AI Skills Hub - Browse 180,000+ Agent Skills

Visualization patterns for sparse single-cell gene expression data. Trigger: boxplots flat at zero, single-cell expression plots, sparse data visualization

Spatial region-aware cell matching for CODEX/scRNAseq integration

Scale alignment for RNA-protein cross-modal integration - BOTH modalities must be z-scored

Python package reorganization with pyproject.toml inside package directory

Generate a print-optimized, ATS-friendly single-page resume PDF from portfolio content. Use when user wants to create or regenerate their resume. (project)

Preventing Jupyter cell hangs with explicit CuPy GPU memory cleanup

Multi-format channel name parsing for KINTSUGI CHANNELNAMES.txt files

SNAKE vs RASTER tile acquisition patterns for image stitching in KINTSUGI

Analyze Claude Code session transcripts to debug plugins, understand context usage, and trace execution flow

Comprehensive org-mode file generation and editing with proper syntax, formatting, and structure. Use when Claude needs to work with org-mode files (.org) for: (1) Creating new org-mode documents, (2) Editing existing org files while preserving formatting, (3) Converting content to org-mode format, (4) Ensuring correct org-mode syntax for headlines, properties, links, timestamps, and other elements. IMPORTANT: This skill is for general org-mode files. For org-roam notes (files in roam/ directory), use the org-roam-skill instead.

Use this skill to diagnose and repair broken tests with a methodical, surgical approach.

Use when needing to search Slack message history, find past conversations, or retrieve channel messages - provides Slack Web API patterns for search.messages and conversations.history endpoints using WebFetch or curl

Expert assistant for provisioning charm development and testing environments using concierge. Use when setting up development machines, bootstrapping Juju controllers, installing craft tools (charmcraft, snapcraft, rockcraft), or preparing test environments. Keywords include concierge, provision, development environment, Juju bootstrap, LXD, MicroK8s, K8s, craft tools, prepare, restore.

Use when updating filter options in Dawncaster card/talent browser after game expansions release - systematically checks ALL filter types (categories, rarities, types, banners, expansions) across both HTML dropdowns and JavaScript arrays to prevent missing updates

Use when configuring Spectral for API linting, creating custom rulesets, and validating OpenAPI or AsyncAPI specifications

Implement persistent storage with Docker volumes, bind mounts, and backup strategies

Docker Swarm orchestration, cluster management, and production deployments

Secure Docker containers and images with hardening, scanning, and secrets management

Generates three project-specific behavioral mode skills (planner, debugger, qa-tester) from project memories and bundled templates, and makes them selectable via switching-modes. Use when creating project-local agent modes for a repository.

Alembic を使用した DB マイグレーション管理スキル。 スキーマ変更、履歴管理、ロールバックの標準手順を提供。

Railway platform CLI for service deployment, infrastructure management, and debugging. Use for creating services, managing deployments, configuring networking, and reviewing logs.

Master Solidity smart contract development with patterns, testing, and best practices

Master Ethereum development including EVM, gas optimization, and client interactions

CI/CD（GitHub Actions、Screwdriver）の確認方法とトラブルシュート。 推測ではなく、必ずログを確認してから対策を講じる。

Analyze a project to provide a summary of line counts per programming language (e.g., how many lines of Go vs Rust). Generates a PDF summary report.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Expert Neovim/Lua configuration assistant for NOE.ED (LazyVim-based setup). Covers plugin configuration, LSP setup, keymaps, Mason, TreeSitter, and troubleshooting. Trigger with: neovim skill, lua skill, nvim skill, neoed skill, lazy skill (or plurals). Use for: LSP config help, error troubleshooting, keymap creation, plugin setup, theme customization.

Execution status management and reporting for implementation plugin. Use when initializing execution tracking, updating task status, generating progress reports, calculating completion metrics, tracking layer execution, monitoring feature implementation progress, or when user mentions execution status, progress tracking, or implementation monitoring.

Templates and scripts for generating layered BUILD-GUIDE.json/md from Airtable plugin index - shows available commands organized by infrastructure layers

Framework and stack identification with detection scripts and patterns. Use when detecting project type, analyzing framework, identifying stack, initializing projects, or when user mentions project detection, framework analysis, stack identification, or codebase analysis.

