AI Skills Hub - Browse 180,000+ Agent Skills

Automates browser interactions using Playwright CLI and templates - takes screenshots, generates PDFs, clicks elements, fills forms, monitors console/network. Use when testing web pages, automating browser tasks, or when user mentions screenshots, web testing, form automation, or Playwright

This skill should be used when users ask questions about pod network development, pod smart contract language, pod APIs, pod tooling, or pod-specific features. It provides semantic search over the pod network knowledge base to retrieve relevant documentation, code examples, and best practices.

PR作成時に生成AIがPR本文にオンボーディングを記述するスキル。変更の契約を、レビューア・将来の自分・障害対応者に渡す。理解の再現性・反証可能性・運用可能性を同時に成立させる。

Turns ambiguity into an Uncertainty Register, prioritizes items, and produces observation tasks/experiments with evidence and decision rules. Use when the user mentions uncertainty/unknowns/assumptions/validation/investigation/hypotheses/risks or cannot decide (不確実性, 曖昧, 未知, 前提, 仮説, 検証, 調査, 優先順位, 観測, 意思決定).

運用観測性の確保。ログ、メトリクス、ヘルスチェック、設定検証でバグを扱う能力を担保。Use when: デプロイ前チェック、障害調査が困難、原因不明、ログ設計、メトリクス設計、設定管理実装。

生成AIが人間に対して行う作業開始時オンボーディング。AIが"説明係"ではなく"進行役"として、探索→仮説→検証→要約→未確定の明示を回し、人間が最小スキーマ（因果・境界・不変条件・壊れ方・観測）を短時間で再構築できる状態に導く。

Issueの初期トリアージスキル。Issueを受け取り、標準化された分析結果（分類・深刻度・影響スコープ・不確実性・次アクション参照）を生成する。GitHub/Jira/Linear等のトラッカーからissue_payload形式で受け取る。

This skill should be used when the user asks to "sync to Google Calendar", "import activities to calendar", "add GitHub/Linear events to calendar", or "convert activity report to calendar". Transforms structured activity data into gcalcli commands for Google Calendar import.

Updates the Betty Framework Skill Registry when new skills are created or validated.

Automatically wraps verbose commands (pytest, ruff, builds) with silent execution for context-efficient output. Use this proactively when running tests, linters, formatters, or build commands to minimize context usage while preserving error information.

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

Generate Builder Methods hand-drawn line art illustrations (icons, scenes, periphery) with a single accent color (Coral/Teal/Indigo/Amber). Use for blog headers, thumbnails, course graphics, social posts, and on-brand UI/tech metaphors.

Schedule recurring background tasks in rwsdk/Cloudflare Workers - cron syntax, setup, local testing, and patterns for cleanup, metrics, billing, and maintenance

Validates beads issues after creation. Checks dependencies, PRD mapping, order, and issue quality. Use when: after creating issues, before TDD loop, before handoff. Triggers: "validate beads", "check issues", "verify tasks", "check quality", "validate handoff".

Build .NET solution/projects using dotnet CLI. Use when task involves compiling, restoring dependencies, or building artifacts.

Run .NET tests using dotnet CLI. Use when task involves executing unit tests, generating code coverage reports, or running benchmarks.

Generates intelligent GitLab merge request descriptions from git commits with automatic categorization and Jira integration

This skill should be used when users need to create Jira tickets for the RD (Research & Development) project. It supports creating features, bugs, and tasks with proper field mapping including assignee, team, sprint, and state. The skill uses Jira CLI commands and provides templates for different ticket types.

OpenSCAD 3D modeling assistant for creating and modifying parametric 3D models. Use when working with .scad files, making adjustments to 3D models (resizing, adding/removing sections, holes, fillets), creating new OpenSCAD geometry, or debugging OpenSCAD code. Supplements the openscad MCP server (mcp__openscad__render_single) with language knowledge and modification patterns.

Conditionally installs GitHub Packages component library at latest version. Adds to package.json when user requests it.

