AI Skills Hub - Browse 180,000+ Agent Skills

Operations for local container stacks defined in docker-compose.yaml or docker-compose/ directory. Handles AI/ML services (Ollama, ComfyUI), standalone databases, and local observability stacks. Use for 'docker compose' commands, checking container logs, or restarting specific local services. For cluster Grafana/Prometheus (via kubectl or cluster/manifests/), use kubernetes-operations instead.

Distill content with 5-level granularity, showing quality loss estimation before execution

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.

Backup database before tests, migrations, or other database operations

Principal/Senior-level Go (Golang) playbook for architecture, idiomatic code, concurrency, testing, performance, reliability, security, observability, and production readiness. Use when: designing services/APIs/CLIs, doing large refactors, running code reviews, debugging races/leaks, tuning performance, hardening security, and shipping to production.

Debug, diagnose, and troubleshoot skill issues including trigger failures, parameter problems, prompt conflicts, and SKILL.md structural issues. Use when skills don't activate as expected, trigger incorrectly, produce unexpected behavior, conflict with system instructions, or fail packaging validation. Analyzes YAML frontmatter, descriptions, progressive disclosure, token budget, absolute statements, and reference file organization. For skill creators reviewing, validating, or fixing skill problems.

Create and scaffold new RooGent skills with proper structure, documentation templates, and helper scripts. Use when building custom automation capabilities.

Translate A/B test lift percentages into annualized dollar projections. Shows conservative and optimistic revenue impact, break-even analysis, and opportunity cost of waiting.

Get a prioritized morning summary of all your active Intelligems tests. Shows health status, action items, emerging winners, and daily run rates — designed for daily use.

Shared Python library for Intelligems Analytics skills. Sets up the workspace, API client, metric helpers, and configuration. Run this before using any other Intelligems Analytics skill.

OCR skill using PaddleOCR model via SiliconFlow API. This skill should be used when the user asks to "recognize text from an image", "extract text from a photo", "OCR this image", "read text from screenshot", or mentions "PaddleOCR", "image text recognition", "text extraction from images".

X (Twitter) browser automation skill. Post tweets, like, reply, retweet, and quote via Playwright + Chrome. Triggers on "post tweet", "like tweet", "reply tweet", "retweet", "quote tweet", "x setup", "twitter".

Async resumable OpenCode agent sessions via CLI

Analise a saida JSON do terraform plan para o provider AzureRM para distinguir diffs falso-positivos (mudancas apenas de ordenacao em atributos do tipo Set) de mudancas reais de recurso. Use ao revisar saida do terraform plan para recursos Azure como Application Gateway, Load Balancer, Firewall, Front Door, NSG e outros com atributos Set que causam diffs espurios por mudancas internas de ordem.

Guia abrangente para criar designs profissionais de UI/UX no Penpot usando tools MCP. Use esta skill quando: (1) Criar novos designs de UI/UX para apps web, mobile ou desktop, (2) Construir design systems com componentes e tokens, (3) Projetar dashboards, forms, navegacao ou landing pages, (4) Aplicar padroes de acessibilidade e boas praticas, (5) Seguir diretrizes de plataforma (iOS, Android, Material Design), (6) Revisar ou melhorar designs existentes no Penpot para usabilidade. Gatilhos: "design a UI", "create interface", "build layout", "design dashboard", "create form", "design landing page", "make it accessible", "design system", "component library".

Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".

Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".

按本仓库约定运行 pytest、启动 uvicorn、定位测试失败并给出可复制命令。用于用户要求“跑测试/启动服务/复现问题/验证修复”或出现测试失败需要排查时。

Daily log generator: summarize yesterday or accept today's progress (casual or single-sentence), generate dated log file, update today's todo checkboxes, transfer incomplete to today. Triggers: '整理昨天的日志', '总结昨天', '汇报今天', '记录一下今天', '我完成了 X', '作业做完了', 'daily log', '运行 daily-log'.

