Decomposes scope into Epics, Stories, and RICE priorities. Use when user has project scope and wants full Agile breakdown. — from majiayu000/claude-skill-registry
Implement AI chatbot analytics and conversation monitoring. Use when adding conversation metrics, tracking AI usage, measuring user engagement with chat, or building conv — from…
Generate images using Google's Gemini API — hero backgrounds, OG images, placeholder photos, textures, and style-matched variants.
Audio configuration for Bazzite. Virtual audio channels for Game/Voice/Browser/Music, 7.1 surround for headphones, Bluetooth headset profiles, and PipeWire management.
Implement or adjust background transcription jobs for whisper-lolo. Use when wiring Inngest events, handling long-running jobs, chunking before transcription, persisting…
List recent threads. Requires authentication. Use for Agentuity cloud platform operations — from majiayu000/claude-skill-registry
Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible end — from…
Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API.
Problem solving using Fishbone (Ishikawa) diagrams and 5 Whys technique. Identifies root causes systematically and recommends corrective actions.
Common interface patterns, navigation patterns, form patterns, data display patterns, feedback patterns, and accessibility considerations
Write technical Q&A responses as markdown files to Claude Overflow. Use for programming questions, code explanations, debugging help, API usage.
When the user wants to combine machine learning with optimization, use ML predictions in optimization models, or integrate AI with mathematical programming.
Use when creating or modifying Model Context Protocol (MCP) servers with FastMCP framework - guides through tools, resources, prompts, authentication, Claude Desktop integration,…
Write effective MCP server instructions for tool compaction support. Use when creating or updating the `instructions` parameter in MaaSProtectedFastMCP server initialization.
Expert prompt engineering for building AI agents via Claude, GPT, and Gemini APIs. Triggers when: writing or editing system prompts, tool descriptions, agent instructions,…
RWD研究の企画から完成までを統括する編集長Skill。他のSkillを適切な順序で呼び出し、 研究案Top3の選定、スコアリング、感度分析計画、次アクションを統合出力する。
Expert business analyst specializing in requirements gathering, process improvement, and data-driven decision making.
Configure WaveCap LLM-based transcription correction. Use when the user wants to enable/disable LLM correction, change models, tune prompts, or optimize correction qualit — from…
Running and validating Probitas scenarios. Use when executing tests, running scenarios, or debugging test failures.
Complete guide for Google Gemini API using the CORRECT current SDK (@google/genai v1.27+, NOT the deprecated @google/generative-ai).
Load, convert, and manipulate Hi-C contact matrices using cooler format. Read .cool/.mcool files, convert from .hic format, access matrix data, and export to different fo — from…
Microsoft 365 Agents SDK for Python. Build multichannel agents for Teams/M365/Copilot Studio with aiohttp hosting, AgentApplication routing, streaming responses, and MSAL — from…
Explores codebases to find relevant files, trace execution paths, and map architecture with team communication capabilities for collaborative analysis (converted from agent)
Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED.
You are an expert in Mastra, the TypeScript framework for building AI agents, RAG pipelines, and workflows.
REST API and GraphQL design patterns, authentication, error handling, and best practices. Use when building APIs, designing endpoints, or implementing backend services.
Execute tasks using the OpenAI Codex CLI (GPT-5.2). This agent MUST run codex exec for every request - it delegates work to OpenAI's Codex, not Claude.
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing.
Generate navigable code maps for unfamiliar codebases. Extracts exports/imports via AST (tree-sitter) to create _MAP.md files per directory showing classes, functions, me — from…
Behavioral rules and lifecycle event handlers for the dev-tools package. Defines automated behaviors that trigger at specific points in the agent workflow. (converted from hooks)
Basic MCP skill demonstrating CLI-based execution pattern for fetching URL content
Adds a new AI platform to DeepWork with adapter, templates, and tests. Use when integrating Cursor, Windsurf, or other AI coding tools. — from majiayu000/claude-skill-registry
Archaeological analysis of WordPress sites. Detects all page builders, audits plugins (active vs dead weight), maps content structure, finds orphaned shortcodes, measures…
YouTube 영상에서 쇼츠 클립 3개를 자동 제작합니다. yt-dlp, whisper, ffmpeg 파이프라인을 사용합니다. "쇼츠 만들어줘", "영상 클립 추출해줘" 요청 시 사용합니다.
