AI Skills Hub - Browse 180,000+ Agent Skills

Complete development with structured merge/PR options. Use when ready to merge or submit work.

Structured workflow for integrating external codebases into agent-studio. Ensures skills, agents, templates, and workflows are properly imported with mandatory router updates.

Comprehensive scientific research toolkit with 139 specialized skills for biology, chemistry, medicine, data science, and computational research. Transforms Claude into an AI research assistant with access to scientific databases, analysis tools, and domain-specific workflows.

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.

Create research posters using HTML/CSS that can be exported to PDF or PPTX. Use this skill ONLY when the user explicitly requests PowerPoint/PPTX poster format. For standard research posters, use latex-posters instead. This skill provides modern web-based poster design with responsive layouts and easy visual integration.

Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification.

Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.

Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.

NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.

Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.

Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows.

Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.

Generate or edit images using AI models (FLUX, Gemini). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

Access BRENDA enzyme database via SOAP API. Retrieve kinetic parameters (Km, kcat), reaction equations, organism data, and substrate-specific enzyme information for biochemical research and metabolic pathway analysis.

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.

High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.

Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP/REST work or KEGG-specific control.

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.

Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.

ESP32 embedded development with PlatformIO, native unit testing, and Raspberry Pi support. Use this skill for ESP32 projects using Arduino framework - compiling, uploading, organizing code, native testing with Unity/mocks, refactoring, debugging, and working with GPIO/SPI/I2C/UART peripherals. Includes Raspberry Pi Bookworm setup and ARM64 toolchain guidance.

Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.

检查 Linux 服务器上的 Docker 部署配置，验证 .env 文件、端口、防火墙、日志等是否正确配置。当用户询问"部署检查"、"环境配置"、"服务器状态"时自动触发。

Deploy Python FastAPI backend applications to Railway with PostgreSQL database, environment configuration, and production optimization. Use when deploying backend services, troubleshooting Railway deployments, fixing dependency issues, configuring databases, or setting up production environments for FastAPI/Python applications.

HuLa project skill for frontend (Vue 3 + Vite + UnoCSS + Naive UI/Vant), backend (Tauri v2 + Rust + SeaORM/SQLite), full-stack flows, and build/release work. Use when the user mentions hula or HuLa or requests changes in this repository; after triggering, ask which scope (frontend/backend/fullstack/build-release) to enable.

Serena MCP usage guide for semantic code operations, symbol manipulation, project memory, and session persistence. Use when invoking any mcp__serena__* tools, performing symbol operations (rename, find references, extract), navigating large codebases, or managing project memory/sessions.

This skill should be used when creating professional software documentation (SRS, PRD, OpenAPI, user manuals, tutorials, runbooks) from templates (greenfield) or reverse-engineering documentation from existing code like Spring Boot or FastAPI (brownfield). Also handles documentation audits/reviews, format conversion (Markdown, DOCX, PDF), and diagram generation (C4, Mermaid, PlantUML, ER, sequence).

| Error | Wrong Code | Correct Code | |-------|------------|--------------| | `ModuleNotFoundError: chatkit.stores` | `from chatkit.stores import Store` | `from chatkit.store import Store` | | `ModuleNotFoundError: chatkit.models` | `from chatkit.models import ...` | `from chatkit.types import ...` | | `ImportError: Event` | `from chatkit.server import Event` | Remove - doesn't exist | | `ImportError: ClientToolCallOutputItem` | `from chatkit.types import ClientToolCallOutputItem` | Use `Any`...

Improves the RAG (Retrieval-Augmented Generation) chatbot for the Physical AI & Humanoid Robotics textbook with strict grounding, citation requirements, and performance optimization.

Use this skill when you need to: - Update a Galaxy tool to a new version - Fix bugs in existing Galaxy tools - Improve tool documentation - Debug failing planemo tests

Навык запуска и сопровождения workflow bundle project-analyse (ADR-015) в системе AI-KOD: установка bundle из git/локального пути, запуск (project-analyse)/research-structure и (project-analyse)/research-analyse, требования окружения (AI_KOD_ROOT, AI_KOD_PROJECT_ROOT), контрольные точки стадий, артефакты и расследование отклонений.