Create, edit, and validate EnergyPlus IDF input files. Run building energy simulations and analyze results. Generate visualizations from simulation output data. Modify weather files (EPW), run parametric studies, and calibrate models against measured data. Use when working with EnergyPlus, IDF files, building energy modeling, HVAC design, thermal simulation, energy analysis, EPW weather files, parametric comparison, baseline calibration, or building geometry.

Investigate rg.exe churn and quarantine decisions in skill-arbiter runs. Use when a skill causes CPU spikes, unexpected scans, blacklist actions, or when arbitration thresholds need evidence-backed tuning.

Consolidate repository-specific skills into modular, reusable sets. Use when auditing skill overlap, splitting monolithic skills, reducing one-shot skills, defining per-repo core vs advanced skills, and planning safe deprecations with lockdown admission tests.

Best practices, references, and templates for integrating games with the Play.fun ecosystem.

Security auditing skill for AI coding agents — scans for credentials, dangerous commands, PII, and prompt injection

Control TP-Link Kasa smart plugs, switches, and bulbs locally. Use for turning devices on/off, checking status, and discovering Kasa devices on the network.

CLAUDE.mdをベストプラクティスに基づいてリファクタリング

Autonomous multi-session feature development framework. Use when the user wants to systematically implement features from a specification, track progress across sessions, and ensure all tests pass before marking features complete. Activated by the /lynyx-agent-kit:auto-coder command or when working with feature_list.json files in an .auto-coder directory.

A Windows screenshot skill that provides both programmatic full-screen capture and interactive region selection.

Efficiently navigate codebase documentation during Research phase. Use instead of Grep/Glob for finding architectural decisions, feature specs, and technical docs. Maps topics to doc locations for fast context retrieval. If codebase lacks documentation structure, provides patterns to establish one.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

直接透過 REST API 存取 UniProt。蛋白質搜尋、FASTA 檢索、ID 映射、Swiss-Prot/TrEMBL。對於需要多個資料庫的 Python 工作流程，建議使用 bioservices（40+ 服務的統一介面）。使用此技能進行直接 HTTP/REST 工作或 UniProt 專用控制。

Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.

顯微鏡資料管理平台。透過 Python 存取影像、擷取資料集、分析像素、管理 ROI/註解、批次處理，用於高內涵篩選和顯微鏡工作流程。

查詢 Ensembl 基因組資料庫 REST API，涵蓋 250+ 物種。基因查詢、序列擷取、變異分析、比較基因組學、直系同源、VEP 預測，用於基因組研究。

Upgrade JS/TS dependencies with risk assessment and Dependabot PR integration

What it does AND when to use it. This is the ONLY thing Claude sees to decide if the skill triggers. Be comprehensive.

使用 scripts/worktree.sh 管理 Git worktree, 适用于并行开发、多分支独立工作区、批量创建或清理 worktree、共享配置文件等场景。用户提到创建或删除 worktree、并行开发、不切换分支修 bug、管理 worktree、清理 worktree 时使用。

Expert Bash help for writing, debugging, and optimizing safe, portable shell one-liners and scripts on macOS/Linux. Use when users ask for Bash or POSIX sh commands, script reviews, ShellCheck fixes, quoting/pipeline issues, process/file automation, or converting requirements into shell scripts.

Use this to run and debug the UI + server locally (Vite dev server, `lotar serve`, ports, SSE).

Analyseur de qualité web basé sur le référentiel Opquast V5 (245 règles). Expert certifié pour auditer les sites selon les bonnes pratiques qualité.

Write Nodel node recipes (script.py) using Jython 2.5 - define actions, events, parameters, TCP/UDP/HTTP protocols, and device control logic. Use when creating or modifying Nodel scripts.

Post content and articles to X (Twitter). Supports regular posts with images and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation.

GitHubと連携した作業を効率的に行うためのスキル

Validate TCL AST against Lua schema definitions

Craft or refactor a CLI interface and behavior using the CLI Guidelines. Use when defining a new CLI spec or reshaping an existing command surface arguments, flags, subcommands, help text, outputs, errors, exit codes, prompts, config/env precedence, and safe/dry-run behavior.

