AI Skills Hub - Browse 180,000+ Agent Skills

Use when starting any task in a project - keeps CLAUDE.md instruction file current with high-level project state, prompts for init if missing, adds reflection todo before work to ensure documentation stays updated

Use when creating or refining Claude Code skills to validate that skill descriptions trigger correctly - provides systematic testing methodology for skill activation patterns using test cases and automated evaluation

嚴格測試協議。強制執行「如果沒測試，就不算完成」原則。

Generate images using Google Gemini NanoBanana via browser automation. Use this skill for general-purpose AI image generation from text prompts. Includes persistent authentication, automatic environment setup, and reference image support for style matching.

Queries Nx workspace metadata, project configurations, affected detection, generator schemas, and dependency graphs via unified Python CLI. Use when analyzing monorepo structure, inspecting project.json configurations, determining affected projects for CI optimization, discovering available generators, or visualizing workspace dependencies.

Queries Context7 library documentation via Python CLI. Use when resolving library IDs, fetching API references, code examples, or conceptual guides.

Executes SonarCloud API queries via unified Python CLI. Use when checking quality gate status, searching issues (bugs, vulnerabilities, code smells), retrieving metrics (coverage, complexity), or viewing analysis history.

Compares Figma screenshots with HTML screenshots using pixel-level analysis. Use when verifying visual accuracy of Figma-to-HTML conversion.

Refines screen spec.md by incorporating details from specification documents. Use when enhancing existing screen specifications with business logic, component details, and validation results.

Downloads images, icons, and SVGs from Figma designs. Use when extracting visual assets from Figma for implementation.

Production-grade file operations - permissions, find, archives, rsync

Production-grade Bash fundamentals - syntax, variables, control flow, functions

Production-grade process management - jobs, signals, cron, systemd

Production-grade shell tools - jq, xargs, parallel, pipelines

Production-grade shell automation - scripts, CI/CD, makefiles

TanStack Start server/client code boundary patterns. Use when: debugging virtual module resolution errors (tanstack-start-injected-head-scripts, tanstack-start-manifest, #tanstack-router-entry), importing from @tanstack/react-start/server, using getCookie/getRequestHeaders/getRequestUrl, adding providers to router.tsx, or when Vite fails to resolve TanStack Start imports. Covers createServerFn patterns, dynamic imports, and proper placement of server-only code.

End-to-end testing with Playwright. Use when writing E2E tests, implementing page objects, setting up test fixtures, handling authentication in tests, adding visual regression testing, or configuring E2E tests for CI. Covers when to use E2E vs integration tests, critical path identification, page object pattern, test isolation, and CI considerations.

Document toolkit (.docx). Create/edit documents, tracked changes, comments, formatting preservation, text extraction, for professional document processing.

Perform automated static code analysis on modified files. Triggers automatically after code changes to catch common issues before QA Lead review. Checks for: code complexity, dead code, type errors, import issues, and style violations.

Run Ark from cloned source using devspace

Expert for creating and managing Claude Code Agent Skills. Create skills with git submodule + sparse-checkout for source references, write SKILL.md with proper frontmatter, and follow best practices. Use when creating new skills, adding source references to skills, or managing skill configurations.

Extracts and analyzes HEC-HMS simulation results from DSS files using HmsDss and HmsResults classes. Handles peak flows, hydrographs, volume summaries, and time series data. Leverages ras-commander's RasDss for DSS V6/V7 support. Use when processing HMS results, extracting peak flows, analyzing hydrographs, computing volumes, or exporting time series. Integrates with HEC-RAS for boundary condition workflows. Trigger keywords: DSS file, results, peak flow, hydrograph, time series, volume, extract results, HMS output, analyze results.

