AI Skills Hub - Browse 180,000+ Agent Skills

Search local files, Jira issues, Confluence pages, and Figma designs using semantic similarity. Use when user asks to find documents, search code, look up information, query indexed content, or needs context from external sources like Jira tickets or Confluence documentation.

国内ITニュースを収集・要約してPDF生成・Slack投稿する

Clean Architecture API patterns for Hono endpoints following Route → Handler → Service → Factory → Interface pattern with multi-tenant support

Show what's new in Kata since the installed version, displaying changelog entries, checking for Kata updates, or reviewing recent changes. Triggers include "what's new", "whats new", "show changes", "changelog", "recent changes", and "what changed".

Add planned work discovered during execution to the end of the current milestone in the roadmap. This skill appends sequential phases to the current milestone's phase list, automatically calculating the next phase number. Triggers include "add phase", "append phase", "new phase", and "create phase". This skill updates ROADMAP.md and STATE.md accordingly.

Add a milestone to an existing project, starting a new milestone cycle, creating the first milestone after project init, or defining what's next after completing work. Triggers include "add milestone", "new milestone", "start milestone", "create milestone", "first milestone", "next milestone", and "milestone cycle".

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

代码安全扫描工具，用于检测危险操作和安全漏洞。当用户请求以下操作时使用：(1) 扫描安全风险/检查危险操作 (2) 审查敏感信息泄露 (3) 检测安全漏洞 (4) 检查破坏性操作 (5) 审查 Skill/代码仓库。支持 Shell/Python/Node.js/PowerShell/PHP/Ruby/Go/Java/C# 多语言，检测 16 大类安全风险（破坏性操作、远程执行、命令注入、网络外传、权限提升、敏感信息泄露、持久化、敏感文件访问、提示注入、数据外传、越权工具使用、混淆、社会工程、资源滥用、策略违规、能力夸大）。

How to write and organize VS Code Copilot custom instructions (.instructions.md) and agent skills (SKILL.md). Use when creating, editing, reorganizing, or debugging custom instruction or skill files, or when asked about applyTo glob syntax.

LangGraph state-machine design and debugging for `StateGraph`, node/edge routing, checkpoints, `interrupt`, and HITL flows. Use when building or troubleshooting graph-based agents with conditional edges and thread state.

Build and maintain assistant-ui based React chat apps with reliable setup, runtime selection, LangGraph wiring, tool UI integration, and upgrade workflows. Use when tasks explicitly involve `assistant-ui` dependencies or APIs, including `assistant-ui` CLI commands (`create/init/add/update/upgrade/codemod`), `@assistant-ui/*` providers/runtimes, `AssistantRuntimeProvider`, Thread/Composer primitives, cloud persistence, or tool rendering behavior. Do not use for generic React chat work, backend-only LangGraph tasks, or non-assistant-ui UI work. If the prompt explicitly says without/no/not assistant-ui, do not trigger this skill.

CopilotKit integration patterns for providers, runtime wiring, `useCoAgent`, `useCopilotAction`, `useLangGraphInterrupt`, shared state, and HITL with LangGraph. Use when building agent-native product UX.

Practical guide for building safe, syntax-aware srgn CLI commands for source-code search and transformation. Use when users ask for srgn commands, scoped refactors (comments/docstrings/imports/functions), multi-file rewrites with --glob, custom tree-sitter query usage, or CI-style checks with --fail-any/--fail-none.

AG-UI protocol implementation guidance for event ordering (`RUN_STARTED`, `TOOL_CALL_*`, `STATE_SNAPSHOT`/`STATE_DELTA`), streaming semantics, and middleware patterns. Use when integrating agent backends with AG-UI clients.

Effective code search, analysis, and refactoring using ast-grep (sg). Use this skill for precise AST-based code modifications, structural search, and linting.

Meta-skill for creating, editing, and managing Antigravity skills and workflows. Use when asked to create new skills, update existing ones, or sync to GitHub.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees as sibling directories with per-worktree dependencies

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

Creates step-by-step incident response runbooks for common outages with actions, owners, rollback procedures, and communication templates. Use for "incident runbook", "outage response", "incident management", or "on-call procedures".

Validates environment variables in CI, prevents secret leaks, enforces masking, and provides fail-fast validation with clear documentation. Use for "secrets management", "env var validation", "credential security", or "secret masking".

