AI Skills Hub - Browse 180,000+ Agent Skills

This skill should be used when the user wants to manage Railway deployments, view logs, or debug issues. Covers deployment lifecycle (remove, stop, redeploy, restart), deployment visibility (list, status, history), and troubleshooting (logs, errors, failures, crashes, why deploy failed). NOT for deleting services - use environment skill with isDeleted for that.

This skill should be used when the user wants to push code to Railway, says "railway up", "deploy", "deploy to railway", "ship", or "push". For initial setup or creating services, use new skill. For Docker images, use environment skill.

This skill should be used when the user asks about resource usage, CPU, memory, network, disk, or service performance. Covers questions like "how much memory is my service using" or "is my service slow".

This skill should be used when the user wants to add a database (Postgres, Redis, MySQL, MongoDB), says "add postgres", "add redis", "add database", "connect to database", or "wire up the database". For other templates (Ghost, Strapi, n8n, etc.), use the templates skill.

Users can become experts through multiple paths. Expertise is recognized at different geographic levels.

Guides GetIt dependency injection patterns for service registration. Use when creating new services, registering dependencies, or refactoring service architecture.

Browser notifications with Web Audio API sounds. Use when implementing task reminders, due date alerts, or notification sounds in web applications.

Normalize static analysis reports (QAC, PC-lint/FlexeLint, Coverity, clang-tidy, cppcheck, GCC/Clang warnings) into a single JSON schema for Automotive ECU CI pipelines. Produces stable, machine-readable findings plus human-friendly summaries.

Explain MISRA C rule violations and produce minimal, behavior-preserving fixes for Automotive ECU C code. Parses common static analysis outputs, classifies findings into MISRA-oriented buckets, suggests fix patterns, and can optionally cite official MISRA PDF locations if an index is provided.

Generate comprehensive UAT (User Acceptance Testing) test scripts for end users with click-path instructions, action steps, and expected results. USE WHEN user mentions UAT, user acceptance testing, test script, testing script, end user testing, OR says generate, create, write followed by UAT, test script, or testing instructions.

Generate comprehensive Salesforce documentation including job aids, technical specifications, runbooks, and user guides. USE WHEN user mentions documentation, job aid, user guide, technical spec, runbook, how-to, OR says create, generate, write followed by documentation, guide, spec, or runbook.

Generate images using Google's Gemini API. Use this skill when the user wants to generate, create, or edit images with AI. Keywords: image generation, create image, generate picture, AI art, edit image, Gemini, icon, render, illustration.

SkillsBench contribution workflow. Use when: (1) Creating benchmark tasks, (2) Understanding repo structure, (3) Preparing PRs for task submission.

规范驱动开发 (SDD) 与双仓 (Gitea/GitHub) 同步管家。当用户需要初始化项目、开始新功能开发、进行高频本地存档 (Checkpoint)、或在 GitHub 合并后同步本地状态时，此技能提供严格的 Git 工作流指导。它确保 Spec 领先于代码，且 GitHub 历史记录保持整洁。

Guide for building CompCert, the formally verified C compiler, from source. This skill should be used when compiling, building, or installing CompCert, or when working with Coq-based software that has strict dependency version requirements. Covers OCaml/opam setup, Coq version compatibility, memory management, and common build pitfalls.

Guide for extracting code or pseudocode from images using OCR and implementing it correctly. This skill should be used when tasks involve reading code, pseudocode, or algorithms from images (PNG, JPG, screenshots) and executing or implementing the extracted logic.

Professional press release writing and distribution strategy for B2B companies. Use when creating press releases for product launches, funding announcements, market/location expansions, or awards/recognition. Guides users through data gathering, newsworthy angle development, quote strategy, wire distribution selection, and journalist pitch emails. Adapts output based on available context - complete drafts when inputs are rich, section-by-section building when starting from scratch.

Guidance for text embedding retrieval tasks using sentence transformers or similar embedding models. This skill should be used when the task involves loading documents, encoding text with embedding models, computing similarity scores (cosine similarity), and retrieving/ranking documents based on semantic similarity to a query. Applies to MTEB benchmark tasks, document retrieval, semantic search, and text similarity ranking.