Create and manage zsh-snip snippets. Use when the user asks to create, modify, or manage shell command snippets for the zsh-snip plugin.

Grafix の `draw(t)` スケッチを生成・改良し、`python -m grafix export` で PNG を複数枚 headless 出力して比較するための手順。ユーザーが「Grafix の draw を作って」「PNG を書き出して」「候補を複数出して比較したい」「headless で export したい」などと言ったときに使う。

Grafix の組み込み primitive/effect を「薄いカード」形式で参照するためのカタログ。作品制作中に「何がある？」「この表現に合う op は？」を素早く探索する用途。`references/api.md` は `scripts/build_catalog.py` の自動生成を正とする。

Structure for creating hands-on exercises in the Physical AI textbook.

Track tasks, features, and project work using the track CLI. Use when breaking down work into tasks, tracking progress, managing dependencies between tasks, or coordinating multi-step work like security scans, refactoring, migrations, or any multi-part project.

Search the web and browse/scrape web pages to extract text content. Use this skill to find information online or read the content of specific URLs.

Updates PENDING picks with WIN/LOSS/PUSH results. Use after games have finished to update history.json with final scores and outcomes.

Comprehensive operational guidance for Jemena's Databricks platform following 5-layer architecture (AWS Resources → Unity Catalog → Workspaces → Data Products → Governance Apps). Covers complete runbooks for adding workspaces, onboarding business units, modifying shared modules safely, terraform remote state patterns, GitLab HTTP backend, module vs stack decisions, Unity Catalog design (centralized metastore, catalog-per-BU-per-environment), 3-dimensional RBAC (functional×classification×compliance), metastore binding constraints (permanent, cannot rebind), deployment order WHY (immutable dependencies), state file coupling, blast radius calculations, and troubleshooting permission denied errors. Use when working with terraform, databricks-unity-catalog repo, databricks-workspaces repo, app-datahub-aws-infra repos, adding new workspaces or BUs, RBAC issues, catalog/schema operations, or state file management.

Critical guidance for working in Jemena's shared VPC networking model where core-network account (234268347951) owns VPCs, subnets, NAT gateways, Transit Gateway, and VPC endpoints shared to app-datahub accounts via AWS RAM. Prevents common mistakes like attempting to create/modify networking resources, investigating NAT gateways, or modifying security groups owned by Cloud team. Covers Databricks Private Link architecture (Backend vs Frontend), 3 DNS workarounds (AD forwarder flipping, endpoint conflicts, Zscaler CNAME), RDS metastore firewall requirements, and troubleshooting workspace access issues. Use when working with AWS networking, VPCs, subnets, security groups, Private Link, Route 53, DNS, or debugging connectivity issues in app-datahub-prod (339712836516) or app-datahub-nonprod (851725449831) accounts.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Strategy for creating efficient short-form video prompts. Use when creating filler shots, atmospheric scenes, or quick video clips that don't require full Production Brief methodology. Covers when to go short vs long, format+style upfront rule, and two approaches (Descriptive vs Directive) for compact yet coherent results.

Control Windows applications using UiAutomationGRPC.Server with the "See → Think → Act" loop for efficient LLM-driven UI automation.

Complete toolkit for web crawling and data extraction using Crawl4AI. This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction.

Document parsing specialist using LlamaParse API for extracting structured text from PDFs, images, and office documents. Use when users need to parse documents, extract tables, convert files to markdown, or process document batches.

Complete toolkit for web crawling and data extraction using Crawl4AI. This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction.

Git 저장소의 변경사항을 추적하고 요약합니다. 미커밋 코드, 최근 커밋, 커밋 히스토리를 확인할 때 사용하세요. catchup, 변경사항, git diff, 커밋 히스토리, 작업 내용 파악 등의 키워드에 반응합니다.