Designs background job processing systems with queue integration (BullMQ/Celery), job definitions, retry policies, exponential backoff, idempotent execution, and monitoring hooks. Use when implementing "background jobs", "task queues", "async processing", or "job workers".

Designs robust function/tool calling schemas for LLMs with JSON schemas, validation strategies, typed interfaces, and example calls. Use when implementing "function calling", "tool use", "LLM tools", or "agent actions".

Secures webhook receivers with signature verification, retry handling, deduplication, idempotency keys, and error responses. Provides verification code, dedupe storage strategy, runbook for incidents. Use when implementing "webhooks", "webhook security", "event receivers", or "third-party integrations".

Use when the user asks to create a new Codex skill (SKILL.md), design trigger conditions in the description, generate a skill skeleton/scaffold, or debug why a skill isn't being selected or discovered.

Use when the user suspects a Codex skill is not triggering, wants to validate SKILL.md frontmatter (name/description), check description quality for discovery, or needs a plugin-dev-like validation step for skill packaging.

Use when the user asks which skill to use, wants to route a request to an existing skill, or wants to create/improve skills.

Use when the user wants to remediate higher-education PDFs into accessible formats (PDF to Markdown to accessible DOCX), including course readings, handouts, and image-heavy files.

Talk to your Garmin data naturally - "what was my fastest speed snowboarding?", "how did I sleep last night?", "what was my heart rate at 3pm?". Access 20+ metrics (sleep stages, Body Battery, HRV, VO2 max, training readiness, body composition, SPO2), download FIT/GPX files for route analysis, query elevation/pace at any point, and generate interactive health dashboards. From casual "show me this week's workouts" to deep "analyze my recovery vs training load".

Guard agent for AI agents — scan emails and webpages for prompt injection, jailbreak, phishing, and malware.

Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features

Parse moey! bank statement PDFs into CSV, categorize transactions, and sync them to InfluxDB and Google Sheets.

Reliable Google Workspace CLI skill (gogcli). Defaults to all-calendars for agenda queries; JSON-first; safe writes.

Manages project knowledge using ByteRover context tree. Provides two operations: query (retrieve knowledge) and curate (store knowledge). Invoke when user requests information lookup, pattern discovery, or knowledge persistence. Developed by ByteRover Inc. (https://byterover.dev/)

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.

ウマ娘のスキルデータベースから条件に合うスキルを検索する。作戦、距離、発動タイミング、効果種別などの条件でフィルタリング可能。

| Field | Value | |-------|-------| | **Name** | creative-analyzer | | **Version** | 1.0.0 | | **Author** | Meta Ads MCP Team | | **Description** | Analyze Meta Ads image and video creatives with performance correlation | | **Triggers** | "analyze creative", "analyze ad", "why is this ad performing", "creative analysis" |

Use when compressing a YAML ADR into Y-Statement format. Use when creating a minimal-context summary of an architectural decision for agent search and retrieval.

SwiftData persistence framework patterns for macOS and iOS apps. Covers @Model definitions, @Query, relationships (with delete rules), ModelContainer/ModelContext configuration, class inheritance with @Model subclasses, type-based predicates (#Predicate with is/as? casting), polymorphic relationships, @Attribute options (.preserveValueOnDeletion), schema migrations, and import/export. Use when implementing data persistence, defining models, querying data, or working with SwiftData. Prevents common LLM errors like generating Core Data syntax, inventing nonexistent SwiftData APIs, or misusing @Query.

macOS app distribution covering code signing (Developer ID, App Store certificates), notarization (notarytool), DMG/pkg creation, App Store submission workflow, sandboxing entitlements, StoreKit for in-app purchases and subscriptions (SubscriptionOfferView, appTransactionID, Transaction.currentEntitlements, subscriptionStatusTask), StoreKit testing with local configuration files, PrivacyInfo.xcprivacy manifest, and dual distribution strategies (App Store + direct). Use when preparing an app for distribution, implementing purchases/subscriptions, configuring signing, or troubleshooting App Store rejection.

