GitHub
explainability-planning
Plan explainable AI (XAI) requirements including SHAP, LIME, attention visualization, and regulatory explainability needs.
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
ethics-review
AI and technology ethics review including ethical impact assessment, stakeholder analysis, and responsible innovation frameworks
GitHub
ai-ethics-advisor
Comprehensive AI ethics and responsible AI development specialist. Use PROACTIVELY for bias assessment, fairness evaluation, ethical AI implementation, community impact analysis, and regulatory compliance. Trig...
GitHub
agentic-workflow-design
Design multi-agent AI systems including orchestration patterns, tool design, memory management, and error handling for autonomous agents.
GitHub
token-budgeting
Estimate and optimize AI/ML costs including token usage, context window management, batch processing, and caching strategies.
GitHub
multilingual-localization
Translate documentation and instructions to EU languages while preserving formatting. Use when the user wants to translate, localize, or convert documents to another language, especially for EU AI Act Article 1...
GitHub
rag-architecture
Design retrieval-augmented generation pipelines including chunking, embedding, retrieval, and context assembly strategies.
GitHub
prompt-engineering
Design, test, and version prompts with systematic evaluation and optimization strategies.
GitHub
hitl-design
Design human-in-the-loop workflows including review queues, escalation patterns, feedback loops, and quality assurance for AI systems.
GitHub
gemini-workspace-bridge
Central authority for Claude-Gemini shared workspace architecture. Defines directory structure, artifact exchange, and file naming conventions. Use when setting up dual-CLI workflows, deciding where to store AI...
GitHub
ai-safety-planning
Plan AI safety measures including alignment, guardrails, red teaming, and regulatory compliance (EU AI Act, NIST AI RMF).
GitHub
writing-claude-rules-skills-subagents
Guidelines for creating custom rules, custom skills, and custom subagents for Claude.
GitHub
skill-creator
Create new Claude Code skills following V3 DX patterns with Beads/Serena integration. MUST BE USED when creating skills. Follows tech lead proven patterns from 300k LOC case study. Use when user wants to create...
GitHub
jules-dispatch
Dispatches work to Jules agents via the CLI. Automatically generates context-rich prompts from Beads issues and spawns async sessions. Use when user says "send to jules", "assign to jules", "dispatch task", or...
GitHub
cass-search
Coding Agent Session Search (CASS) for semantic search over past agent sessions. Use when looking for how something was solved before, finding past solutions, or searching conversation history. Keywords: search...
GitHub
quantum-templ-ebook
Assists in writing ebooks 2-8 of The Quantum Templ™ System, maintaining consistency with Gate I's established voice, structure, and philosophy. Use when creating new Gate ebooks, drafting sections, or ensuring...
GitHub
claude-md-optimizer
Analyzes and optimizes CLAUDE.md files following Anthropic's official best practices. Use when reviewing existing CLAUDE.md for improvements, or when user mentions CLAUDE.md is too long or ineffective.
GitHub
llm-eval-designer
LLM生成システムの検証設計スキル。assay-kitフレームワークを活用し、LLM特有の失敗モード（幻覚、例への過学習、部分的処理）を考慮した総合的なテストケース設計を支援する。 使用タイミング: - LLMベースのワークフロー/...
GitHub
claude-md-customizer
対話形式の質問を通じてユーザーの技術的背景、開発スタイル、AI協働の好みを把握し、最適化されたCLAUDE.mdを生成するスキル。ユーザーが「CLAUDE.mdをカスタマイズしたい」「AIの振る舞いを自分に合わせたい」「開発スタイル...
GitHub
ai-led-onboarding
生成AIが人間に対して行う作業開始時オンボーディング。AIが"説明係"ではなく"進行役"として、探索→仮説→検証→要約→未確定の明示を回し、人間が最小スキーマ（因果・境界・不変条件・壊れ方・観測）を短時間で再構築できる状態...
GitHub
resolving-uncertainty
Turns ambiguity into an Uncertainty Register, prioritizes items, and produces observation tasks/experiments with evidence and decision rules. Use when the user mentions uncertainty/unknowns/assumptions/validati...
GitHub
eld-sense-activation
PCE (Process-Context Engine) のアクティブコンテキスト構築スキル。タスクに最適化されたコンテキストをコンパイルし、プロセス駆動の投入物を生成する。 トリガー条件: - 新しいタスクを開始する時（「この機能を実装して...
GitHub
reasoningbank-intelligence
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cogn...
GitHub
agentdb-performance-optimization
Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling t...
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.