학습 중 떠오른 아이디어와 메모를 아카이브 파일에 시간순으로 기록합니다. `scripts\study-note-helper.bat`를 사용하여 현재 KATA 프로젝트의 docs/study/아카이브.md에 노트를 추가합니다.

This skill should be used when deploying a Docusaurus site to GitHub Pages. It automates the configuration, building, and deployment process, handling GitHub Pages setup, environment configuration, and CI/CD automation. Includes local validation before GitHub Actions triggering.

When implementing any feature or bugfix - write the test first, watch it fail, write minimal code to pass; if you didn't watch the test fail, you don't know if it tests the right thing

When writing Python scripts that call Claude locally, or when you want to use your Claude subscription instead of API credits

When encountering any bug, test failure, or unexpected behavior - use this four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) before proposing any fixes

When tests have race conditions, timing dependencies, or pass/fail inconsistently - replaces arbitrary timeouts with condition polling for reliable async tests

When starting a new business process project, organizing agent files, or separating generated outputs from functional code

When deploying Claude Agent SDK to Docker/Railway, debugging spawn ENOENT errors, or configuring session persistence in containers

This skill should be used when the user asks to "combine multiple api calls", "parallel langdock action", "batch requests in langdock", "Promise.all langdock", "multi-endpoint action", or needs to build Langdock actions that efficiently combine multiple API calls with proper error handling.

This skill should be used when the user asks to "prepare a meeting", "JF vorbereiten", "Jour Fixe", "prepare update", "meeting agenda", "Lenkungsausschuss vorbereiten", "stakeholder update", or needs help preparing for recurring meetings and update sessions.

Use when the user says "analyze trace", "debug workflow", "why did this fail", "output is wrong", "missing data", "slow run", or needs root-cause analysis that ties Langfuse traces to code and fixes.

Daily planning and Linear task management. Use when the user asks to check Linear tasks, plan their day/week, create or update Linear issues, mark tasks done or in progress, search issues, or summarize project activity for weekly updates.

Use when the user wants to set up a new Langfuse dataset with evaluation dimensions, score configs, and judge prompts (LLM-as-judge or human review).

Use this skill when the user needs to define evaluation metrics, select datasets, or design grading/annotation strategies for agent optimization. Provides a structured, decision-driven workflow and reusable templates.

Use this skill when the user invokes /optimize, /optimize-bootstrap, asks to "improve my agent", "run optimization loop", "iterate on agent quality", "systematic agent improvement", "bootstrap optimization", "build evaluation infrastructure", or needs guidance on hypothesis-driven optimization cycles. Provides the full methodology for iterative AI agent improvement in Codex, including bootstrap workflows for users without existing datasets or graders.

YouTrack operations and weekly reporting. Use when the user asks to add KW updates, review epic health, prepare JF agendas, create project overviews, compile weekly emails from YouTrack, update YouTrack epics, or sync Linear issues to YouTrack Aufgaben.

プロジェクト構造を分析し CLAUDE.md、skills、hooks、agents、commands を自動生成するスキル。「Claude 設定を生成」「CLAUDE.md を作成」「プロジェクトを初期化」「Claude をセットアップ」と言われた場合に使用。既存設定がある場合は「Claude 設定を更新」「再解析」で最新化。

Phoenix GraphQL observability for LLM and application traces. Use when analyzing LLM performance, debugging API calls, querying traces and spans, or investigating OpenTelemetry telemetry data.

Protocols for agents that modify the MCP platform itself (vs agents that use the tools). Use when editing tool source code, deploying services, or changing platform architecture.

Reactor workflows and Oban background jobs for Elixir applications - use this skill when working with multi-step transactional workflows (sagas), background job processing, compensation patterns, or integrating workflows with jobs. Essential for building reliable asynchronous operations with automatic rollback and actor context propagation.