Guidance for setting up HuggingFace model inference services with Flask APIs. This skill applies when downloading HuggingFace models, creating inference endpoints, or building ML model serving APIs. Use for tasks involving transformers library, model caching, and REST API creation for ML models.

Guidance for building and fixing Cython extensions, particularly for numpy compatibility issues. This skill should be used when tasks involve compiling Cython code, fixing deprecated numpy type errors, or resolving compatibility issues between Cython extensions and modern numpy versions (2.0+).

Guidance for recovering data from SQLite Write-Ahead Log (WAL) files that may be corrupted, encrypted, or inaccessible. This skill should be used when tasks involve database recovery, WAL file analysis, decrypting database files, or recovering missing/corrupted SQLite data. Helps avoid common pitfalls like fabricating data based on patterns instead of actual recovery.

Guide for implementing gRPC-based key-value store services in Python. This skill should be used when building gRPC servers with protobuf definitions, implementing KV store operations (Get, Set, Delete), or troubleshooting gRPC service connectivity. Applicable to tasks involving grpcio, protobuf code generation, and background server processes.

Guidance for setting up Git repositories with automatic web deployment via post-receive hooks. This skill applies when configuring bare Git repositories, setting up web servers to serve pushed content, creating Git hooks for deployment automation, or implementing push-to-deploy workflows.

This skill should be used when the user explicitly wants to review plans, implemented code, or other content using Codex. It invokes the codex CLI in non-interactive mode with solid prompts containing clear background and context.

Implement data fetching with tRPC queries, mutations, and cache management

Implements inbound and outbound webhook handling with signature verification, Zod validation, and idempotency. Use when integrating external services via webhooks, handling Stripe/Clerk/GitHub webhooks, or when the user mentions "webhook", "handle events", "Stripe integration", "external provider".

Use when the user mentions 'GWOSC', 'gravitational waves', 'LIGO', 'Virgo', or asks to find gravitational wave events, get event parameters, or download strain data. GWOSC provides open data from gravitational wave detectors.

Use when the user mentions 'HEPData' or asks to find experimental data, download data tables from HEP papers, get digitized plots, or retrieve cross-section measurements. HEPData contains data points behind figures in high-energy physics publications.

Use when the user mentions 'INSPIRE', 'INSPIRE-HEP', 'inspirehep', or asks to search high-energy physics literature, find HEP papers, get citation counts, or retrieve BibTeX from INSPIRE. Specializes in particle physics, quantum field theory, and related fields.

Use when the user mentions 'arxiv' or asks to find, search for, or download arxiv papers (by arxiv ID, author name, or topic), get paper source code, or retrieve LaTeX files from arxiv. Can search for papers to find arxiv IDs when only author/topic is provided, then download them. Prefer source format over PDF.

Use when the user mentions 'ADS', 'NASA ADS', 'Astrophysics Data System', or asks to search astronomy/astrophysics literature, find papers by bibcode, get citation counts from ADS, or retrieve BibTeX from the ADS database.

Use when the user mentions 'Zenodo' or asks to find, search, or download datasets, software, or research artifacts with DOIs. Zenodo hosts scientific datasets, code releases, and supplementary materials from publications.

Use when creating or updating rules in CLAUDE.md, settings, or rule files. Covers confidence thresholds and false positive prevention.

Use for parallel branch development with workspace isolation.

Use when documenting reusable code patterns, architectural approaches, or established solutions with keyword triggers and anti-patterns.

Use when creating new skills, editing existing skills, or verifying skills work before deployment. Follows TDD methodology.

Use when creating new agents, defining agent roles, or configuring agent handoff protocols and model selection.

Supabase client setup, Row Level Security (RLS), edge functions, and real-time. Use when working with Supabase database, auth, or edge functions.

Use when creating hooks for prompt interception, permission handling, or event-triggered automation with timeout and bypass handling.