Vercel deployment using Vercel CLI for Next.js, React, Vue, static sites, and serverless functions. Includes project validation, deployment orchestration, environment management, domain configuration, and analytics integration. Use when deploying frontend applications, static sites, or serverless APIs, or when user mentions Vercel, Next.js deployment, serverless functions, or edge network.

Generic DigitalOcean droplet deployment using doctl CLI for any application type (APIs, web servers, background workers). Includes validation, deployment scripts, systemd service management, secret handling, health checks, and deployment tracking. Use when deploying Python/Node.js/any apps to droplets, managing systemd services, handling secrets securely, or when user mentions droplet deployment, doctl, systemd, or server deployment.

DigitalOcean App Platform deployment using doctl CLI for containerized applications, web services, static sites, and databases. Includes app spec generation, deployment orchestration, environment management, domain configuration, and health monitoring. Use when deploying to App Platform, managing app specs, configuring databases, or when user mentions App Platform, app spec, managed deployment, or PaaS deployment.

Post-deployment validation and health check scripts for validating HTTP endpoints, APIs, MCP servers, SSL/TLS certificates, and performance metrics. Use when deploying applications, validating deployments, testing endpoints, checking SSL certificates, running performance tests, or when user mentions health checks, deployment validation, endpoint testing, performance testing, or uptime monitoring.

Vercel and Cloudflare canary deployment patterns with traffic splitting, gradual rollout automation, and rollback strategies. Use when deploying with canary releases, implementing progressive rollouts, managing traffic splitting, configuring A/B deployments, or when user mentions canary deployment, blue-green deployment, gradual rollout, traffic shifting, or deployment rollback.

Automated CI/CD pipeline setup using GitHub Actions with automatic secret configuration via GitHub CLI. Generates platform-specific workflows (Vercel, DigitalOcean, Railway) and configures repository secrets automatically. Use when setting up continuous deployment, configuring GitHub Actions, automating deployments, or when user mentions CI/CD, GitHub Actions, automated deployment, or pipeline setup.

Provides FastMCP templates, patterns, and reference materials. Use when building MCP servers, implementing FastMCP tools/resources/prompts, or working with MCP protocol compliance.

Doctor de Componentes para YuKyuDATA - Diagnóstico y reparación de componentes rotos, detección de bugs visuales, memory leaks, problemas de accesibilidad, inconsistencias CSS, y refactoring de código legacy. Incluye herramientas de auditoría automatizada.

Sanitizers skill for the ikigai project

Memory Refactoring (talloc) refactoring skill

Result Type Pattern (C-Specific) pattern for C development

Secrets Management security skill

Terminal Security security skill

GDB Server skill for the ikigai project

Valgrind skill for the ikigai project

User Stories skill for the ikigai project

Marpを使用した提案資料・比較検討資料の作成スキル。課題提示、複数案の比較検討、メリット・デメリット整理を含む資料を作成する。使用場面：(1) 技術選定や方式比較の検討資料、(2) 提案書・企画書、(3) 問題解決策の提示、(4) 意思決定を支援するドキュメント。作成完了後は必ずサブエージェントでレビューを実施する。

使用 Skill Seekers MCP 工具生成 Claude AI 技能的完整工作流指南

文档驱动开发（DDD）文档管家：以仓库真实证据为准，盘点 ~/project 与 docs 目录，生成/更新 SSOT 文档（计划→补丁/全文→摘要→一致性检查）。触发：需要让文档与代码/配置/运行方式同步、补齐 guides/integrations/features/architecture/incidents/archive、无法推导时标注【待确认】并给验证路径。

File descriptor abuse, race conditions, and TOCTOU vulnerabilities

Timeline Mode specialist - handles release planning, scheduling, task sequencing, and visual timeline layouts for artists.

API route specialist - handles route scaffolding, Zod validation, authentication, error handling, and endpoint consistency.

Zustand store specialist - handles store generation, sync patterns, selectors, and persistence for totalaud.io state management.

Master Terraform state management including remote backends, locking, workspaces, and state operations

Create reusable, composable Terraform modules with proper versioning and registry integration

Testing Terraform configurations with native tests, Terratest, and validation frameworks

Extracts and displays JSON data from Apache Avro files. Use this when the user wants to read, convert, or view the contents of an .avro file. Automatically deserializes nested JSON fields for better readability.

Delegates coding tasks to Coco CLI (Codebase Copilot) for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSION_ID.