Manages HEC-HMS version differences (3.x vs 4.x), handles Python 2/3 compatibility, detects HMS installations, and generates version-appropriate Jython scripts. Use when working with legacy HMS 3.x projects, upgrading models from 3.x to 4.x, testing across multiple HMS versions, or troubleshooting version-specific issues. Handles 32-bit vs 64-bit architecture differences, memory limits, and script syntax variations. Trigger keywords: HMS version, HMS 3.x, HMS 4.x, legacy, upgrade, Python 2 compatible, 32-bit, 64-bit, version detection, multi-version testing.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when feature branch is complete and reviewed, ready to merge to main - squashes multiple commits into single clean commit in main using git merge --squash

Lightweight playbook distilled from AI Architecture to keep dual-engine memory (.ai_context) and manifest dispatcher with minimal overhead; use when bootstrapping or porting the pattern into Claude Skills format.

Stop the Android app running on connected device. Cleanly terminates the app using force-stop. Use when stopping the app for debugging, testing, or cleanup.

Create and maintain architecture documentation using standard formats

Generates comprehensive README.md files for software projects by analyzing codebase structure

Use when user asks about version controlling ~/.claude directory or syncing Claude Code settings across machines. Provides git setup instructions and .gitignore patterns to track only portable settings while excluding logs, session data, and machine-specific plugin metadata. Invoke before initializing git in ~/.claude to prevent committing non-portable data.

This skill automates the capture of high-quality screenshots for MicroSim visualizations using Chrome headless mode. Use this skill when working with MicroSims that need preview images for social media sharing, documentation, or quality assessment. The skill handles JavaScript-heavy visualizations that require proper rendering time and external CDN resources.

Guide for creating CLAUDE.md files. Use when: user asks to create CLAUDE.md, document project, add project instructions, or mentions CLAUDE.md.

Deletes all completed tasks (Done=true) from Notion Todos [DB]. Use when user wants to clean up finished todos, archive completed tasks, or purge done items from the todo database.

Intelligently migrate skills from local to marketplace with dependency analysis, path verification, and venv detection. Use when: migrate skill, publish skill, move to marketplace.

Guide for creating Claude Code hooks - shell commands that execute at specific lifecycle events (SessionStart, SessionEnd, PreToolUse, PostToolUse, etc.). Use when users want to automate actions, add validation, logging, or integrate external tools into Claude Code workflows.

Review and score FastMCP MCP server quality. Use when creating/auditing MCP servers, before publishing to MCP directory, or to improve existing servers.

Display information about the current project or a specified path

Best practices for Windows Batch scripts (.bat). Covers encoding, path handling, variables, error management, and common pitfalls.

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

GitHub Gist API を使用したコードを書く際に使用。Gist作成、GistHack URL変換、ky/zod を使った実装パターンを提供。

Generate app icon using IconKitchen and place in correct locations

Create or refactor a .NET 8 WPF shell for a desktop widget host using CommunityToolkit.Mvvm and a custom viewmodel-first navigation service. Use when working on App.xaml, MainWindow/ShellWindow, shared ResourceDictionaries, runtime Light/Dark theming, or shell layout for widget-style apps. Avoid Prism, Frame navigation, and heavy region managers.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when implementing any feature or bugfix, before writing implementation code

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when executing implementation plans with independent tasks in the current session

Run visual tests, compare golden files, and report bugs for Stapledons Voyage. Use when user asks to run tests, check golden files, or report visual regressions.

Django development standards for the Tellurium Games World of Darkness application. Use when: creating/editing models (characters, items, locations), implementing CRUD views, building forms, creating templates, configuring URLs, working with permissions, caching, migrations, testing, validation, deployment, or management commands. Triggers on: model inheritance patterns, polymorphic models, view mixins, gameline-specific code (vampire/werewolf/mage/wraith/changeling/demon/mummy/hunter), tg-card components, XP/freebie transactions, ST permissions, character templates, frontend styling.