경쟁사 리뷰 분석 자동화. "경쟁사 분석", "한샘 리뷰 분석", "리뷰 크롤링", "competitor analysis", "다나와 리뷰", "상품 리뷰 수집", "리뷰 분석해줘" 등을 언급하거나 다나와 URL을 제공하면 자동 실행. 크롤링 → AI분석 → 인사이트 도출까지 전체 SOP 수행.

올리브영 상품 리뷰 분석. "올리브영 분석", "올영 리뷰", "화장품 리뷰 크롤링", "oliveyoung.co.kr" 등을 언급하거나 올리브영 URL을 제공하면 자동 실행. (project)

Expert guidance for creating and working with marimo notebooks - reactive Python notebooks that can be executed as scripts and deployed as apps. Use when the user asks to create marimo notebooks, convert Jupyter notebooks to marimo, build interactive dashboards or data apps with marimo, work with marimo's reactive programming model, debug marimo notebooks, or needs help with marimo-specific features (cells, UI elements, reactivity, SQL integration, deploying apps, etc.).

Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.

Image and video analysis via z.ai GLM-4.6V vision model. Use for analyzing screenshots, extracting text/code from images (OCR), diagnosing errors from screenshots, understanding technical diagrams, reading charts/dashboards, comparing UI screenshots, and analyzing videos. Powered by MCP.

Calendar canvas for displaying events and picking meeting times. Use when showing calendar views or when users need to select available time slots.

Flight canvas for comparing flights and selecting seats. Use when users need to browse flight options and book seats.

Works response: ```json { "status": "ok", "message-type": "work-list", "message": { "total-results": 12345, "items": [ { "DOI": "10.1038/nature12373", "title": ["Paper Title"], "author": [ { "given": "John", "family": "Smith", "ORCID": "https://orcid.org/0000-0001-2345-6789" } ], "container-title": ["Nature"], "published": { "date-parts": [[2024, 3, 15]] }, "type": "journal-article", "is-referenced-by-count": 42, "references-count": 35, "abstract": "<jats:p>Abstract text...</jats:p>", "URL": ...

A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.

Choose based on aesthetic needs:

A user may ask you to create, edit, or analyze the contents of an .xlsx file. You have different tools and workflows available for different tasks.

Expert on FLUI's three-tree architecture (View-Element-Render), widget composition, and Flutter-inspired patterns. Use when discussing views, elements, render objects, widget trees, or UI architecture.

Complete release workflow for Markdown Preview Enhanced. Use when publishing a new version, bumping versions, or updating distribution channels (GitHub, Sparkle, Homebrew). Triggers include "release", "publish", "bump version", "make release", "create release", or any request involving version management and distribution updates.

Expert on FLUI's reactive state management with signals, hooks, and effects. Use when discussing state, signals, use_signal, use_effect, reactivity, or data flow.

Project-wide coding and database design standards for Python + MySQL codebases. Use when adding or modifying Python modules, project structure, data access layers, SQL queries, or schema/migrations; and when reviewing for scope creep or standards compliance.

Comprehensive Qt compiler error resolution guide covering common CMake/qmake build issues, MOC (Meta-Object Compiler) problems, linking errors, and Qt framework integration issues. Use when encountering Qt compilation failures with Q_OBJECT, vtable errors, signal/slot connection problems, or build system configuration issues.

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

Writing Move modules, testing, and deployment on Movement Network. Use for smart contract development. (project)

Writing Move modules, testing, and deployment on Movement Network. Use for smart contract development. (project)

This skill should be used when building cube draft configurations for GEMP-SWCCG from CSV files containing card names. It handles mapping card names to IDs, generating cube configurations with add-on card support, and integrating the cube into the application (swccgDrafts.json registration and frontend dropdown setup).

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

Manage email inbox including triage, prioritization, summaries, and automation rules. Use when checking emails, organizing inbox, setting up filters, asking about messages, or anything email-related.

Use when needing to search academic papers in engineering fields (electrical, microgrid, railway, thermal, renewable energy). Searches Semantic Scholar, filters results, and saves to markdown with deduplication.

Comprehensive codebase analysis and understanding tool for OSS projects. This skill should be used when users need to understand existing code architecture, trace data flows, analyze dependencies, or comprehend pull request contexts. Ideal for onboarding to new projects, deep code reading, and systematic codebase exploration.