Use when about to claim work is complete, fixed, or passing. Requires running verification commands and confirming output before making any success claims. Evidence before assertions, always.

Use when you have a design or requirements for a multi-step task, before writing code. Creates bite-sized TDD task plans with exact file paths, complete code, and verification steps.

Use when facing 2+ independent tasks that can be worked on without shared state. Dispatch one agent per problem domain for concurrent investigation.

Use before any creative work - creating features, building components, adding functionality. Explores user intent, requirements, and design before implementation. One question at a time, multiple choice preferred.

Terraform構成の依存関係管理とバリデーションを評価・強化するスキル。Terraform 1.14以上を対象に、variable validation、depends_on/lifecycle、precondition/postcondition、check blockの現状評価と改善提案を実施。(1) 既存Terraform構成の評価・診断、(2) バリデーション不足の自動検出と修正提案、(3) ベストプラクティス適用、(4) セキュリティ・可用性要件の検証が必要な場合に使用。

Use when implementation is complete and tests pass. Guides completion by presenting structured options for merge, PR, or cleanup.

Restarts WitchCityRope Docker TEST containers using the CORRECT procedure. Handles shutdown, rebuild with test compose overlay (--no-cache by default), health checks, and verification. Ensures environment is ready for testing. SINGLE SOURCE OF TRUTH for test container restart process. Uses -p witchcityrope-test for isolation from dev containers.

Restarts WitchCityRope Docker DEVELOPMENT containers using the CORRECT procedure. Handles shutdown, rebuild with dev compose overlay, health checks, and compilation verification. Ensures environment is ready for development. SINGLE SOURCE OF TRUTH for dev container restart process. Uses -p witchcityrope-dev for isolation from test containers.

Resets production database with full schema drop. EXTREME CAUTION - deletes all production data. SINGLE SOURCE OF TRUTH for production database reset automation.

Run all tests (unit, integration, E2E) in isolated containers separate from dev environment. Handles build, container startup, health checks, test execution, and cleanup. SINGLE SOURCE OF TRUTH for running tests in isolated containers.

Validates Finalization Phase completion before workflow concludes. Checks documentation updates, file registry, git commits, deployment readiness, and lessons learned contributions.

Deploys WitchCityRope to staging environment on DigitalOcean. Automates build, registry push, server deployment, database migrations (if needed), health verification, and rollback capability. SINGLE SOURCE OF TRUTH for staging deployment automation.

Deploys WitchCityRope to production environment on DigitalOcean. Automates build, registry push, server deployment, database migrations (if needed), health verification, and rollback capability. SINGLE SOURCE OF TRUTH for production deployment automation.

Validates Implementation Phase completion before advancing to Testing Phase. Checks code compilation, test coverage, implementation completeness, and code quality standards.

Resets local development database by deleting all data and restarting API container to trigger auto-seeding. SINGLE SOURCE OF TRUTH for dev database reset automation.

Validates Testing Phase completion before advancing to Finalization Phase. Checks test execution results, coverage targets, test quality, and environment health. Ensures 100% test pass rate required by quality gates.

Automates cleanup of old container images from DigitalOcean registries based on retention policies. Keeps last 10 tags for staging, 30 for production, always preserves :latest.

Validates Design Phase completion before advancing to Implementation Phase. Checks functional specifications, database design, and UI/UX design for completeness and technical feasibility.

Resets staging database with full schema drop. Use for schema changes or migrations. SINGLE SOURCE OF TRUTH for staging database reset automation.

Web/アプリの画面ワイヤーフレーム（構造・レイアウト・導線）をASCII図とMarkdown注釈で作成するSkill。 「ワイヤーフレームを作って」「画面構成を設計して」「画面のレイアウトを考えて」「UI構造を整理して」「画面の骨組みを作って」 「wireframeを書いて」「画面設計して」「ラフを作って」などの依頼で発動する。 出力はASCIIワイヤーフレーム + 画面注釈（状態・制約・挙動）のMarkdown。モックアップ（見た目重視）やプロトタイプ（動作検証）とは異なる。

PRD（Product Requirements Document）を、Universal PRDフォーマット（軽量1ページ〜詳細版まで同じ型）で作成する。 ユーザーが「PRDを書いて」「要件定義書を作って」「仕様をまとめて」「Press Release / FAQ（Working Backwards）を書いて」 「Shape UpのPitchっぽく提案書を作って」「成功指標/KPIとスコープを整理して」などを依頼したときに使う。 出力はMarkdown。必要に応じて1ページ版→標準版→詳細版へ段階的に拡張する（progressive disclosure）。