Use when working with the Peekaboo CLI or MCP server to capture macOS screens, inspect UI elements, and automate GUI interactions (see/click/type/scroll/hotkey/window/menu/dock/space), or when troubleshooting Peekaboo permissions, snapshots, or focus issues.

Run comprehensive code quality checks including TypeScript typecheck, ESLint linting, Prettier formatting, and Markdown validation. Auto-fixes formatting issues in agent mode or provides read-only checks for CI pipelines. Use when: (1) Before committing code changes, (2) In CI/CD pipelines for automated quality gates, (3) After making significant code changes, (4) When preparing code for review, (5) When ensuring code meets quality standards, (6) For type checking, linting, formatting, and markdown validation, (7) In pre-commit hooks, or (8) For automated quality gates before merging. Triggers: finalize, code quality, typecheck, lint, format, check code, quality check, run checks, pre-commit, before commit, CI checks, validate code.

Analyze git diff to identify code changes requiring documentation updates. Categorizes changes (database/schema, API endpoints, components, configuration, authentication) and suggests relevant documentation files to review. Use when: (1) After making code changes, (2) Before committing significant changes, (3) When adding new features or modifying APIs, (4) During PR preparation, (5) When working with database schemas, API routes, components, or configuration files, (6) To ensure documentation stays synchronized with code changes, (7) For documentation sync and maintenance, or (8) For pre-commit documentation checks. Triggers: check docs, docs check, documentation check, update docs, sync documentation, what docs need updating, check if docs are up to date, after code changes, before committing.

Review code changes using CodeRabbit CLI - supports uncommitted files (task mode) or all PR files vs main branch (pr mode). Catches bugs, security issues, and code quality problems before committing or when reviewing pull requests. Use when: (1) Reviewing uncommitted changes before committing (task mode), (2) Reviewing all changed files in a PR against main branch (pr mode), (3) Working on subtasks and want to check progress, (4) Need feedback on work-in-progress code, (5) Preparing PR for merge, (6) When CodeRabbit review is needed, (7) For bug detection and security scanning, or (8) For automated code quality assessment. Triggers: review code, check code quality, review changes, code review, review PR, check for bugs, security scan, review uncommitted, finalize code, pre-commit review.

Extract and analyze metadata from NetCDF files. Use this skill when working with NetCDF (.nc) or CDL (.cdl) files to extract variable information, dimensions, attributes, and data types to CSV format for documentation and analysis.

Fetch and analyze Azure Container Apps logs, check container status, and troubleshoot production issues. Use when viewing API/frontend logs, checking deployment health, investigating errors, or restarting containers.

Debug GitHub Actions workflow failures and Terraform errors. Use when deployment failed, Terraform state lock, CI/CD pipeline errors, or troubleshooting deploy.yml.

Creates and evaluates Agent Skills following the official specification. Use when the user wants to create a new skill, scaffold a skill directory, evaluate or validate an existing skill, or needs guidance on skill structure and format.

Creates and evaluates Agent Skills following the official specification. Use when the user wants to create a new skill, scaffold a skill directory, evaluate or validate an existing skill, or needs guidance on skill structure and format.

Creates and evaluates Agent Skills following the official specification. Use when the user wants to create a new skill, scaffold a skill directory, evaluate or validate an existing skill, or needs guidance on skill structure and format.

Generates smart App Store review prompt infrastructure with configurable conditions and platform detection. Use when user wants to add review prompts, request ratings, or implement StoreKit reviews.

易經陽宅風水分析。基於倪海廈易經陽宅學的風水分析技能，強調「名位相等」與「長幼有序」。觸發詞：風水、陽宅、住宅分析、方位、辦公室風水、老闆位置

Backend development using Fastify + TypeScript. Use when creating new backend APIs, adding routes, implementing services, working with plugins, or configuring environment variables.

Evaluate codebase readiness for AI coding agents using automated assessment. Use when onboarding repos, diagnosing agent struggles, or planning infrastructure improvements.

