AI Skills Hub - Browse 180,000+ Agent Skills

Publish OpenWork DMG releases

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

Automates the build, git tagging, changelog generation, and deployment to Firebase Hosting.

Given a binary search tree (BST), find the lowest common ancestor...

Initialize kanban board infrastructure in project. Creates .kanban directory, copies viewer HTML, adds npm script. Use when setting up kanban board for first time.

Always load first in this repo to manage PRDs/specs/projects and keep append-only Implementation Notes.

Integrates Keywords Everywhere API to validate page strategy and optimize content. Use when (1) Architect Agent validates keyword viability before committing to pages, or (2) Content Agent needs related keywords for copy optimization.

Use when creating standalone Python scripts, utility scripts, automation scripts, or data processing scripts that are not part of a larger package.

Export Pixel Detective UMAP projections with HDBSCAN and manage Qdrant collections via the ingestion API. Use when the user asks for latent space exports, UMAP clustering assets, or collection operations (list/create/select/delete/merge).

Customized Xiaohongshu content generator for summarizing articles into minimalist, high-quality visual cards with strict platform compliance

Export Dev Graph UI assets and dashboard data. Use when the user asks for structure SVG exports, timeline SVG/MP4 exports, per-commit SVGs, sprint-linked visuals, or dashboard/analytics JSON from the Dev Graph API.

Start, stop, or check Dev Graph services on this machine. Use when the user asks to start Dev Graph, start backend only, start full stack, restart, stop, or check Docker, Neo4j, API, or UI status, or to provide a specific Dev Graph page URL.

Generate per-sprint perspectives (narrative + cards) by mining git history for documents and files co-updated alongside sprint anchor docs. Use when the user asks for sprint perspectives, evidence linking, research doc discovery, or sprint retrospectives with code-change metrics.

Generate per-sprint PDF summaries with a card layout from docs/sprints. Use when the user asks for sprint summaries, sprint recap PDFs, shareable sprint story cards, or to drop PDFs into each sprint folder.

Extract and read Claude conversation JSONL files with composable filters (discovery: rubber-duck). Evaluate at rubber-duck or at any point in the sesssion when task requires reading conversation history, verifying tool outputs, or auditing session behavior. Use instead of raw Read/grep on ~/.claude/projects/*.jsonl files.

MongoDB patterns. Schema design, document modeling, indexing, aggregation pipelines, Mongoose/native driver patterns.

Query and display Juicebox V5 fund access limits (payout limits, surplus allowances). Use when: (1) surplusAllowancesOf or payoutLimitsOf returns empty but values exist, (2) need to detect "unlimited" values which can be various max integers not just uint256, (3) fund access limits show as zero for USDC-based projects when querying with ETH token, (4) REVDeployer stageOf or configurationOf reverts. Covers JBFundAccessLimits querying, multi-token support (ETH/USDC), ruleset chain walking, and unlimited value detection.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Use when editing .vue files, creating Vue 3 components, writing composables, or testing Vue code - provides Composition API patterns, props/emits best practices, VueUse integration, and reactive destructuring guidance

このスキルは、ユーザーが「PDFを作成」「PDFからテキストを抽出」「PDFを結合」「PDFフォームに記入」「PDFを分割」「PDFからテーブルを抽出」「PDF OCR」「PDFを暗号化」「PDFメタデータを編集」などを要求した際に使用する。

このスキルは、ユーザーが「Inngest 関数を作成」「バックグラウンドジョブを実装」「ステップ関数を書く」「Inngest をセットアップ」「イベント駆動処理を実装」「耐久実行を実装」「Cron ジョブを作成」「Fan-out パターンを実装」「サガパターン」「ワークフローオーケストレーション」「step.run」「step.waitForEvent」「step.invoke」「Inngest テスト」と言った場合に使用する。

Work with InstantDB database in Boundless. Use when querying data, creating transactions, updating entries, or working with the schema. Covers entries, settings, and real-time subscriptions.