Trigger asynchronous work for an agent

分析结构化数据并生成统计报告和可视化建议

Sentry issue triage and investigation with automatic cross-linking. Handles issue investigation, AI analysis via Seer, and integration with Linear for tracking fixes. Use when triaging Sentry errors, investigating sentry.io URLs, or creating Linear issues from Sentry.

Generates release notes and changelog entries for the DocumentDB VS Code extension. Use when preparing version releases, creating patch update notes, writing changelog entries, or documenting new features and fixes. Handles both major/minor versions (new file) and patch updates (append to existing file).

Sync dotfiles from private chezmoi repository to public dotfiles repository. Use when the user requests to update their public dotfiles repo, sync dotfiles, or copy dotfiles from chezmoi to the public repository. This skill renders chezmoi templates and applies safety filtering to prevent accidentally exposing sensitive files.

Native Fabric pattern execution for Claude Code. USE WHEN processing content with Fabric patterns (extract_wisdom, summarize, analyze_claims, threat modeling, etc.). Patterns run natively in Claude's context - no CLI spawning needed. Only use fabric CLI for YouTube transcripts (-y) or pattern updates (-U).

检查 VVCode 定制功能的完整性。验证核心模块（认证、设置、余额、补全等）的文件是否存在、代码是否完整。用于合并上游后验证或日常完整性检查。使用方式：告诉 AI "检查 VVCode 功能完整性" 或 "验证 vv-auth 模块"。

Activates after local and remote testing pass. Use when finishing work, wrapping up a CR, preparing to mark implemented, creating implementation notes, updating data models, or adding semantic tags. MUST complete before transitioning work item to implemented.

NOTE: Line numbers approximate, update after refactoring -->

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

PostgreSQL query and migration expert for sqlc. Use when working with `*/sql/*`, `*/sql/queries/*`, or `*/sql/migrations/*` directories. Ensures idiomatic, well-structured queries and migrations following sqlc best practices.

Create conference talk outlines and iA Presenter markdown slides using the Story Circle narrative framework. Use when the user wants to structure a tech talk, create presentation slides, or needs help organizing talk ideas into a story-driven format.

Manages CDP parent segments using `tdx ps` commands with YAML configs. Covers master tables, attributes, behaviors, `tdx ps validate` for join validation, `tdx ps preview` for data preview, and schedule configuration (daily/hourly/cron). Use when creating customer master tables, validating join match rates, or troubleshooting parent segment workflows.

Validates CDP segment YAML configurations against the TD CDP API specification. Use when reviewing segment rules for correctness, checking operator types and values, or troubleshooting segment configuration errors before pushing to Treasure Data.

Auto-update .AGENTS.md files based on code changes.

Centralized list of commands safe for auto-execution without user approval. Single source of truth.

Complete protocol for archiving TASK.md with ID generation. Single source of truth for archiving.

Guidelines for managing the Product-to-Technical handoff, including Quality Gates and BRD Compilation.

Persist and restore agent session context (Mode, Task, Summary) to survive resets.

Stage Cycle pattern and dispatch table for Orchestrator compression. Defines common Init→Review→Revision flow.

Guidelines for creating and refining Product Vision and Strategy.

Starts the Orchestrator 3 Stream application (backend + frontend) in background mode. Use when the user asks to start orchestrator, launch orchestrator, run orchestrator, or open the orchestrator UI. Supports --session and --cwd flags for backend.

Validate code examples in documentation for syntax, correctness, and best practices. Use when reviewing or creating tutorials with code samples. Essential for ensuring all examples work.

Create isolated git worktrees with smart directory selection and safety verification

Deploy and use skills in any repository as IDE-agnostic markdown documentation

Contribute skills back to upstream via branch and PR

Semantic code search. Use alongside grep - grep for exact strings, osgrep for concepts.

Static analysis security scanning with Semgrep

Use when creating new Rust library projects with production-ready setup. Provides guidance for using the standardized lib template via cargo-generate, including CI/CD workflows, pre-commit hooks, security auditing, and changelog automation. Triggers: lib template, cargo generate, rust library template, new library project, 新库项目.