Extracts all chunks with three-tier contextual embeddings from a specific PDF file in Qdrant vector database and saves to plain text. Use when user wants to extract, export, dump, or view all chunks from a PDF document, inspect file content, save chunks for analysis, or review contextual embeddings.

Implements TF-IDF based search engines for text datasets using vector space models and cosine similarity. Use when building search functionality, finding similar documents, ranking text by relevance, or working with text retrieval systems.

Open状態のGitHub Issueから低品質・曖昧なIssueを検出して分析するスキル。 「Issueが多すぎてどれから対応すべきか分からない」「質問や報告の質を上げたい」場合に使用。 環境変数で指定されたリポジトリのIssueを品質評価し、最もスコアの低いIssueを特定する。

Clean up test sessions - kill browsers, stop dev servers, free ports, and optionally remove test data. Use this BEFORE starting new tests or AFTER completing tests.

Helps organize files in a Johnny Decimal system at ~/Documents. Use this skill when filing documents, finding files, creating folders, taking notes about JD items, or understanding where something belongs in the system.

Create or update Codex skills (SKILL.md plus optional scripts/references/assets). Use when asked to design a new skill, update an existing skill, or validate/package skills.

Create, improve, and debug professional LuaLaTeX documents using KOMA-Script + the moderndoc package (and the legacy modern-doc shim). Use for: generating new documents from a goal, improving typography/layout, producing PDF/A-4-friendly output, setting up minted/biblatex/tabularray/tikz, converting Mermaid → TikZ, and debugging compilation logs.

Monitor and troubleshoot dual-pipeline data collection systems on GCP. This skill should be used when checking pipeline health, viewing logs, diagnosing failures, or monitoring long-running operations for data collection workflows. Supports Cloud Run Jobs (batch pipelines) and VM systemd services (real-time streams).

Execute chunked historical blockchain data backfills using canonical 1-year pattern. Use when loading multi-year historical data, filling gaps in ClickHouse, or preventing OOM failures on Cloud Run. Keywords chunked_backfill.sh, BigQuery historical, gap filling, memory-safe backfill.

Run EPUBCheck and Ace accessibility validation. Use before final EPUB packaging or distribution to ensure publication readiness.

Guided workflow for implementing HTML design prototypes as production React components with glassmorphism styling and quality standards enforcement. Use when converting design prototypes to production code.

Triage large log directories without loading everything into context by extracting and grouping errors, emitting a compact debug brief, and (optionally) chunking raw logs for LLM upload.

Scaffolds tRPC routers, procedures, and Zod schemas with full type safety following DevPrep AI patterns

Tic Tac Toe game development for Unity. Use for game logic, AI implementation, MVVM architecture, and UI development specific to this project.

Browser automation for NHS Nervecentre EPR systems using local MCP servers. Use when asked to scrape, extract, or interact with Nervecentre patient data, worklists, clinical notes, or any NHS EPR system that requires local network access. Supports browser-use MCP (primary), Playwright MCP (fallback), and Browser MCP extension. Handles OAuth 2.0 authentication, dynamic SPA content, and FHIR-compliant data extraction. IMPORTANT - Requires local network access (hospital WiFi) - cloud browser services will not work.

Set up custom Claude Code status line with Nerd Font icons, colors, git status, usage tracking, system info, and project context. NO EMOJIS - only Nerd Font icons and symbols. Use when configuring statusline, setting up status bar, or customizing Claude UI. Triggers with statusline, status bar, custom theme.

[What it does + when to use + trigger keywords]

Manages local web server lifecycle and enables web page development with Playwright MCP. Use when developing HTML/CSS/JS, building web pages, viewing web pages, testing UI interactions, verifying renders, debugging frontend issues, or iterating on web design. Covers build, startup, shutdown, and browser-based testing workflows.

