GitHub
asset-creator
Generate web page assets (illustrations, icons, logos) using the Gemini image generation API. Use when the user wants to create images, icons, logos, or illustrations for web pages.
☆ 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
debate
Multi-model adversarial debate where Claude defends positions against external CLI models (Gemini, Codex, Qwen). Use when facing complex decisions, wanting to expose blind spots, or needing documented reasoning...
☆ 0View skill
GitHub
auto-ralph
PROACTIVELY activates for ANY task with clear success criteria. This skill should be used when the user provides tasks like: "fix the bug", "add tests", "implement feature X", "refactor Y". Explicit triggers: "...
☆ 0View skill
GitHub
carlin-audit
George Carlin BS Detector. Auto-activates on: "BS", "bullshit", "jargon", "marketing speak", "what does this mean", "sounds fake", "corporate speak", "buzzwords", "overpromising", "skeptical about"
☆ 0View skill
GitHub
research-handoff-oracle
Use when asked to create a deep-research handoff bundle: do web research, codebase analysis, Gemini Oracle critique, and produce a prompt + context folder on Desktop for another AI agent (include a zipped archi...
☆ 0View skill
GitHub
sketch-prompt-lab
Prompt iteration workflow for kid-friendly, realistic outputs. Use when tuning prompts, selecting styles, or when outputs look too similar to the original sketch.
☆ 0View skill
GitHub
sketch-ai-provider-debug
Debug OpenAI/Gemini image generation failures for Sketch Magic. Use when `/api/convert` returns 500, when models are unsupported, when outputs are empty, or when provider timeouts/quota errors appear.
☆ 0View skill
GitHub
oracle
Parallelized multi-agent critique system using Gemini, Copilot, Claude, and Codex. Decomposes complex engineering tasks into specialized domains and synthesizes a single authoritative report.
☆ 0View skill
GitHub
question-refiner
Transform raw research questions into structured, validated research prompts with automatic research type detection and output format validation. Ensures prompts are ready for research-executor with comprehensi...
☆ 0View skill
GitHub
research-planner
Create detailed research plans by decomposing structured prompts into subtopics, search strategies, and agent deployment configurations. Extracted from Phase 2 of research-executor for standalone planning capab...
☆ 0View skill
GitHub
writing-assistant
Work on writing assistance features including real-time style analysis, grammar checking, writing goals tracking, inline suggestions, and writing analytics. Use when implementing linguistic analysis, productivi...
☆ 0View skill
GitHub
skill-creator
Create new Claude Code skills with proper structure, modular organization, and performance optimization. Use when building new skills, refactoring existing skills, or improving skill maintainability.
☆ 0View skill
GitHub
goap-agent
Invoke for complex multi-step tasks requiring intelligent planning and multi-agent coordination. Use when tasks need decomposition, dependency mapping, parallel/sequential/swarm/iterative execution strategies,...
☆ 0View skill
GitHub
novel-development
Work on novel-specific features including plot engines, character development, world-building, timeline management, and GOAP-based story generation. Use when implementing narrative systems, character arcs, or s...
☆ 0View skill
GitHub
agent-coordination
Coordinate multiple specialized agents through systematic planning, dependency mapping, and quality gate enforcement for complex multi-domain tasks.
☆ 0View skill
GitHub
goap-agent
Invoke for complex multi-step tasks requiring intelligent planning and multi-agent coordination. Use when tasks need decomposition, dependency mapping, parallel/sequential/swarm/iterative execution strategies,...
☆ 0View skill
GitHub
context-monitor
Detects context drift, conversation unfocus, and suggests refocusing strategies. Trigger: When conversation exceeds 50 messages, when multiple topics are mixed, when repeated errors occur, when confusion patter...
☆ 0View skill
GitHub
vercel-ai-sdk
AI integration with Vercel AI SDK - Build AI-powered applications with streaming, function calling, and tool use. Trigger: When implementing AI features, when using useChat or useCompletion, when building chatb...
☆ 0View skill
GitHub
skill-creator
Guides creation of new skills following dsmj-ai-toolkit v2.0 format with validation. Trigger: When creating new skills, when user says "create skill", when adding domain knowledge, when documenting patterns, wh...
☆ 0View skill
GitHub
prompt-engineer
Best-practice prompt engineering using research-backed patterns. Handles: transforming rough prompts into production-ready, debugging prompt issues, creating new prompts from scratch. ALWAYS researches via suba...
☆ 0View skill
GitHub
geo-audit
Audit and optimize website for AI search engines like ChatGPT, Perplexity, Google AI Overviews, and Claude. Use when discussing GEO (Generative Engine Optimization), SEO for AI, llms.txt, AI crawlers, structure...
☆ 0View skill
GitHub
notes-generator
Generate comprehensive educational notes using Bloom's Taxonomy methodology. Creates structured learning materials with summaries, practice questions, and visual diagrams. Use when user requests notes generatio...
☆ 0View skill
GitHub
cover-letter-generator
Generate tailored AI-focused cover letters using the PSI (Problem-Solution-Impact) methodology. Use when: (1) User wants to create cover letters for AI/ML job applications, (2) User provides a resume and wants...
☆ 0View skill
GitHub
fastapi
Comprehensive FastAPI development skill for building APIs from hello world to production-ready applications. Use when building REST APIs, microservices, ML/AI APIs, or full-stack applications with FastAPI. Cove...
☆ 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.