Comprehensive guide to Apple's Liquid Glass design system introduced in macOS 26, iOS 26, and across all Apple platforms. Covers SwiftUI (.glassEffect(), GlassEffectContainer, .interactive(), .tint(), glassEffectID morphing, .buttonStyle(.glass), .buttonStyle(.glassProminent), glassEffectUnion), AppKit (NSGlassEffectView, NSGlassEffectContainerView), UIKit (UIGlassEffect, UIGlassContainerEffect, UIScrollEdgeEffect), and WidgetKit (accented rendering mode, widgetAccentable). Use whenever building UI with the new Apple design language, adopting glass effects, styling buttons or toolbars, or creating modern macOS/iOS interfaces. Always consult this skill when asked about new Apple design.

macOS application architecture patterns covering App protocol (@main), Scene types (WindowGroup, Window, Settings, MenuBarExtra), multi-window management, NSApplicationDelegateAdaptor for AppKit lifecycle hooks, Info.plist configuration (LSUIElement for menu bar apps, NSAccessibilityUsageDescription), entitlements for sandbox/hardened runtime, and project structure conventions. Use when scaffolding a new macOS app, configuring scenes and windows, setting up menu bar apps, or resolving macOS-specific lifecycle issues. Corrects the common LLM mistake of generating iOS-only app structures.

MapKit and GeoToolbox framework patterns for location-based features. Covers PlaceDescriptor (standardized place representation across mapping services), PlaceRepresentation (.coordinate, .address), SupportingPlaceRepresentation for third-party service IDs (Google Places, Here, Foursquare), MKMapItem ↔ PlaceDescriptor conversion, Map view with annotations and overlays, geocoding, local search, and place sharing. Use when building location features, implementing maps, working with place data, or integrating with third-party mapping services.

System-wide keyboard shortcut registration on macOS using NSEvent monitoring (simple, app-level) and Carbon EventHotKey API (reliable, system-wide). Covers NSEvent.addGlobalMonitorForEvents and addLocalMonitorForEvents, CGEvent tap for keystroke simulation, Carbon RegisterEventHotKey for system-wide hotkeys, modifier flag handling (.deviceIndependentFlagsMask), common key code mappings, debouncing, Accessibility permission requirements (AXIsProcessTrusted), and SwiftUI .onKeyPress for in-app shortcuts. Use when implementing global keyboard shortcuts, hotkey-triggered panels, or system-wide key event monitoring.

Diagnose and fix third-party library loading failures in Vite, Webpack, or other bundlers. Use when encountering "Failed to fetch dynamically imported module", worker loading failures, CDN 404 errors, "Invalid type" errors when importing library assets, or assets loading in wrong format. Covers version mismatches, worker loading patterns, and bundler-specific solutions.

Localize and maintain multi-language Digital Combat Simulator (DCS) documentation in Markdown (EN/ES/SV/FI), keeping structure consistent, links localized, and terminology stable. Use when asked to translate DCS docs, add new languages, fix language bars/links, or standardize terminology across multiple DCS documents.

Quality-assure Digital Combat Simulator (DCS) Markdown documentation: validate relative links, enforce basic structure (headings like step-by-step/bindings/common mistakes), and produce actionable QA reports. Use when asked to review DCS docs for consistency, fix broken links, standardize headings, or run automated checks across a docs tree.

Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.

Multi-framework frontend development skill for React, Vue, and Next.js applications. This skill should be used when: building UI components (forms, tables, modals), optimizing Core Web Vitals (LCP, INP, CLS), reviewing frontend code quality, implementing design systems, or improving accessibility (a11y).

You are installing the Loa framework onto a repository. This is the first step before the Loa can ride through the codebase.

Use when encountering n8n workflow issues, Code node errors, HTTP requests failing, data flow problems, environment variables not working, JSON parsing errors, or need n8n development patterns and debugging strategies

このスキルはデータベース設計に関するアンチパターンを検出し、改善案を提示します。

Manage indicators and metrics in the Engage Analytics dbt project. Use when working with healthcare analytics indicators, adding new metrics, creating questionnaire response models, or understanding the metrics architecture. Triggers on requests involving indicator creation, metric definitions, questionnaire data models, PHQ-9/GAD-7 scores, mwTool eligibility, or dbt model development for Engage.

Generate professional shot lists from screenplays and scripts. Use when user uploads a screenplay (.fountain, .fdx, .txt, .pdf, .docx) or describes scenes for production planning. Parses scripts to extract scenes, helps determine camera setups, shot types, framing, and movement through collaborative discussion, then generates beautifully formatted PDF shot lists for production. Triggers include requests to create shot lists, plan shots, break down scripts for filming, or organize camera coverage.