Verify deployment health for production or staging. Use when checking if a deployment succeeded, running smoke tests against live environments, or confirming a feature works before continuing development. Works with Cloudflare Workers, GitHub Actions, and generic HTTP endpoints.

Build and run evaluations for session title generation quality. Use after modifying prompts, when curating test cases, or for periodic quality audits.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Generate images using AI APIs (OpenAI gpt-image-1, Google Imagen 4, Nano Banana Pro, fal.ai Flux). Use when user asks to generate, create, or make an image.

Security scanner for Skills. Use before importing new Skills or for batch auditing existing Skills.

Use when SSHing to servers, running remote commands, checking logs, or needing to discover available SSH hosts.

Debug jsgui3 client-side activation issues. Use when SSR renders but clicks don’t work, this.dom.el is null, or you see Missing context.map_Controls / activation failures.

Fast, repeatable UI verification using Puppeteer without paying browser startup per test. Use scenario suites + deterministic fixtures before jumping to full Jest E2E.

Use the VSCode CLI to open files at specific line and column positions when explaining code, debugging, pointing to TODOs, or guiding users to specific locations in files. Automatically invoked when Claude needs to show users exactly where in a file to look.

ANYTHING related to SolidWorks. Writes, modifies, and debugs C# code that interacts with SolidWorks. Use when working with .cs or .csproj files that (will) reference SolidWorks SDK, SolidWorks.Interop assemblies, COM interop with SolidWorks.

Writes, modifies, and debugs KCL (KittyCAD Language) code for parametric 3D CAD modeling. Use when working with .kcl files, code-first CAD, parametric geometry, or when the user mentions KCL, KittyCAD, or zoo CLI tools.

Document CI/CD, deployment, and operational procedures. Use when creating runbooks, documenting deployment processes, or writing operational guides.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Master Redis Lists and Sets - queues, stacks, unique collections, set operations, and real-world implementation patterns

Master Redis modules - RedisJSON, RediSearch, RedisTimeSeries, RedisBloom, and extending Redis functionality

Master Redis performance - memory optimization, slow log analysis, benchmarking, monitoring, and tuning strategies

Write or update documentation (tutorial, how-to, reference, explanation) with clear style, structure, visuals, API/ADR/runbook patterns. Use when: (1) Creating or updating docs after code changes, (2) During PR preparation or addressing review feedback, (3) Adding new features that need documentation, (4) Updating API endpoints, database schemas, or configuration, (5) Creating ADRs or runbooks, (6) Adding or updating diagrams and visual documentation, (7) When documentation needs to be written or revised, (8) For tutorial creation, how-to guides, or technical writing, or (9) For documentation standards compliance and structure. Triggers: write docs, update documentation, create documentation, write tutorial, document API, write ADR, create runbook, add documentation, document this, write how-to.

Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.

Run user-defined macOS Shortcuts for custom automation workflows. Use when user wants to trigger a Shortcut by name or execute a custom automation.

Verify and test Angular 18 frontend changes using Chrome DevTools MCP. Automatically check console errors, network requests, and visual rendering after implementing tasks or when fixing UI bugs. Use when creating components, debugging visual issues, validating API integration, or ensuring UI requirements are met. File types: .ts, .html, .css, .scss

Error Handling skill for the ikigai project

Convert Markdown files to beautifully styled PDFs with full Chinese font support. Use when: (1) Converting .md files to PDF format, (2) Creating printable documents from Markdown, (3) Generating book chapters or story PDFs, (4) Needing PDF output with custom styling (colors, fonts, backgrounds), (5) Working with Chinese text that needs proper rendering in PDF.

将 Java 项目转换为标准 Maven 结构，自动重组目录、转换包名（test→example）并生成 pom.xml。当用户需要将非 Maven Java 项目转换为 Maven 项目、重构现有项目为 Maven 标准结构，或请求 Maven 项目设置/转换时使用此技能。

Design and review CLI commands following clig.dev and 12-Factor CLI principles. Use when adding commands, designing flags/arguments, writing help text, handling errors, formatting output, or reviewing CLI code for UX issues.