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature. Use when users invoke `/speckit.taskstoissues`, want to create GitHub issues from tasks, need to sync task list with issue tracker, or want to enable team collaboration on implementation. Requires a GitHub repository with proper remote configured.

Playbook for the Beer Line Watcher repo (Next.js + Prisma + LINE bot for beer event crawling/notifications). Use when updating crawlers, cron/LINE API routes, Prisma models, or running the app locally/deploying.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.

Generate .xlsx reports from JSON/CSV inputs using a local Python utility. Use this skill to convert structured data into Excel workbooks, add formatting, and produce multi-sheet reports.

Digital pathology image processing toolkit for whole slide images (WSI). Use this skill when working with histopathology slides, processing H&E or IHC stained tissue images, extracting tiles from gigapixel pathology images, detecting tissue regions, segmenting tissue masks, or preparing datasets for computational pathology deep learning pipelines. Applies to WSI formats (SVS, TIFF, NDPI), tile-based analysis, and histological image preprocessing workflows.

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

Draft a conventional commit message when the user asks for help writing a commit message.

R package for creating REST APIs with plumber framework

R package for calibrating verbal autopsy cause-of-death classifications using Bayesian methods

Browser automation via visual AI. Use when executing ATML tests, interacting with web pages, or automating browser tasks. Core tool for Airis test execution.

Smart PR creation and updates with auto-generated descriptions and pre-flight checks

Interactive release workflow with automated checks and tasks

Practical guide for maximizing organic engagement on X (Twitter) based on reverse-engineering the open-sourced recommendation algorithm. Use this skill when users ask about: (1) How to get more reach/engagement on X/Twitter, (2) How the X algorithm works, (3) Content strategy for X, (4) Why posts aren't getting visibility, (5) Best practices for posting on X, (6) Understanding the For You feed algorithm.

Standardized status reporting for agents and subagents. Ensures consistent progress tracking and machine-readable results.

This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 25 available options, extracts parameters based on detailed specifications, and generates a chart image using a Python script.

Scala 3.4+ development specialist covering Akka, Cats Effect, ZIO, and Spark patterns. Use when building distributed systems, big data pipelines, or functional programming applications.

Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.

rustfeed のフィード管理（追加、削除、更新）と記事操作（取得、既読管理、お気に入り）のCLI/TUIコマンド実行をサポートします。フィード操作、記事取得、データベース操作時に使用します。

Read-only Jira integration for querying issues, sprints, projects, and users

Create and manage Issues - individual work items with testable acceptance criteria. Use when planning features, creating tasks, or updating issue status.

Fetch tweets and download Twitter/X videos without API key

The reference framework to generate, compile, and lint greenfield prompts that conform to the Agnostic Prompt Standard (APS) v1.0.

Build Model Context Protocol (MCP) servers that enable Claude to interact with external services. Creates TypeScript or Python MCP servers with proper tool schemas, error handling, and testing. Use when: building MCP servers, integrating APIs, extending Claude's capabilities, or when user mentions MCP, Model Context Protocol, Claude擴展, external tools, MCP server. Triggers: "MCP", "Model Context Protocol", "MCP server", "Claude擴展", "external tools", "整合API"

Create state machine diagrams of existing components to map out all code paths and verify system understanding. Use when analyzing user flows, authentication, multi-step processes, or any stateful logic to ensure comprehensive coverage of all transitions, edge cases, and error paths.

JPA entities, repositories, and Hibernate ORM patterns for Spring Boot 3.2.5 with Kotlin Use when: Creating/modifying entities, repositories, database queries, or handling persistence layer concerns

Publish a new release of hardimpactdev/craft-laravel to Packagist. Handles CHANGELOG updates, git tagging via GitHub CLI, and creating GitHub releases.

Write Playwright E2E tests using MCP browser for selector discovery and verification. Use when implementing new tests, discovering selectors, or building test flows step-by-step with real browser state. It is designed to be iterative and self-improving.

Develop and maintain Convex backend functions including queries, mutations, and actions. Use when working with database operations, authentication, game management, scoring logic, and real-time data updates in the dev-quiz-battle app.

