includes all foundational principles.
Create or improve Claude Code skills. Use when building new skills, adding capabilities, or refining existing skill instructions.
Create vision documents for features, products, or company direction. Use when starting something new.
Research markets, competitors, or people for agent creation. Use when needing external information with verified sources.
Core prompt engineering and context engineering best practices for Claude Code prompts.
DO NOT invoke unless explicitly instructed. Core guidelines for orchestrating tasks with subagents.
Philosophical partner exploring Ghost in the Shell shell/ghost duality. Handles existential reasoning, ethical gray areas, and meta-cognitive analysis.
Default skill for daily tasks, casual conversation, and general assistance. Dave's personal AI partner for everyday life.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fi...
Creates blog article proposals before writing. Use when starting a new blog article to evaluate quality (rarity, value, novelty, verification), avoid product-specific terms, and collaborate with the operator to...
Design architecture proposals and detect violations for ClaudeMix project. Use when planning new features, checking architecture compliance, or needing guidance on which tools/agents to use.
Debug and trace MachinaMed medical agent errors in GKE environments. Use for investigating agent failures, tracing invocations, analyzing MALFORMED_FUNCTION_CALL errors, and generating comprehensive error repor...
Integrate with Google's Gemini CLI for delegating tasks to Gemini. Use when you need an alternative AI perspective, Google Search grounding, parallel task execution, or want to leverage Gemini's 1M token contex...
Integrate with Claude Code CLI for delegating complex coding tasks. Use when you need to spawn a separate Claude Code instance to work on files, run tests, or perform multi-step coding operations in a specific...
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.