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

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills. Use when creating Claude skills from docs, scraping documentation, packaging websites into skills, or converting repos/PDFs to Claude knowledge.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

> **START WITH WARNINGS, ONLY BLOCK WHEN NECESSARY**

Resume session with minimal context load

Flutter design system and UI tokens

Guide for interacting with Obsidian vaults via MCP. Use when the user wants to read, write, search, manage tags, or organize notes within their Obsidian vault.

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

Detect slow queries and performance issues in Entity Framework Core codebases. Use when analyzing database performance, finding N+1 queries, identifying missing indexes, reviewing repository patterns, or optimizing EF Core queries. Triggers on requests like "find slow queries", "check for N+1 problems", "analyze database performance", "review query performance", or "optimize EF Core queries".

CQRS+DDD implementation patterns for .NET. Use when designing aggregates, implementing command/query handlers, setting up repositories, or understanding architectural principles. Triggers on "CQRS", "DDD", "aggregate", "command handler", "query handler", "repository", "value object", "domain event", "entity configuration".

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. Use when working with spreadsheets (.xlsx, .xlsm, .csv, .tsv) for creating, reading, analyzing, or modifying spreadsheet data.

Robust shell scripts with POSIX compliance, error handling, and automation patterns. Use when writing bash/zsh scripts, deployment automation, or system administration tasks.

Create Architecture Decision Records (ADRs) documenting significant technical decisions for the FF Analytics platform. This skill should be used when making architectural choices, evaluating alternatives for data models or infrastructure, documenting trade-offs, or when the user asks "should we use X or Y approach?" Guides through the ADR creation workflow from context gathering to documentation.

创建有效技能的指南。当用户想要创建新技能（或更新现有技能）以通过专业知识、工作流程或工具集成扩展Claude功能时，应使用此技能。

全面的电子表格创建、编辑和分析功能，支持公式、格式、数据分析和可视化。当Claude需要处理电子表格（.xlsx、.xlsm、.csv、.tsv等）时，可用于：(1)创建带有公式和格式的新电子表格，(2)读取或分析数据，(3)在保留公式的同时修改现有电子表格，(4)在电子表格中进行数据分析和可视化，或(5)重新计算公式

Expert guidance on statistical analysis methodologies and Monte Carlo simulation for fantasy football. Use this skill when selecting regression approaches, designing simulations, performing variance analysis, or conducting hypothesis tests. Covers regression types (OLS, Ridge, Lasso, GAMs), Monte Carlo frameworks, regression-to-mean analysis, and statistical best practices for player performance modeling.

This skill should be used when the user asks about "MCP tools", "Unity MCP", "enable tool groups", "which MCP tools", "create GameObject", "add component", "run Unity tests", "check scene hierarchy", "spawn agent for Unity", "MCP not working", or needs to coordinate Unity Editor operations via MCP.

Control Dyson air purifiers, fans, and heaters via local MQTT. Use when asked to control Dyson devices, adjust fan speed, set temperature/heat, enable oscillation, or check room temperature/humidity. Requires being on the same WiFi network as the device.

Use this skill to offload heavy operations (build, test, lint, typecheck, playwright) to ArtemiPC, a high-powered worker machine with 32 cores and 31GB RAM.

Generate actionable insights from transaction data. Use when implementing insight generators, anomaly detection, or data analysis features for financial/tax tracking applications.

Optimize and test LLM prompts for the research agent. Use when writing prompts, improving prompt quality, debugging LLM responses, fixing JSON parsing issues, or tuning output format.

Tune and optimize fact-checking in the research agent. Use when adjusting claim extraction, verification strictness, fixing fact-check loops, reducing API costs, or improving accuracy.

Comprehensive Claude Code conversation analysis skill for deep-diving into CC session logs. Use when analyzing exported Claude Code conversations to understand: project patterns, error rates, command failures, security risks, session duration, tool usage, and workflow efficiency. Triggers: "analyze conversation", "CC analysis", "conversation analysis", "session review", "Claude Code logs", "analyze my sessions", "review CC usage", "conversation insights", "what went wrong in my session", "session forensics", "CC forensics"

Update assistant-ui and AI SDK to latest versions. Detects current versions, identifies breaking changes, and executes migrations.