Guide for consuming the leader-owned Graph API service. Use this when asked to fetch graph data, integrate with Graph API, or understand API consumption patterns.

Guide for running and understanding predictive analysis simulations. Use this when asked to simulate failures, scaling scenarios, or understand simulation logic.

Guide for Kubernetes deployment using Minikube. Use this when asked about deployment, Kubernetes manifests, or local k8s testing.

Generate optimized CLAUDE.md files for Claude Code projects. Use when user wants to create a new CLAUDE.md, asks how to set up Claude Code, mentions project constitution or project rules, or wants to configure Claude Code behavior. Supports web frontend, backend, fullstack, CLI, library, and monorepo projects.

Fetch manual YouTube subtitles (no auto captions), fall back to local Whisper (turbo) when manual subs are missing, then translate to Korean/English with Codex CLI. Use when a user provides a YouTube link and needs high-quality subtitles, bilingual subtitle generation, or SRT/VTT outputs.

Convert a Korean transcript (SRT/VTT/plain text) into a detailed Markdown document with a 3-line summary and chaptered notes with timestamps. Use when a user provides transcript text and wants a structured Markdown writeup with minimal content loss.

Use when implementing error handling, cleanup routines, or debugging in shell scripts. Covers traps, exit codes, and robust error patterns.

Use when you have customer feedback files (transcripts, tickets, surveys) and need to identify themes and opportunities without hallucinating.

Logs every compilation event with timing, tier (T1/T2), success/failure, and invalidation reasons. Use to verify hot code is compiling, diagnose compilation failures/bailouts, track recompilation cycles, and understand tiered compilation behavior. Shows WHEN compilation happens. Combine with detecting-performance-warnings to understand WHY compilation fails.

Traces deoptimization events where execution falls back from compiled code to interpreter. Use to detect deoptimization loops, unstable assumptions, and type instability. Zero transfers in steady-state is the goal. Many transfers indicate severe performance problems. Critical for diagnosing compilation instability.

Time-based sampling profiler showing WHERE execution time is spent (wall-clock time, not frequency). Provides histogram with self/total time, compilation tiers (T0/T1/T2), and flame graphs. Use as FIRST step to identify hot functions consuming most time. Low overhead, suitable for longer runs. Pair with tracing-execution-counts to understand time-per-execution vs execution frequency.

Detects optimization barriers during Truffle compilation. Identifies virtual calls, non-constant stores, unresolved type checks, and TruffleBoundary issues that prevent peak performance. Reports exact source locations with stack traces. Use as essential step for eliminating compilation warnings. ONLY works with traditional Truffle DSL nodes (NOT Bytecode DSL).

Configures and builds ESP-IDF projects from within Claude Code or other environments that use Git Bash/MSYS. Use when setting up ESP-IDF based ESP32/ESP32-C6 projects, running idf.py commands, building firmware, flashing devices, or troubleshooting ESP-IDF builds on Windows where MSYS/Mingw environments are not officially supported. Not for use with PlatformIO projects.

Signal secure messaging via signal-cli REST API. USE WHEN sending signal messages, checking signal, secure messaging. Invoke with /signal.

ServiceDesk Plus ticket management. USE WHEN checking tickets, viewing overdue tickets, adding notes to tickets, replying to tickets, OR managing SDP helpdesk requests. Invoke with /sdp.

Telegram Bot API integration for personal messaging. USE WHEN sending telegram messages, checking telegram, managing personal chats. Invoke with /telegram.

Ant Design Pro（Umi Max）前端项目的开发/质量门禁/构建/部署前检查。提供：yarn 脚本约定、产物目录、常见坑点。 适用：前端开发、构建失败排查、上线前静态资源检查、与后端联调。 不适用：非 Umi Max/非 Ant Design Pro 的前端项目（先识别脚手架）。

Python3 + uv 项目的开发/测试/修复闭环。提供：测试入口标准化、常见项目结构与排错路径。 适用：实现后端功能、修复后端 bug、增加/修复测试、依赖与运行问题排查。 不适用：未明确技术栈的项目（先确认是否为 uv 管理）。

Generate and maintain a project structure index for fast AI navigation. Creates docs/structure.md with an AI-friendly map + tree. Use when starting a new project, after major changes, or when docs/structure.md is stale.