Classify tasks (type/domain), estimate complexity/iterations, recommend specialists from feedback themes — from majiayu000/claude-skill-registry
Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from majiayu000/claude-skill-registry
Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK.
Documentation for the logistic regression MI estimation experiment (exps_logistic) — from majiayu000/claude-skill-registry
Autonomous crypto trading with technical and sentiment analysis. Use when executing trades, analyzing markets, or managing positions on Coinbase.
코드 검색 전 코드베이스 문서를 참고하여 프로젝트 구조와 컨텍스트를 파악합니다. 코드 검색, 파일 탐색, 구현 위치 파악, 프로젝트 이해가 필요할 때 사용하세요.
Selects and configures agents from the agents repo based on PRD tech stack. Runs after task decomposition, before specification generation. — from majiayu000/claude-skill-registry
Bidirectional conversion between Elm and Haskell. Use when migrating projects between these languages in either direction.
병렬 리서치 오케스트레이션. 여러 소스(Context7, WebSearch, 코드베이스)를 동시에 탐색하여 기술 조사를 수행합니다. Use when researching libraries, APIs, best practices, or when comparing technical approaches.
Text-to-speech conversion using OpenAI's TTS API for generating high-quality, natural-sounding audio.
Iterative development loop methodology for autonomous AI work. Configure self-correcting coding loops that iterate until completion criteria are met, integrate with Archon for…
基于 Manus 风格的文件规划系统，用于组织和跟踪复杂任务的进度。创建 task_plan.md、findings.md 和 progress.md 三个文件。当用户要求规划、拆解或组织多步骤项目、研究任务或需要超过5次工具调用的工作时使用。支持 /clear 后的自动会话恢复。触发词：任务规划、项目计划、制定计划、分解任务、多步骤规划 — from…
Behavioral specification for the CoBuilder Heartbeat teammate. Loaded as prompt when spawning the Haiku work-finder agent within the session-scoped cobuilder-live-{hash} team.
Frontend aesthetics policy. Use when building UI, components, landing pages, dashboards, or any frontend work. Prevents generic ai-generated look.
Prompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve structure, add constraints, optimize for specific models,…
Create and transform features using encoding, scaling, polynomial features, and domain-specific transformations for improved model performance and interpretability — from…
Automate ML workflows with Airflow, Kubeflow, MLflow. Use for reproducible pipelines, retraining schedules, MLOps, or encountering task failures, dependency errors, experiment…
Use when creating, updating, or syncing Codex skills for this repo, including installing skills into CODEX_HOME and using scripts/sync_skills.ps1 to symlink repo skills; also use…
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Query and analyze Claude Code observability data (metrics, logs, traces). Use when analyzing performance, costs, errors, tool usage, sessions, conversations, or subagents.
Apply P3 Identity Stack to recognize that individuals operate from multiple nested identities simultaneously.
Use when fine-tuning LLMs, training custom models, or optimizing model performance for specific tasks.
谐波形态信号引擎——基于斐波那契几何识别 XABCD 五点结构，支持 Gartley、Bat（蝙蝠）、Butterfly（蝴蝶）、Crab（螃蟹），在潜在反转区（PRZ）生成交易信号。Triggers: "谐波形态", "谐波", "Gartley", "蝙蝠形态", "蝴蝶形态", "螃蟹形态", "XABCD", "潜在反转区", "PRZ",…
Harbor framework for agent evaluation. Use when: (1) Running harbor commands (harbor run, harbor tasks check), (2) Creating/validating SkillsBench tasks, (3) Understandin — from…
Converts a PRD or plan markdown file into prd.json format for ralph-json-start-loop to execute autonomously. Use when user wants to convert a PRD or plan to JSON stories.