AI Skills Hub - Browse 180,000+ Agent Skills

Creates Azure Service Principal with Entra ID App Registration configured for workload identity federation. Grants RBAC permissions across multiple environments. Use when setting up CI/CD authentication for Azure DevOps pipelines or automated deployments requiring federated credentials.

Guide for Lightdash's CASL-based authorization system. Use when working with scopes, custom roles, abilities, permissions, ForbiddenError, authorization, or access control. Helps with adding new scopes, debugging permission issues, understanding the permission flow, and creating custom roles.

Use after any change to skeleton/, packages/core/, or docs/. Use to verify types compile and documentation is synchronized.

Manage Portainer deployments - create stacks from Git repos, check deployment status, redeploy, view logs. Use when user asks about deploying to Portainer, checking stack status, or managing Docker deployments.

> Design and implement RESTful APIs following clean architecture patterns and conventions.

Use when the user wants to create or refine Codex skills, improve skill descriptions, organize skill resources, or follow Codex skill best practices.

HARD GATE before PR creation - verifies review artifact exists in issue comments, all findings addressed or tracked, blocks PR creation if requirements not met

Use before starting ANY work - hard gate ensuring a GitHub issue exists, creating one if needed through user questioning

MANDATORY for all work - the project board is THE source of truth. This skill provides verification functions and gates that other skills MUST call. No work proceeds without project board compliance.

Queries Datadog for debugging and investigation. Search logs, query metrics, check monitors, list hosts, view events, and search APM traces. Use when the user asks about Datadog data, wants to debug issues, check alerts, or investigate infrastructure.

This skill should be used when the user asks to "deploy", "upload", "publish", or "pin" any files, folders, frontend projects, or static websites to IPFS. Also activates when user mentions "pinme", "IPFS", or wants to share files via decentralized storage.

Calypso reference skill for WordPress imports and E2E testing. Use when working on: (1) Looking up @wordpress package exports, (2) Writing E2E tests with Playwright, (3) Migrating legacy tests, (4) Understanding test fixtures, (5) Debugging test failures, (6) Feature flags usage, or (7) SCSS styling with WordPress tokens.

Build consistent WordPress admin interfaces using official @wordpress/components and design tokens. Use when creating UI screens, dashboards, settings pages, or any interface that should feel native to WordPress admin. Covers component selection, proper token usage for colors/spacing/typography, and composition patterns to avoid visual inconsistency.

Working with model instances and fields, use when you need to access fields on a model

controller and API setup and basic patterns. Use when you need controller permissions, controller post data, controller params and queries, or setup a new controller or API route

Use when investigating bugs, failures, leaks, crashes, or unexpected behavior. Activate when user describes something not working as expected, provides error messages or stack traces, mentions nightly test failures, or asks "why is this happening?" This skill shifts Claude into debugging mode with systematic investigation techniques.

Use when reviewing tutorial screenshots, using ImageComparer, analyzing screenshot diffs, or updating screenshots for releases. Activate for s-XX.png references in tutorial context.

Run database seeders to populate test/development data

구글드라이브 연동(업로드+다운로드): 워크스페이스와 구글 드라이브 간 양방향 파일 관리

노션 연동(업로드+다운로드): 워크스페이스와 Notion 간 양방향 파일 관리

First step for any task. Uses HelixDB to map code relationships, then loads precise context into Repo Prompt. Trigger when starting work, feeling lost, or context seems stale.

Systematic debugging by tracing data backwards from symptom to root cause. Uses HelixDB for relationships, Repo Prompt for inspection. Trigger when investigating bugs or unexpected behavior.

For changes spanning multiple files, ensures correct order and atomicity. Prevents partial migrations and broken intermediate states. Trigger when changing 3+ files or any shared contract.

Create and configure Obsidian Bases (database-like views for notes). Use when creating .base files, embedding bases in markdown, writing base formulas or filters, configuring table/list/cards/map views, or querying vault content by properties like tags, dates, topics, or status.

Toolkit for testing and automating web applications. Prioritizes Claude Code Chrome integration for real browser testing. Falls back to Playwright scripts for CI/CD or headless scenarios.

Performs root cause analysis for Jenkins pipeline failures using MCP tools with evidence-backed citations, guided workflow, and concrete remediation steps.

Write AST-based code search and rewrite rules using ast-grep YAML. Create linting rules, code modernizations, and API migrations with auto-fix. Use when the user mentions ast-grep, tree-sitter patterns, code search rules, lint rules with YAML, AST matching, or code refactoring patterns.