Generate comprehensive test coverage reports when reviewing code. Identifies untested code paths and low-coverage areas. Supports Python (pytest-cov), JavaScript (jest), Go (go test -cover), Java (JaCoCo). Use when reviewing tests or before approving code changes.

Track development velocity, cycle times, and identify trends for PM decision-making

Run code quality linters when reviewing code. Checks style, complexity, and best practices. Supports Python (ruff), JavaScript (eslint), Go (golangci-lint), Ruby (rubocop), Java (Checkstyle/PMD). Use when reviewing any code changes for quality issues.

Detect dangerous operations in database migrations before deployment

Seed JSON configuration files into database. Use ONCE at BAZINGA session initialization, BEFORE spawning PM.

Analyze existing tests to identify patterns, fixtures, and conventions before writing new tests

Mine historical data for patterns and predictive insights

Architecture rules and validation patterns for Claude Code marketplace components ensuring self-contained skills, proper skill usage, and clean reference patterns

Detect breaking changes in API contracts (OpenAPI/Swagger specs)

Run comprehensive security vulnerability scans when reviewing code. Automatically uses basic mode (fast, high/medium severity only) for first reviews, advanced mode (comprehensive, all severities) for iterations. Detects SQL injection, XSS, hardcoded secrets, insecure dependencies. Use before approving any code changes or pull requests.

Unified project health dashboard aggregating all quality metrics

Control interactive terminal processes via tmux - launch CLI applications, send input, capture output, wait for completion. This skill should be used when tasks require interactive debugging (pdb, node inspect), REPL exploration, long-running observable processes, or spawning another Claude instance for independent analysis or second opinions.

Two-phase reasoning paradigm that reduces hallucinations and constraint violations in complex planning tasks. Use when tasks involve multi-step planning, constraint satisfaction, resource allocatio...

Guides correct usage of @j0kz/mcp-agents standardization and automation scripts including version.json single source of truth, test count automation, URL casing rules, and critical workflow pattern...

Guides creation of new MCP tool packages in @j0kz/mcp-agents monorepo following modular architecture with constants/, helpers/, utils/ extraction, tools.json registration, and version.json synchron...

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when building MCP servers to integrate APIs, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Provides expert guidance for NautilusTrader algorithmic trading platform. Covers backtesting strategies, live trading deployment, event-driven architecture, and building trading systems.

GitHub CLI (gh) operations for repos, PRs/issues, workflows/runs, secrets/variables, releases/tags, and deployment-related automation. Use when a request involves gh commands, GitHub Actions workflows/runs, secrets or variables, releases, deployments/environments, or coordinating git with GitHub.

Enforce Sketch Magic dev-readiness gates. Use when asked “are you done?”, when dev server errors appear, when proof video is required, or when verifying compile/lint/test/dev-smoke status.

Vercel CLI expert for serverless deployment. Use when users need to deploy apps, manage domains, env vars, or Vercel projects.

Use when requesting or receiving code reviews - covers dispatching review subagent, handling feedback with technical rigor, and avoiding performative agreement

Capture bugs/enhancements/ideas to request-logs. For quick operations use /mc command instead.

Use after completing a refactor, implementing a major feature, or when skills may be outdated. Analyzes code changes, identifies affected skills, and proposes updates to keep team knowledge current. Also use when you notice a skill contains outdated patterns. Ask clarifying questions if changes are confusing.

Use when working with embeddings, semantic similarity, vector search, or the <-> <#> <=> operators. Load for pgvector queries, HNSW index creation, embedding storage, or similarity calculations. Covers distance operators, index strategies, and common pitfalls with 384-dimensional vectors.

Project context from ChromaDB knowledge graph. Triggers on "how does this project work", "architecture", "where is X", "why was Y chosen", "project structure", "component relationships", "design decisions".

Read/write FASTA, GenBank, FASTQ files. Sequence manipulation (complement, translate). Indexed random access via faidx. For NGS pipelines (SAM/BAM/VCF), use pysam. For BLAST, use gget or blat-integration.