Master feature stores - Feast, data validation, versioning, online/offline serving

Quality gate using LLM Council multi-model consensus for CI/CD pipelines. Use for automated approval workflows and pipeline quality checks. Keywords: gate, CI, CD, pipeline, automated approval, quality gate, GitHub Actions

Git submodules, VCS path repositories, and custom package development for pcrcard/* namespace packages

Idempotent seeder patterns with core/reference/dev separation and environment-specific execution using firstOrCreate/updateOrCreate

Use this skill when categorizing code review findings into severity levels. Apply when determining which emoji and label to use for PR comments, deciding if an issue should be flagged at all, or classifying findings as CRITICAL, IMPORTANT, DEBT, SUGGESTED, or QUESTION.

Extracts structured data from cybersecurity fatigue research papers and calculates statistical correlations

Executes tests, analyzes test results, checks test coverage, and provides comprehensive testing status overview. Primarily for Go projects. Activates after implementing/modifying code to verify correctness, or when explicitly requested to assess test suite health.

Debug and analyze web applications using Chrome DevTools MCP. Use for console log inspection, network request monitoring, performance analysis, and debugging authenticated sessions. For basic browser automation (screenshots, form filling), use browser-discovery skill instead.

Knowledge of documentation platforms and fetching strategies. Use when adding new documentation sources, determining fetch strategy for a docs site, detecting doc frameworks, or configuring the docs registry.

Browser automation for documentation discovery. Use when curl fails on JS-rendered sites, when detecting available browser tools, or when configuring browser-based documentation collection.

从 macOS 应用程序中提取 icon 图标并转换为 PNG 格式。当用户需要获取 APP 图标、提取应用 icon、将 icns 转 png 时使用。

管理本地 Cloud NMS 服务器的完整部署流程，包括卸载、上传、全新安装和保留数据升级。当用户需要重新安装 Cloud NMS、部署新版本、或在开发环境中重置 NMS 服务时使用。

批量管理本地服务器集群的生命周期。支持**并发查询**服务器状态、启动指定虚拟机(virsh start)以及安全关闭服务器(自动处理VM下电)。

Run comprehensive system diagnostics including dependency checks, test suite execution, git status, and pipeline health verification. Use when troubleshooting issues, verifying system readiness, or preparing for a release.

Search over a million GitHub repositories for real-world code examples using grep.app. Find literal code patterns, usage examples, and implementation patterns across popular open-source projects. Perfect for discovering how developers use specific APIs, libraries, or coding patterns.

Website-level technical SEO audit with engineering backlog. Covers robots.txt, sitemap, canonical, redirects, meta/OG/Twitter, JSON-LD, internal linking, Core Web Vitals, mobile. Use for site-wide SEO improvements or technical SEO implementation.

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

生成专业金融图表（K线图、技术指标图）。适用于数据可视化、技术分析展示、报告生成等场景。支持多种图表类型（basic、comprehensive）和自定义样式（深色、浅色主题）。

Deployment and infrastructure for the site. Consult when troubleshooting deployments, modifying CI/CD, or diagnosing build issues.

Create structured GitHub Issue knowledge entries with one-shot input. Handles auto-formatting, AI labeling, title extraction, and publishing. Use when user wants to share tips, document solutions, create how-tos, or add any knowledge to the base.

Guide for creating Claude Code hooks - user-defined shell commands that execute at lifecycle points. Use when the user wants to create, add, or configure a hook for Claude Code, including PreToolUse, PostToolUse, Notification, UserPromptSubmit, Stop, SubagentStop, PreCompact, SessionStart, or SessionEnd hooks.

Guide for creating Claude Code subagents (custom agents) - specialized AI assistants with isolated context. Use when the user wants to create, add, or configure a subagent/custom agent for Claude Code.

UX expert for WTP, an iOS espresso shot dialing app. Use when working on WTP user experience including critiquing flows/screens, generating UX concepts, writing user stories, conducting accessibility audits, designing gamification/motivation systems, or any design decisions. Triggers on terms like UX, user experience, flow, screen, accessibility, user story, design critique, usability, HIG, gamification, achievements, streaks, or motivation for WTP contexts.