Manage dotfiles with chezmoi for cross-machine configuration management. Use when setting up dotfiles, syncing configs across machines, managing secrets, using templates, or troubleshooting chezmoi. Triggers include "chezmoi", "dotfiles", "sync configs", "manage configurations", "dotfiles repo", "home directory management".

Reference guide for AI CLI tool config locations (Claude, Codex, Gemini, Cursor). Use when you need to FIND where configs live, understand config structure, or create new skills. For MCP operations use `/mcp-admin`. For backup workflows use `/config-backup`. Triggers include "where is config", "config location", "claude path", "codex path", "find settings", "skill structure", "create skill".

AST-based code search and refactoring tool. Use when migrating code patterns, bulk refactoring, renaming across codebase, removing debug statements, or any structural code transformation. Triggers include "ast-grep", "code migration", "bulk refactor", "rename pattern", "structural search", "AST search".

Semantic code analysis tool. Use when searching for code by behavior ("find auth logic"), analyzing call graphs, finding callers of a function, or getting LLM-optimized context. Triggers include "semantic search", "who calls this", "what affects line", "call graph", "impact analysis", "tldr".

Execute step-by-step system performance tuning tasks using starttune.py functions. Use this skill when Claude needs to collect metrics, analyze bottlenecks, optimize parameters, and optionally generate strategy recommendations on target servers.

This skill should be used when starting or cleaning up isolated feature work using git worktree, with smart directory selection, safety checks, and teardown after merge.

Predict which support tickets will breach SLA based on ticket metadata (priority, age, status, last update, group workload). Outputs breach risk (LOW/MEDIUM/HIGH) with explainable reasons and recommended actions. Use when users need to: (1) Analyze tickets for SLA breach risk, (2) Prioritize which tickets need immediate attention, (3) Monitor SLA compliance, (4) Generate SLA breach reports, or (5) Automate SLA monitoring workflows. Accepts CSV or JSON ticket data.

Generate production-ready AWS CLI commands from natural language operations requests. Use when users describe AWS infrastructure needs in plain English (e.g., "create an EC2 instance", "set up an S3 bucket", "deploy a Lambda function"). Outputs complete commands with best-practice flags, proper tagging, IAM permissions, dry-run options, and cleanup commands. Supports EC2, S3, Lambda, RDS, and other core AWS services.

Creer et executer une migration de base de donnees Laravel. Utiliser automatiquement quand on demande de modifier le schema, ajouter une colonne, creer une table.

NATS and JetStream best practices. Auto-invoked when working with NATS, JetStream, messaging, or queue-related code.

Generate high-quality training data using powerful LLMs (Teacher Models) to train smaller models (Student Models). This is data-centric knowledge distillation - the teacher generates labeled data, not logits. Use this skill when the user needs to: (1) Generate NER/entity annotation data using LLM, (2) Create embedding training pairs (query-positive-negative) with LLM, (3) Generate text classification datasets, (4) Create instruction-tuning data for fine-tuning, (5) Synthesize domain-specific training corpora, (6) Augment existing datasets with LLM, (7) Quality control and filtering of generated data. Supports OpenAI GPT-4, Claude, and local LLMs as teacher models.

Train and fine-tune NLP models using Hugging Face Transformers for Chinese/Traditional Chinese tasks. Use this skill when the user needs to: (1) Train or fine-tune NER (Named Entity Recognition) models, (2) Train or fine-tune embedding models for semantic search/similarity, (3) Train word segmentation models, (4) Fine-tune BERT/RoBERTa for text classification, (5) Prepare datasets in proper format for NLP training, (6) Evaluate NLP model performance, or (7) Export models to ONNX/production formats. Supports Traditional Chinese with CKIP Lab models and multilingual embeddings with BGE models.

Implement Skills system on LangChain with progressive disclosure pattern. Use when building agent skills, implementing middleware for skill injection, or designing YAML-based skill discovery systems.

SQL queries for MySQL/PostgreSQL. Default MySQL, use --postgres for PostgreSQL.

在对话中检索、追加或更新个人/项目记忆库

Development workflow for code changes. Load when: implementing features, fixing bugs, writing tests, refactoring, creating PRs, reviewing code. Covers exploration → design → implementation → commit → PR cycle. Keywords: feature, bug, fix, test, refactor, PR, pull request, commit, code review, implement, develop, build.

Magic-API脚本开发助手。当用户需要编写magic-api接口脚本、数据库操作、HTTP请求、或询问magic-script语法时触发。

Onboard new users to Personal OS. Collects context through interview, lets user choose a creature companion, and populates context files.

Migrate vault files to current schema versions. Use when files have outdated frontmatter, missing schema_version, or need bulk updates to match current schema definitions. Detects, previews, and applies migrations with validation.