Render Manim scenes to still frames and review them to diagnose animation/layout issues. Use when debugging scenes, verifying visual correctness, or inspecting frame-by-frame output.

Implement Claude Code hooks for deterministic control over agent behavior. Use when creating custom hooks for notifications, auto-formatting, logging, feedback, permissions, or lifecycle events.

Build .NET solution/projects using dotnet CLI. Use when task involves compiling, restoring dependencies, or building artifacts.

Generate a recap of recent Claude Code sessions with summaries of what was discussed and accomplished

Run .NET tests using dotnet CLI. Use when task involves executing unit tests, generating code coverage reports, or running benchmarks.

Manage git worktrees for parallel branch development using custom git scripts (git-newtree, git-killtree, git-maingulp). Use when creating new worktrees, listing active worktrees, or closing/merging worktrees back to main. All worktrees are stored in .tree/ subdirectories of the repository.

Professional document generator for Active Directory health assessments. Creates executive-quality DOCX reports with consistent branding, proper data visualization, severity-based formatting, and actionable remediation guidance. Use when generating assessment reports from OpsIdentity JSON data or improving document output quality.

Package custom skills into versioned distributable ZIP files with installation and user documentation. Use when preparing a skill for sharing, distribution, or archival. Supports semantic versioning, automatic documentation generation, and version management.

Deploy to Azure Container Apps using azd (provision + deploy workflow)

Active Directory operational hygiene analyzer for OpsIdentity project. Detects administrative disorder, architectural debt, and suboptimal configurations—not offensive security. Use when (1) improving OpsIdentity PowerShell collection functions, (2) adding AI analysis prompts to server.js, (3) analyzing coverage gaps against 87 industry metrics, (4) implementing smart filtering or anti-hallucination rules. Triggers on AD health, GPO analysis, replication, trusts, token size, FSMO, site topology, DNS/DHCP hygiene, or requests to analyze existing OpsIdentity code.

Use when educators need to validate if their lesson plan covers all 3 Delegation subcategories (Problem/Platform/Task Awareness). Analyzes lesson plans and provides objective scores (0-10) with actionable feedback. Works in Claude.ai, Claude Code, and API for maximum portability.

Send a Bark push notification when work is blocked, needs user input, or when all requested tasks are finished. Use by default for these cases unless the user explicitly opts out.

WSL2 system health checks and Windows-specific hardening operator kernel for SYSopGPTWSL: run a repeatable sysop pipeline (preflight, WSL healthcheck, drift check, Windows snapshot via PowerShell, perf bench), produce a diffable report, and append evidence to `learn/LEDGER.md`. Use for sysop/health checks, drift/baseline verification, or when debugging Windows/WSL interop pitfalls (UNC cwd, UTF-8 BOM in PowerShell JSON, `/mnt/c` performance) and for Windows-side hardening/performance signals (power plan, power throttling, storage/volume inventory, WSL status/version). Use Plan-first execution and explicit verification reporting.

Process documents into RAG database. Use when user wants to chunk, embed, or index files into a vector database for semantic search.

Use this skill to validate code changes pass all checks (format, lint, build, tests). Runs validation script and iteratively fixes failures. Invoke before finalizing PRs or after making code changes.

Write and validate SimpliX documentation following project templates and guidelines. Use when creating README files, overview documents, feature guides, or any markdown documentation for SimpliX modules.

This skill should be used when the user asks to 'create an article', 'add a blog post', 'modify frontmatter', 'add a category', or 'update content schema'. Provides guidance for MDX articles, content-collections, and static content data in content/articles/*.mdx, content/data/*.ts, content-collections.ts.

新しいスキルを対話形式で作成するメタスキル。 スキルの作成、新規スキル追加、カスタムスキル開発、スキルテンプレート生成をサポート。 要件をヒアリングし、SKILL.md、scripts/、references/を自動生成する。 Use when user asks to create a new skill, add custom skill, or develop agent capabilities.