Claude Developer Platform Skills feature. Custom knowledge packages for agents, curated playbooks, and versioned expertise domains.

Analyze test failures from CTRF reports using jq for deterministic parsing

ASGI server for Python web applications - Fast, production-ready server for async frameworks

Coding conventions and patterns for the mymind codebase. Use this skill when writing or modifying any code in this project to ensure consistency with established patterns.

Manage and standardize frontmatter metadata across Obsidian vault. Use when files are missing metadata, have inconsistent frontmatter, or need standardized date/tag/type fields. Works with both Korean and English content.

Normalize and standardize tags across Obsidian vault. Use when working with documentation that has inconsistent tags, duplicate tags, or needs hierarchical tag organization. Handles both English and Korean content.

Test WordPress form submissions and email delivery. Validates contact forms, checks WP Mail SMTP configuration, and sends test emails. Use when verifying form functionality or troubleshooting email delivery issues.

Build selected K1.node2 pattern(s), upload firmware to the ESP32-S3 over LAN, verify the web API/UI, capture artifacts, and draft release notes.

Lightweight Linear skill for fetching issue details. Returns only essential data (title, description, state, assignee) to optimize context usage compared to full Linear MCP.

Guide for creating and running tests in the Markco VS Code extension

Fetch and post Gerrit review comments (as JSON) for a given change URL, change number, or Change-Id. Use when you need real review feedback for code fixes or want to post automated review comments.

Create multi-step workflow skills with progressive step loading, state management, and interactive decisions. Use when building complex skills like APEX that need structured phases.

Automated CI/CD pipeline fixer - watches CI, fixes errors locally, commits, and loops until green. Use when CI is failing and you want to automatically fix and verify changes.

Setup the Ralph autonomous AI coding loop - ships features while you sleep

Create technical design documents (TDD) or system design documents. Use when user asks to design a feature, write a TDD, create a technical spec, or plan system architecture.

Manage fixed assets including capitalization, depreciation, and disposal. Use when user wants to (1) process asset transactions from source files, (2) run the interactive workflow with guided questions, (3) execute scripts directly, or (4) understand depreciation calculations and account mappings.

Use this agent when [specific conditions]. Examples:

Write and refine scientific papers in LaTeX (English). Use this when asked to draft, rewrite, or improve paper sections (IMRAD), strengthen academic tone, add citations/refs correctly, or build an outline.

Workflow for editing the root-level paper.tex and references.bib (English papers). Use when working with paper.tex at repo root, checking citations, or extracting content from PDFs in papers/.

Focused workflow for TUI E2E testing with Termwright. Use for fast agent guidance when running step files, capturing artifacts, and debugging with trace output.

Apply variation theory of learning to structure instructional content using contrast, generalization, and fusion patterns. Variation must target the critical aspects of the learning objective. Use when writing educational materials, explanations, tutorials, literate programming documentation (.nw files), structuring lecture slides, designing exercises, or when user mentions variation theory, learning theory, pedagogy, or critical aspects of learning. Works alongside the literate-programming skill for .nw files.

Query fleet telematics data using the Terminal CLI - vehicles, drivers, safety events, HOS, trips, locations, and more

Reviews existing CLAUDE.md files against expected sections and suggests additions for gaps. Part of the review-* skill family for project quality checks.

Dynamic access to playwright MCP server (22 tools)

Use for Pydantic Logfire observability, tracing, and debugging. Query exceptions, spans, logs with SQL. View traces in Logfire UI. 4 tools for application monitoring and error analysis.

Fetch GitHub feedback after git push OR PR creation. These are TWO SEPARATE use cases with different feedback sources. Use the Python script with appropriate flags.

WHAT: Error boundaries with fallback UI and OpenTelemetry span recording. WHEN: isolating component errors, handling GraphQL failures, implementing retry logic. KEYWORDS: ErrorBoundary, error handling, fallback UI, OpenTelemetry, recordException, retry, GraphQL, errorPolicy, scope.