Manages git operations: worktree creation, branch management, commits, PRs, semantic versioning, daily rebase workflow, and PR feedback handling. Use when: Creating branches/worktrees, committing, pushing, versioning, handling PR feedback Triggers: create worktree, commit, push, rebase, version, PR, PR feedback

Use the Cursor CLI (agent) for software engineering tasks. Includes installation, auth, commands, and tmux-based automation for AI/agent invocation.

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

AI 건축 기획설계 서비스 개발 스킬. Flexity 벤치마킹 프로젝트로 Next.js + Tailwind + Three.js 기반. VWorld/공공데이터포털 API 연동 및 Google Gemini AI 통합. 사용 시점 - 토지분석 API 개발, AI 매스 스터디, 수익성 분석, 3D 시각화, Lambda 프록시 구현. 핵심 규칙 - URL 끝 슬래시 필수, 한글 파라미터는 POST+JSON, 타임아웃 설정, CORS 헤더.

Design or refactor skills by separating deterministic and non-deterministic steps. Use when creating or improving skills, especially to move repeatable workflows into scripts/ and update SKILL.md to call them.

Use when ready to publish a new version. Triggers on "release", "publish", "ship it", or version bump requests. Runs quality checks, bumps version, tags, and creates GitHub release.

This skill should be used when automating repetitive workflows, creating task pipelines, setting up CI/CD processes, or orchestrating multi-step operations. It provides templates and scripts for common automation scenarios.

将任何 MCP 服务器封装为 Claude Skill，支持 stdio/SSE/HTTP 传输协议

Document a software project in this repo’s portfolio data model by extracting tech stack, learnings, screenshot, and live links from a Git repository and updating src/data/projects.ts for the ProjectPage.

This skill should be used when working with REST APIs, including making requests, handling authentication, parsing responses, error handling, and rate limiting. It provides structured workflows for API integration and testing.

AI image generation powered by OpenAI's GPT Image model (chatgpt-image-latest).

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

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.

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.

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

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 isn't a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.

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.

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

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

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.

Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.

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

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

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.

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

Collect and analyze Git commit history from GitHub, GitLab, and/or local git repos; filter by author and year; and generate an annual work summary/述职/自评 report draft and prompt (Markdown) using Conventional Commits semantics and business-impact framing. Use when asked to write 年度工作总结/述职 based on git commits, to summarize contributions by repo/author/year, or to produce a reusable workflow that supports both GitHub and GitLab.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Provide **clean, predictable, and standardized API interaction patterns** using **Axios** for dashboard applications.

Writing Move modules, testing, and deployment on Movement Network. Use for smart contract development. (project)

Diagnose system performance issues: CPU/memory usage, disk space, and cleanup. Use when user asks: what's slowing down my computer, why is my Mac slow, what's using CPU/memory/disk, check system performance, find resource hogs, free up space, clean disk, 电脑卡, 查看系统占用, 什么进程占用资源, 磁盘清理, 清理缓存, 磁盘空间不足. Shows process trees and identifies cleanable items.

Automated UI testing using Playwright. Opens browsers, navigates URLs, clicks through UI flows, fills forms, takes screenshots, and tests complete user journeys. Use after frontend changes to verify the UI works correctly. Triggers on "ui test", "test the ui", "browser test", "screenshot test", "test the frontend", "visual test".

Visual testing - catch invisible buttons, broken layouts, contrast

Rails console guide for Whop production database queries

Manages centralized configuration for Azure AI Foundry starter deployment including organization names, resource names, project names, and all other customizable values. Use this skill first to set up configuration, or when you need to retrieve/update deployment settings.

Triggers and runs Azure DevOps pipelines via Azure DevOps CLI. Queues pipelines with parameters, monitors initial start status, and returns run ID for tracking. Use when you need to execute ADO pipelines programmatically.

Creates Azure AI Foundry resources including AI Services (kind AIServices) and AI Foundry Projects for multi-environment deployments. Configures RBAC permissions for Service Principals. Use when provisioning Azure AI Services and AI Foundry Projects for development, testing, or production environments.