Generate AI images with various themes, styles, and aspect ratios. Use when asked to generate images, create artwork, make graphics, generate backgrounds, or create visual assets.

画面遷移図(画面フロー図 / Screen flow / UI flow / Wireflow)を、要件・ユーザーストーリー・既存ルート・Figma構成・文章仕様から再現可能に作成/更新する。出力はMermaidのflowchartを基本とし、画面カタログ(画面ID/名称/状態/権限)と遷移カタログ(トリガー/条件/結果/例外)も併記する。例外系(失敗・戻り・未ログイン・権限不足・空状態)を必ず含め、スパゲッティ化する場合はユースケース単位で図を分割(L0/L1/L2)する。トリガー語: 画面遷移図, 画面フロー, UIフロー, screen flow, wireflow, 遷移図, フロー図, 画面一覧, 画面設計, 導線

AI 비서 스킬. Gmail, Google Calendar, GitHub를 통합 분석하여 할일을 자동 추출하고 일일 업무 현황을 제공합니다. "오늘 할 일", "이메일 분석", "GitHub 현황" 요청 시 사용합니다.

API 接口测试工作流，使用 HTTPie 作为核心工具。当用户需要测试 API 接口、执行接口调用、生成测试报告、管理接口依赖关系、或在项目中建立标准化的接口测试流程时使用此 skill。适用于 RESTful API 测试、接口联调、回归测试等场景。

Webページに画像が必要な場合にUnsplashから検索して挿入する。例：「ヒーロー画像が必要」「旅行ブログに風景写真を追加して」「コーヒーショップの画像を探して」

MUST USE when searching for official Claude Code or Anthropic platform documentation links (MCP, hooks, skills, CLI). Provides fast fuzzy-search CLI for authoritative Claude documentation.

Transforms repositories into structured plain-text digests optimized for LLM consumption. Use when analyzing GitHub repositories, digesting codebases, or ingesting git repos for AI analysis.

Manages Python environments, dependencies, and tools using uv and ruff. PROACTIVELY Use when setting up Python projects, adding dependencies, managing virtual environments, or enforcing code quality standards. MUST Use `uv` for all operations.

Validates Claude skill files for correct structure, YAML frontmatter, Python imports, naming conventions, and compliance with official documentation

Automate version bumping and release preparation for the stele CLI project. Use this skill when the user requests to create a new release, bump the version, or prepare release tags for stele. The skill analyzes conventional commits to suggest appropriate semantic version bumps and guides through the complete release workflow.

Extract clean article content from URLs and save as markdown. Triggers when user provides a webpage URL and wants to download it, extract content, get a clean version without ads, capture an article for offline reading, save an article, grab content from a page, archive a webpage, clip an article, or read something later. Handles blog posts, news articles, tutorials, documentation pages, and similar web content. Supports Wayback Machine for dead links or paywalled content. This skill handles the entire workflow - do NOT use web_fetch or other tools first, just call the extraction script directly with the URL.

Manage and troubleshoot Coolify deployments using the official CLI and API. Use this skill when the user needs help with Coolify server management, WordPress troubleshooting on Coolify, debugging service issues, checking SSL certificates, accessing containers, or managing applications and databases through Coolify. Particularly useful for diagnosing down services, fixing .htaccess issues, REST API problems, and performing deployment operations.

Connect to the Pieces MCP server (SSE) and reliably query or write to Pieces Long‑Term Memory (LTM) using query/write tool patterns (e.g., ask_pieces_ltm + create_pieces_memory), with practical troubleshooting and request-shaping examples.

Given outputs from 5 research sub-agents (time-sliced or partitioned), validate and synthesize them into a coherent, citation-backed Markdown deep research report with deduplication, contradiction handling, and explicit debug visibility when inputs are missing or malformed.

Playwright end-to-end testing for ScreenGraph using .env-driven configuration. Use when validating full user flows, running regression suites, or inspecting UI behavior with Cursor browser tools.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.