UXの「5層モデル（Strategy/Scope/Structure/Skeleton/Surface）」に基づいて、要件〜画面設計を一貫して設計し、 各層の問い・意思決定・成果物をMarkdownで作成するUXデザイナーとして振る舞うSkill。 新規プロダクト/機能のUX設計、既存UXの課題診断、PRD/仕様/画面フロー/ワイヤー/モックの整合性レビューに適用する。 トリガー例: 「UXを5層で設計」「Garrett 5 planes」「戦略/要件/構造/骨格/表層」「ユーザーフロー/サイトマップ/ワイヤーフレーム」

Crawl and ingest websites into whorl. Use when scraping a personal site, blog, or extracting web content for the knowledge base.

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

Create, evaluate, and improve Agent skills...

新機能調査、提案、設計方針確認時に使用。

Use when writing SQL queries, optimizing database performance, or analyzing data

Guide for adding localized text using l10n in app_lib/locale package (project)

Systematic workflow and API reference for integrating Streamlit playground with vrp-toolkit modules. Use when developing playground features, connecting UI to vrp-toolkit APIs, or encountering API signature mismatches. Provides interface mapping table, contract test integration, and troubleshooting guide to avoid token-intensive source code exploration.

Manage and maintain VRP Toolkit skills through compliance checking, audit tracking, and documentation synchronization. Use when (1) adding or modifying skills, (2) checking skill compliance with project standards, (3) auditing SKILLS.md vs skills directory consistency, (4) recording skill changes to SKILLS_LOG.md, or (5) performing periodic skill health checks. Ensures skills stay independent, under 500 lines, properly structured, and well-documented.

Integrate real-world street networks into VRP problems using OpenStreetMap data. Use when loading real map data, creating instances from actual locations, computing network-based distances, or building tutorials with real-world scenarios. Guides through installation, loading areas, extracting nodes, computing distance matrices, and creating PDPTW instances from map data.

GitHub 이슈 해결 워크플로우. 분석 → 구현 → 검증 자동화.

코드 품질 검사 자동화. 린트, 포맷, 타입 체크, 보안 스캔 통합.

通过 bird CLI 发布和管理 Twitter/X 内容。使用此 skill 当用户需要：(1) 发布推文或帖子，(2) 回复推文，(3) 读取或获取推文内容，(4) 搜索推文，(5) 查看 mentions/bookmarks/likes，(6) 附带图片或视频发推。触发词包括：发推、tweet、发帖、回复推文、读取推文、Twitter、X 平台。

Specification-Driven Development (SDD) methodology for building software where specifications are executable and drive code generation. Use when users want to: (1) Create feature specifications with /speckit.specify, (2) Generate implementation plans with /speckit.plan, (3) Create executable tasks with /speckit.tasks, (4) Follow test-first, library-first development, or (5) Implement constitutional architecture principles. Essential for structured AI-assisted development workflows.

Build and test the LocalizeAR Swift project using build.sh scripts. Use this skill whenever building, testing, or cleaning the project. NEVER use xcodebuild or swift build directly - always use build.sh.

Validates skills against production-level criteria with 9-category scoring. This skill should be used when reviewing, auditing, or improving skills to ensure quality standards. Evaluates structure, content, user interaction, documentation, domain standards, technical robustness, maintainability, zero-shot implementation, and reusability. Returns actionable validation report with scores and improvement recommendations.

用于 HarmonyOS NEXT 和 ArkTS 开发，特别是处理 .ets 文件、实现 @ComponentV2 组件或调试错误时使用。基于官方标准提供开发指导，并维护分类错误日志以实现高效故障排查。

Comprehensive plugin auditing for compliance with marketplace best practices. MUST Use when validating, refactoring, or improving plugin quality. Do not use for creating new plugins, scaffolding components, or development tasks.

This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.

Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.

Build, update, and troubleshoot AllayMC plugins in Java or other JVM languages. Use when creating a new AllayMC plugin, migrating an existing plugin to a new Allay API version, wiring commands/events/tasks/config, or setting up Gradle and plugin metadata (plugin.json or AllayGradle plugin block).