Comprehensive reference for Google's Gemini API. Use when building applications with: (1) Gemini models (Gemini 3 Pro, 2.5 Flash/Pro/Flash-Lite) for text and multimodal g — from…
Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`).
Use when asked to normalize audio volume, match loudness, or apply peak/RMS normalization to audio files.
テストワークフローパターン：E2Eテスト生成、テストオーケストレーション。 自動テストのためのテンプレートとプロセスを提供。 トリガー: testing, E2E, end-to-end, playwright, test runner, テストオーケストレーション。
Mandatory protocol that prevents AI agents from fabricating information. Forces best practice search before every action — coding, design, content, pricing, naming, architecture,…
Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights.
Look up current research information using Perplexity Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter.
LiteLLM-RS Caching Architecture. Covers Redis caching, vector database semantic caching, multi-tier cache strategy, TTL management, and cache invalidation patterns.
OpenAI official SDK usage (Python, Node.js). Use when: writing code that calls OpenAI API, implementing chat/embeddings/images/audio features, handling streaming responses, async…
Assess and report on AI tool subscriptions, usage patterns, and cost-effectiveness. Use for reviewing AI subscriptions, analyzing tool usage, optimizing AI spend.
Ralph Wiggum-inspired automation loop for specification-driven development. Orchestrates task implementation, review, cleanup, and synchronization using a Python script.
Monitor and interact with SOLO.ro accounting platform via CLI or TUI (summary, revenues, expenses, queue, e-factura, company).
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination — from majiayu000/claude-skill-registry
Analyze imports and identify all module dependencies. Use when mapping project structure. — from majiayu000/claude-skill-registry
Analyze WAV audio files for debugging TTS and audio pipelines. Use when checking audio quality, validating WAV format, inspecting waveform patterns, or diagnosing generated speech…
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern rec — from…
Comprehensive **project** consistency review across code, documentation, diagrams, and configuration
Deep exploration and synthesis workflow using parallel task agents with dynamic planning and hub-and-spoke coordination.
Internationalization for TSH Clients Console (English/Arabic with RTL). Use when: (1) Adding new text strings that need translation (2) Creating components with user-facing text…
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API.
Interpret YouTube Analytics, TikTok Analytics, and video performance data. Identifies trends, explains metrics, and provides actionable recommendations for growth.
Comprehensive guide for implementing Fullstory's Page Properties API (setProperties with type 'page') for web applications.
Voyager-inspired continuous learning system with Critic Agent, Reflection Agent, and Discord-based approval workflow for skill proposals.
Debug preprocessing pipeline failures. Guides through reading checkpoint files, checking step artifacts, interpreting QC metrics, examining visualization PNGs, and identifying…
Generate AI videos with OpenAI Sora via AceDataCloud API. Use when creating videos from text prompts, generating videos from reference images, or using character referenc — from…
PolicyEngine API v2 - Next-generation microservices architecture with monorepo structure
既存GitHubリポジトリのメンテナンス（リリース、変更履歴、Issue等）。ghコマンド使用。 トリガー例: 「リリースノート」「リリース」「issue」「repo-maintain」 ※ PR 作成・マージは repo-flow スキルを使用
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly. — from majiayu000/claude-skill-registry
AI-human partnership paradigm — identity, consciousness integration, and the three eras of AI collaboration
Company-specific procedures, standards, templates, and best practices for engineering documentation, project management, and professional communication in building energy…
Implementation agent that executes a single task and creates handoff on completion — from majiayu000/claude-skill-registry
Analyze completed Linear cycles for retrospectives. Identifies velocity trends, scope creep, and patterns to improve future planning.
Build tools that agents can use effectively, including architectural reduction patterns — from majiayu000/claude-skill-registry
Create and use Claude Code slash commands - quick prompts, bash execution, file references — from majiayu000/claude-skill-registry
This pipeline performs genome-wide segmentation of CpG methylation profiles to identify Unmethylated Regions (UMRs), Low-Methylated Regions (LMRs), and Partially Methylat — from…
Manages GitLab branches. Use for listing, creating, deleting, or querying branches in projects. Triggers: branch operations, git branching. — from majiayu000/claude-skill-registry
Deconstructs complex problems using the 'Polymath Investor' framework with a 5-step cognitive chain (First Principles → Modular Isolation → Pareto Filtering → Cross-Domai — from…
Waddington's epigenetic landscape: cell fate as gradient flow on potential surfaces, connecting developmental biology to dynamical systems, Schrödinger bridges, and fractional…
Implement multi-layer LLM caching with exact match, semantic similarity, and provider-side prompt caching.
Japanese brand design guidelines with traditional color palettes (伝統色), typography (ゴシック体/明朝体), ma (間) spacing, wabi-sabi (侘寂) aesthetics, and logo design for Japanese characters.
Host interactive expert panel discussions on any topic. Dynamically generates master-level expert personas, facilitates structured debate using Hegelian dialectic patterns, and…
Find unclaimed open source issues that match the user's skills and experience level. Searches for issues created by maintainers/org admins, checks contribution eligibility, and…
Autonomous crypto trading with technical and sentiment analysis. Use when executing trades, analyzing markets, or managing positions on Coinbase.
Quick classifier training with automatic model selection, hyperparameter tuning, and comprehensive evaluation metrics. — from majiayu000/claude-skill-registry
Canonical Claude Code skill authoring kit covering agent Skills, sub-agent templates, custom slash commands, orchestration patterns, hooks, memory, settings, and IAM permission…
Evaluate how well a codebase supports autonomous AI development. Analyzes repositories across eight technical pillars (Style & Validation, Build System, Testing, Documentation,…
Quantum computer music composition and performance using quantum circuits, ZX-calculus notation, and quantum instruments
Configuring and optimizing 16-bit Low-Rank Adaptation (LoRA) and Rank-Stabilized LoRA (rsLoRA) for efficient LLM fine-tuning using triggers like lora, qlora, rslora, rank…
Expert in statistical analysis, predictive modeling, machine learning, and data storytelling to drive business insights. — from majiayu000/claude-skill-registry
Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, or context augmentation.
JAX, Flax, Optax, and Equinox patterns for ML training. Covers JIT, vmap, pmap, TPU usage, and functional model design. Use when building or debugging JAX-based training pipelines.
3-MATCH gadgets and non-backtracking geodesics for 3-SAT via colored subgraph isomorphism.
K-Scale kinfer model inference engine for deploying trained RL policies to real robots via ONNX Runtime in Rust — from majiayu000/claude-skill-registry
Deep-dive analysis of GitHub projects. Use when the user mentions a GitHub repo/project name and wants to understand it — triggered by phrases like "帮我看看这个项目", "了解一下 XXX" — from…
Guide for managing the Agent Registry - database-backed agent configuration system. Use when asked to "configure agents", "manage skills", "set tool permissions", "create — from…
Use when CLAUDE.md is bloated or ineffective. Use when Claude ignores instructions, file exceeds 150 lines, response formatting rules aren't working, or user asks to…
Survey the codebase for analogous features, reusable utilities, and existing patterns relevant to a proposed change. Returns structured findings without writing code.
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, o — from…
Clear specific learnings from CLAUDE.md Skill Memories section. Activates for reflect clear, clear learning, remove learning, delete memory.
Use when writing unit/integration tests for Vite projects - provides Vitest configuration, test APIs, mocking patterns, and coverage setup