Guide for tool registration and tool UI in assistant-ui. Use when implementing LLM tools, tool call rendering, or human-in-the-loop patterns.

Evaluates work quality before allowing progression to next stage.

自動的にGitHub Issueを分析し、構造化された内容に改善するスキル。 雑なIssueや情報不足のIssueをAIが作業しやすい形式に自動補完・加筆訂正する。 タイトルの標準化、本文の構造化、適切なラベル付与、不足情報の指摘を行う。 「このIssueを改善して」「Issue内容を整えて」といった依頼で使用。

Deploy web applications to Domino Data Lab with expertise in React apps (Vite) behind Domino's reverse proxy. Covers app.sh configuration, port configuration, base path handling for SPAs, CI/CD with GitHub Actions, and proxy troubleshooting. Use when deploying apps to Domino, setting up CI/CD pipelines, fixing broken routing, or configuring JavaScript frameworks for Domino's proxy.

Connect Domino workloads to external data sources including AWS S3 (via Mountpoint CSI driver), credential propagation with AWS IRSA and Azure Entra ID, and External Data Volumes. Use when configuring S3 access, setting up credential propagation, or connecting to cloud data sources from Domino.

Work with Domino Workspaces - interactive development environments including Jupyter, JupyterLab, VS Code, and RStudio. Covers launching workspaces, configuring hardware tiers, environment selection, volume mounting, SSH access, and package installation. Use when setting up development environments, configuring workspace settings, or troubleshooting IDE issues.

Guide for developing, deploying, and managing AI agents on Amazon Bedrock AgentCore. Use this skill when working with AgentCore services including Runtime (deploying agents), Memory (persistent knowledge storage), Gateway (MCP endpoints), Code Interpreter, Browser, Observability, or Identity. Triggers on questions about deploying agents to AWS, agent lifecycle management, memory integration, MCP gateways, or the agentcore CLI.

YouTube content strategy partner for data-driven planning. Use when you need to research video ideas, analyze competing videos or channels, validate trends, extract transcript insights, or produce a structured YouTube strategy. Triggers on requests like "plan a YouTube video about X", "analyze competitors for Y", "find what performs for Z", or "is this topic trending on YouTube".

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.

Nano Banana Pro APIで画像・インフォグラフィックを生成する。ユーザーがイラスト、インフォグラフィック、ビジュアルアート、概念のビジュアル説明画像などを求めた時に使用する。

tree-sitter を使った Rust コード解析ツール。コードベースの構造を解析し、public/data/structure/ に構造化JSONを生成する。

rust-code-analysis-cli を使ったコード複雑度解析ツール。コードベースのメトリクスを解析し、public/data/complexity/ に構造化JSONを生成する。

Deploy and manage Vercel projects using the Vercel CLI. Use when deploying Next.js apps, checking deployment status, managing environment variables, linking projects, or any Vercel-related operations. Triggers on "deploy to vercel", "vercel deploy", "check deployment", "add env var to vercel", "link vercel project".

GitHub webhook setup and handling patterns. Use when implementing PR/issue webhooks, verifying signatures, or debugging webhook issues.

Supabase patterns for server-side operations, webhooks, and bypassing RLS. Use when working with Supabase service role keys, SECURITY DEFINER functions, or webhook handlers.

Use when the user wants to setup a new project, create a new feature, write a spec, plan a feature, fix a bug with a plan, start a new track, check project status, implement next task, or revert changes. Also use when user mentions "conductor", "track", or "spec-driven development". If conductor is not yet configured in the project, start with setup.

Guide for implementing error boundaries and crash reporting in Ignite React Native apps. Use when handling runtime errors, customizing error screens, integrating crash reporting services, or implementing graceful error recovery. Triggers on error handling, crash reporting, error boundary setup.

Guide for implementing API services using Ignite's services pattern. Use when creating API endpoints, HTTP requests, backend integrations, or data fetching. Triggers on API implementation, service creation, backend integration, data fetching.

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

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

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

Behavior-preserving code cleanup and compaction with strict verification gates. Only runs when the repo has a runnable build/test command set. Refactors safely, removes dead code, reduces duplication, and hardens scripts without introducing breakage or violating guardrails.

Prepare a release including version bump, testing, and PR creation