GitHub
toolkit-architect
Project scaffolding router for .claude/ configuration and local-first customization. Use when enhancing current project with skills, MCP, hooks, or subagents. Routes to specialized domain architects and toolkit...
Skills IA content media llm ai
Découvrez les skills content media llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: content media llm ai
content media llm ai Effacer les filtres
Explorer
GitHub
research
Research technical solutions, analyze architectures, gather requirements thoroughly. Use for technology evaluation, best practices research, solution design, scalability/security/maintainability analysis.
GitHub
sequential-thinking
Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition, course correction.
GitHub
plot-consistency-checker
Analyzes narrative plot points, timelines, and story events to identify inconsistencies, plot holes, continuity errors, and pacing issues. Use when the user needs help ensuring their story remains logically con...
GitHub
unreal-engine-developer
Expert Unreal Engine 5 developer and technical artist for complete game development via agentic coding. Enables AI-driven control of Unreal Editor through MCP, Python scripting, Blueprints, and C++ for level de...
GitHub
ai-artist
Craft prompts for AI models (text, image, video). Use for Midjourney, DALL-E, Stable Diffusion, Flux, Veo, prompt engineering, style keywords, negative prompts, iterative refinement.
GitHub
agent-centric
Track decisions (AGD) with validation and indexing. Use when making design decisions, recording important choices, discussing trade-offs, or when user mentions AGD or decision record.
GitHub
ai-multimodal
Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.
GitHub
context-engineering
Token optimization and context window management strategies. Load for long sessions, complex tasks, or when approaching context limits.
GitHub
flux-prompt-engineer
Expert prompt engineering for FLUX.1 image generation. Use when users request AI-generated images, artwork, illustrations, or visual content. Converts any visual request into optimized FLUX.1 prompts using laye...
GitHub
research-fact-checker
Assists authors in researching topics, verifying facts, and ensuring accuracy in their writing. Particularly useful for historical fiction, non-fiction, science fiction, and any genre requiring real-world accur...
GitHub
mcp-economy
Enforce cost-aware MCP usage. Use when a task might trigger heavy external tools, web search, or broad context expansion. Prevents token burn by ensuring MCPs are only used when local context is insufficient.
GitHub
guide
Use this skill when the user asks questions about Claude Code CLI, Claude Agent SDK, or Claude API. Provides comprehensive guidance, documentation references, and best practices.
GitHub
voice-system-expert
Use when working with Quetrex's voice interface, OpenAI Realtime API, WebRTC, or echo cancellation. Knows Quetrex's specific voice architecture decisions and patterns. CRITICAL - prevents breaking working voice...
GitHub
skill-architect
Facilitates the creation and refactoring of Agent Skills compliant with the official specification. Use this to scaffold new skills or audit existing ones.
GitHub
search-conversations
Search through Claude Code conversation history. Use when user says "search my conversations", "find when I talked about X", "what did claude say about Y", or "search claude history".
GitHub
agent-exec
Use the agent-exec CLI to run Codex/Claude/Cursor and manage skills for this repo.
GitHub
deep-reason
Esta skill debe usarse cuando el usuario pide "pensemos esto a fondo", "analicemos paso a paso", "evaluemos opciones", "razonemos sobre esto", "pensemos detenidamente", "meditemos", "qué me sugieres", "qué me r...
GitHub
using-skills
Establishes how to find and use skills - requires Skill tool invocation before any response
GitHub
grammar-style-enhancer
Analyzes prose for grammar errors, style inconsistencies, clarity issues, and readability problems. Provides specific suggestions for improvement while preserving the author's unique voice. Use when the user ne...
GitHub
get-session-id
Get the current Claude Code session ID and log file path. Use when user says "get session id", "what is my session id", "current session", "session info", or "what session is this".
GitHub
copywriting
Conversion copywriting formulas, headline templates, email copy patterns, landing page structures, CTA optimization, and writing style extraction. Activate for writing high-converting copy, crafting headlines,...
GitHub
semantic-seo
Semantic SEO framework for reducing Cost of Retrieval (CoR). Use when creating SEO content, topical maps, content briefs, semantic content networks, knowledge graphs, website audits, or optimizing for search en...
GitHub
subagent-orchestration
Esta skill debe usarse cuando el usuario pide "orquestar agentes", "coordinar subagentes", "agentes en paralelo", "flujo multi-agente", "delegar a agentes", "lanzar agentes en paralelo", o necesita ejecutar múl...
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.