Quickly spin up Claude Code hooks for automation. Generates bash scripts, Python handlers, and settings.json configuration for PreToolUse, PostToolUse, SessionStart, Stop, and other hook events.

Generate immersive RPG scene illustrations using the image generation API. Use this skill when narrating key RPG moments that benefit from visual illustration, such as entering new locations, encountering bosses or important NPCs, dramatic combat scenes, discovering legendary items, or witnessing major story events. Triggers on RPG narration, scene transitions, boss encounters, and dramatic story moments.

Generate .NET Core data API code from model definitions using the Maker XML specification and CLI. Use when users need to: (1) Create Maker XML models from JSON objects, SQL scripts, or database schemas, (2) Generate .NET Core CRUD API endpoints from Maker XML, (3) Understand or validate Maker XML model definitions, or (4) Work with the Maker CLI tool for code generation.

Patterns for sustained multi-session task execution with checkpointing and state recovery. Use when working on complex features spanning multiple context windows, long implementations, or tasks requiring progress persistence.

Count tokens in text using tiktoken or Qwen3 tokenizer. Use when user asks for precise token calculations, e.g. "How many tokens are in {file}?", "Count the amount of tokens in the description column of this database entry", "For every line in {file}, tell me how many tokens there are", etc.

This skill guides the development of `ffmpeg-mcp-lite`, an MCP server that provides video and audio processing capabilities through FFmpeg.

Generate mobile app icons using OpenAI or Gemini image generation. Use when creating iOS icons, Android icons, app icons, or generating icon assets.

Guides SOC2/HIPAA compliance annotation usage, evidence generation patterns, and audit trail implementation

Helps with Morphir Go development including workspace setup, go.work management, branch/worktree handling, TDD/BDD workflow, and pre-commit checks. Use when setting up development environment or working on Morphir code.

Drupal cache contexts implementation guide. Use when asked about request-based cache variations, user.roles vs user context, URL contexts, language contexts, custom cache contexts, or cache context hierarchy. Helps prevent cache explosion from overly broad contexts.

Drupal cache tags implementation guide. Use when asked about cache tag naming conventions, entity tags, list tags, custom tags, tag invalidation strategies, or debugging tag-based cache invalidation issues. Covers node:ID, config:name, entity_list patterns.

MX Space API design conventions. Apply when writing controllers, API endpoints, or handling HTTP requests.

Run tests. Supports running all tests, single file, or pattern-matched tests.

集成飞书/Feishu 服务，操作多维表格、文档、消息、群组等。当用户提到飞书、Feishu、Lark 或需要操作飞书相关功能时使用。

四阶段调试法与根因分析；在调查缺陷、修复测试失败或排查异常行为时使用。强调“未找到根因前不得修复”。

GraphQL 查询、Mutation 与代码生成模式；在创建 GraphQL 操作、使用 Apollo Client 或生成类型时使用。

Kotlin Coroutines review and remediation for Android. Use when asked to review concurrency usage, fix coroutine-related bugs, improve thread safety, or resolve lifecycle issues in Kotlin/Android code.

Authoritative rules and patterns for production-quality Kotlin Coroutines onto Android. Covers structured concurrency, lifecycle integration, and reactive streams.

Use when implementing features to write effective tests. Encourages test-first but allows prototyping.

manage branches and full pull request lifecycle, from creation to merge

manage the lifecycle of GitHub Issues, including creation, triage, milestones, search, and sub-issue hierarchy

Create and manage repo-local work artifacts for a user “task request” by generating `.artifacts/artifacts/{request_id}/` with `plan.md`, `todo.md`, and `walkthrough.md`, then indexing completed work into ChromaDB stored at `.artifacts/chroma_db/` for 7-day recall. Use when the user wants (1) a tracked/confirm-before-execute workflow, (2) a minimal final answer that links to a walkthrough, or (3) to ask “what did we do before with the artifacts skill?” and you should answer by querying the ChromaDB artifacts index.

Refactor high-complexity React components in Dify frontend. Use when `pnpm analyze-component --json` shows complexity > 50 or lineCount > 300, when the user asks for code splitting, hook extraction, or complexity reduction, or when `pnpm analyze-component` warns to refactor before testing; avoid for simple/well-structured components, third-party wrappers, or when the user explicitly wants testing without refactoring.

プロフィール写真の標準化処理。 背景除去、顔センタリング、明るさ補正を自動で行う。 Dockerで実行するため安全。

This skill should be used when creating, configuring, or working with Claude Code subagents. Use when users ask to create custom subagents, set up subagent configurations, manage tool permissions, or need guidance on subagent architecture and best practices.

