GitHub
orchestrate
Multi-Model Orchestration - Guide for orchestrating multi-model agents
Skills IA tools llm ai
Découvrez les skills tools llm ai, comparez leurs dépôts et consultez leurs instructions.
Catégories: tools llm ai
tools llm ai Effacer les filtres
Explorer
GitHub
skill-creator
This skill should be used whenever the user mentions "skill" in any way, including creating, updating, modifying, or packaging skills. Guide for creating effective skills that extend Claude's capabilities with...
GitHub
skillmeat-cli
Manage Claude Code environments using natural language. Use this skill when: - User wants to add, deploy, or manage Claude Code artifacts (skills, commands, agents, MCP servers) - User asks about available skil...
GitHub
recovering-sessions
Recover from crashed, failed, or interrupted Claude Code sessions. Use this skill when: session crashed during multi-agent parallel execution, need to determine what work was completed vs incomplete, want to ge...
GitHub
artifact-tracking
Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, valid...
GitHub
groq-chatbot
Build a streaming AI chatbot with Groq API, RAG context, and Next.js. Includes floating UI, model fallbacks, and Vercel deployment.
GitHub
clarify
Clarify a task or decision through guided questioning
GitHub
questions-insight
Question template for Insight stories ('I discovered X while doing Y'). Arc: Routine → Disruption → Recognition → Understanding → Application. Use with question-design skill.
GitHub
web-design
Create distinctive, production-grade layouts for aiandi.dev. Bold aesthetic vision + semantic token system. Use when designing pages, components, or visual treatments.
GitHub
screenshot
Capture screenshots of aiandi.dev for visual verification. Puppeteer-based, outputs to /tmp. Foundation for the design-loop skill.
GitHub
synthesis-prep
Prepare synthesis guidance for the-art. NOT an outline. Provides thematic guidance, narrative intent, and evidence library that enables synthesis instead of expansion.
GitHub
transcribe-walk
Process walk recordings into usable research material. Transcription workflow, insight extraction, integration with pipeline. Use after WALK stage recording.
GitHub
voice
Expressing Robbie's authentic voice for AI and I blog. The voice teaches by demonstration, trusts through expectation, flows between poles without announcing shifts, and finds joy in structure clicking into pla...
GitHub
walk-and-talk
Create talking guides for insight elicitation during physical walks. Use when you need human insight that benefits from embodied cognition, reflective thinking, or extraction of tacit knowledge. Triggers: 'walk...
GitHub
codex-skills-index
Entry point for Codex-discoverable skills used by the Run-Smart AI coach.
GitHub
post-run-debrief
Converts telemetry and user notes into a structured reflection, confidence score, and next-step guidance.
GitHub
conversational-goal-discovery
Guides users through clarifying goals, constraints, and weekly commitments via chat.
GitHub
running-coach-index
Reference catalog for all running coach AI skills, shared TypeScript contracts, safety guardrails, and telemetry conventions. Use when working with any running coach feature to understand data schemas, safety p...
GitHub
implement-text-response-question
Create D3 questions focused on written explanations and reflections of static content (text, images, diagrams). For video-based questions, use implement-video-question instead.
GitHub
app-development
Build features in the AI Coaching Platform Next.js app. Use for creating pages, components, server actions, TanStack tables, and understanding application architecture.
GitHub
create-claude-skill
Create new Claude skills following Anthropic best practices. Use when building specialized agent capabilities, packaging procedural knowledge, or extending Claude's domain expertise.
GitHub
implement-custom-d3-question
Create D3 questions with unique, non-standard interactions. Fallback skill for questions not fitting standard patterns.
GitHub
research
Self-healing documentation lookup. Use when wondering how something in the Awareness project works, where files live, or how to do something technical. Queries tech RAG and spawns improvement agents for gaps.
GitHub
proposal-builder
Assemble proposals from templates and content library. Use when implementing proposal generation, managing content blocks, or working with proposal templates.
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.