Manage git worktrees with shell scripts for listing, creating, and deleting worktrees. Use when working with git repositories and need to create worktrees with new branches, delete existing worktrees, or view all worktrees. Particularly useful for parallel feature development or testing multiple branches simultaneously.

Guide for developing Tauri v2 desktop apps on macOS. Covers debugging native apps (Rust panics, Sentry integration, thread-local issues), app signing and updater setup, global shortcuts, Keychain secret storage, and Homebrew distribution. Use when building Tauri apps, debugging Rust backend issues, setting up auto-updates, handling keyboard shortcuts, or distributing macOS apps.

Reduce LLM API costs without sacrificing quality. Covers prompt caching (Anthropic), local response caching, prompt compression, debouncing triggers, and cost analysis. Use when building LLM-powered features, analyzing API costs, optimizing prompts, or implementing caching strategies.

Programmatically update marathon-ralph state file using deterministic jq commands. Use this instead of manually editing the JSON file.

Use when CI fails on Buildkite and you need to diagnose and fix failures - fetches build results for current branch, extracts errors from logs, and helps fix them

API-first iFood automation for the clifood project. Use when an AI agent needs to find restaurants/items, build carts, prep orders, or extend iFood API integrations in this repo.

Structured Brave Search web queries and summarizer workflows for MCP-style agents.

Build Claude skills from extracted documentation. Use after doc-scraper/pdf-extractor to generate uploadable skill packages.

Standardize all GitHub interactions via the GitHub CLI (`gh`) instead of ad-hoc URLs, UI clicks, or direct REST API calls. Use when you need to read or change GitHub state (repos, issues, pull requests, reviews, check status, Actions workflows/runs, releases, labels, milestones, discussions, gists) and want deterministic output (prefer `--json` + `--jq`). Also use when the user provides a GitHub URL, including deep links like `https://github.com/OWNER/REPO/pull/123`, `.../issues/123`, `.../pull/123/files`, or comment permalinks like `#issuecomment-...`, and you need to fetch the underlying PR/issue/thread and reply. Fall back to `gh api` only when there is no first-class `gh NOUN VERB` command.

Audit SENTINEL game data integrity. Validates regions, jobs, vehicles, and favors against schema enums.

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.

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use for ML training, analytics tools, performance profiling, or any Python heavy lifting.

Validate planning documents before implementation begins. Checks ambiguity resolution, prerequisites, and testing methods. Use when: - Before starting implementation of a ticket - User says "validate plan", "check plan", "ready to implement?" - After completing 2-plan.md and 3-spec.md - Before TDD cycle begins

Convert multiple video files (MOV/MP4) into a single merged GIF with customizable speed per segment. Use this skill when users want to: - Merge multiple videos into one GIF - Create demo GIFs from screen recordings - Combine video clips with different playback speeds - Convert videos to optimized GIFs with compression Triggers: "create GIF from videos", "merge videos to GIF", "convert MOV to GIF", "combine videos into animated GIF"

Guide for spike-driven development methodology. Use when starting new features, testing architecture patterns, integrating unfamiliar APIs/data sources, or validating technical feasibility before full implementation. Emphasizes TDD, real data validation, and risk reduction through minimal proofs-of-concept.

Constroi servidores MCP (Model Context Protocol) para conectar o Claude ao banco de dados PostgreSQL e APIs do PCA Camocim.

Convert subtitle files (WebVTT .vtt and SubRip .srt) into clean, readable text documents with multi-language support (English, Traditional Chinese, Simplified Chinese). Auto-detects format and language, removes timestamps and formatting, merges captions into natural paragraphs, strips annotations, and fixes spacing appropriately for each language. Use when the user provides a subtitle file or asks to convert captions to text.

Write privacy-preserving smart contracts in Compact (Minokawa) for Midnight Network. Use when creating contracts, defining types, using standard library functions, or implementing ZK patterns. Triggers on Compact language, circuits, ledger state, hashing, or zero-knowledge contract questions.