Edit and manipulate images using natural language prompts. Use this skill when users request image creation (photos, illustrations, icons, infographics) or editing tasks (removing objects, changing backgrounds, text overlays, cropping). Supports reference images for character consistency and style transfer. Supports Google Search grounding for real-time factual content (weather, sports, scientific data) - no need to search separately when creating infographics or factual visualizations.

Read and analyze Google Docs, Sheets, and Slides by exporting them to local formats (DOCX, XLSX, PPTX) via browser download. Use this skill when users request to read, summarize, or analyze content from Google Drive URLs or .gdoc/.gsheet/.gslides files.

Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.

SQLite disaster recovery and streaming replication to cloud storage (S3, GCS, Azure, SFTP, NATS). Use this skill for configuring Litestream, deploying to cloud platforms, troubleshooting WAL replication issues, implementing point-in-time recovery, and setting up VFS read replicas.

Automatically updates terminal window title to reflect the current high-level task. Use at the start of every Claude Code session when the user provides their first prompt, and whenever the user switches to a distinctly new high-level task. Helps developers manage multiple Claude Code terminals by providing clear, at-a-glance identification of what each terminal is working on.

Generate clean shell scripts following best practices.

Use when seeing WebSocket errors like "Invalid frame header", "RSV1 must be clear", or "WS_ERR_UNEXPECTED_RSV_1" - covers multiple WebSocketServer conflicts, compression issues, and raw frame debugging techniques

Use this skill when you need to manage **Vapi voice agents** (assistants), calls, phone numbers, tools, and webhooks from an OpenClaw agent.

name: RLS Security description: Row Level Security patterns for multi-tenant Supabase applications. trigger: When implementing security policies, database permissions, or multi-tenant access control. scope: backend ---

Install and verify Databricks CLI and databricks-connect for local development. Use when setting up a new environment, troubleshooting installation issues, or checking tool versions.

Resume a book project exactly where you left off.

Write correct, idiomatic Apple MLX code for Apple Silicon ML. Use when working with MLX arrays, neural networks, training loops, lazy evaluation, unified memory, mx.eval, mx.compile, Metal GPU, memory optimization, quantization, or Apple Silicon performance. Covers critical API differences from PyTorch/NumPy, array indexing gotchas (lists must be mx.array, slices create copies), NHWC format for Conv2d, __call__ not forward(), float64 CPU-only, mlx-lm integration, and debugging patterns.

MCP Gateway / children_config / children_abstract / execute_child_tool の基本に答えるときに使う。

Custom scripted battle system for TV replays and non-interactive battle sequences. Use when discussing, debugging, or extending scripted battles, the Norman TV battle, or adding new pre-choreographed battle sequences.

> Source: https://github.com/obra/superpowers/tree/main/skills/systematic-debugging

Create specialized Claude Code sub-agents with custom system prompts and tool configurations. Use when users ask to create a new sub-agent, custom agent, specialized assistant, or want to configure task-specific AI workflows for Claude Code.

> **Version:** 1.0.0 > **Purpose:** Master guide for the Claude Skills ecosystem > **Scope:** User-scope skills applicable to any development project

Architect cognitive data infrastructure for Agentic AI systems using PostgreSQL + pgvector, Mage orchestration, and H2O ML integration.

Create, modify, and manage PostgreSQL database migrations using golang-migrate with idempotent patterns

當需要解答以下題型時自動啟用： - 字形辨識（形近字、錯別字） - 成語應用（成語用字、成語意義） - 國學常識（作家作品、文學史、文學流派） - 文言文閱讀（108課綱15篇古文） - 修辭手法（10種主要修辭格）

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 quality assessment for LLM/AI outputs, creating evaluators, comparing model performance, or setting up automated testing for generated content - provides evaluator patterns, dataset management, and CI/CD integration guidance

This skill should be used when the user mentions "flaky tests", "race condition", "timing issues", "wait for", "test sometimes fails", or when tests have inconsistent pass/fail behavior. Replaces arbitrary timeouts with condition polling.

Use this skill when creating a new project on the Operator platform.

Research topics by verifying actual source content. Use when asked to research or study links and documentation.

Example Mappingの成果物を実行可能なGherkin仕様に変換します。

自动从PDF教材中提取FIGURE图片的完整工作流程。

Veo 3 视频生成服务集成和成本管控。Use when implementing video generation, managing credits, cost control, handling video callbacks, or when user mentions veo, video generation, AI video, cost budget.

Best practices for implementing Leaflet maps in React 18 + TypeScript applications, particularly for desktop embedded webviews. Use when building or refactoring map UI with Leaflet, working with geo data visualization, implementing interactive maps with markers/polylines/layers, or optimizing map performance for large datasets.