Use this to search the internet or fetch/read a URL in a real browser session (headless Brave via CDP). Prefer this over curl for JS-heavy or bot-protected sites.

Runs Credible Layer assertion backtests against historical transactions. Use when validating assertions on real chain data or known exploits.

Diagnoses common assertion failures and non-triggering issues. Use when assertions fail unexpectedly or do not execute.

Tests Phylax Credible Layer assertions with CredibleTest, fuzzing, and backtesting. Use when writing or reviewing assertion tests.

Practice integration-first TDD in this repo (Svelte + TS + Playwright). Write step-by-step user-interaction story tests with immutable “intent” comments and flexible implementation. When expectations are unclear or contradictory, switch to a focused Q&A mode and only change intent text with explicit user approval.

Управление слайдами презентации mobileDemo - создание, редактирование и сборка

Use when you see /quality-gate, проверь категорию, финальная проверка, валидация перед деплоем. (project)

Create specialized subagents for Claude Code. Use when user wants to create a new agent, configure specialized AI assistants, or says /create-agent, создай агента, новый агент, create agent. Subagents are AI assistants with custom prompts, specific tool access, and focused configuration for domain-specific work.

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

Skills for session management and protocol compliance including investigation eligibility checking per ADR-034 to determine when QA validation can be skipped.

Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus.

Create and manage Docusaurus-based documentation books. Use when building structured educational content, technical books, or multi-module documentation sites. Triggers on requests involving Docusaurus setup, sidebar configuration, MDX content authoring, versioning, or GitHub Pages deployment.

Calculate final scores combining efficacy and safety

Match essential genes in target genome using orthology and literature

Design dsRNA candidates using sliding window algorithm

Search PubMed for RNAi/dsRNA research on target genes or species (utility skill - use anytime)

Transform sequential Python code into parallel/concurrent implementations. Use when asked to parallelize Python code, improve code performance through concurrency, convert loops to parallel execution, or identify parallelization opportunities. Handles CPU-bound (multiprocessing), I/O-bound (asyncio, threading), and data-parallel (vectorization) scenarios.

CLI tool for capturing agent trajectories. Execute prompts against ACP-compatible agents, capture full trajectories (tools, thoughts, plans), and output structured JSONL for downstream scoring.

Designs website content strategy and generates all content assets before development. Creates calls-to-action, audience analysis, sitemaps, page content, form specs, and custom post type definitions. Use when planning a new website, creating website content strategy, building site architecture, or generating website copy. Triggers on website design, content strategy, sitemap creation, or website planning requests.

Fast & safe Apple Mail search with body content support.

Implement and debug stock price fetching from Alpha Vantage or Yahoo Finance. Use when working with stock prices, API integrations, caching strategies, or the update-stock-prices cron job.

Knowledge base for designing AI-agent-friendly build documentation (project)

Cross-platform GPU kernel dialect — write once, run on NVIDIA (CUDA), AMD (HIP), and Intel/others (OpenCL 1.2). Use when: (1) writing portable GPU code across CUDA/HIP/OpenCL, (2) porting CUDA kernels to AMD or OpenCL, (3) creating/editing *.gu.cu files, (4) needing cross-vendor GPU compute, (5) using address-space qualifiers (__global/__local/__constant), (6) implementing portable atomics or shared memory, (7) debugging OpenCL render errors.

Create responsive card/slide layouts with fixed headers and flexible content zones. Use when building presentation slides, dashboard cards, or any layout with fixed and flexible regions.

Complete game rules and mechanics for Hexlock. Reference this skill when implementing any gameplay feature, validating moves, or understanding win conditions.

Pixel-perfect implementation of Figma designs using Figma MCP for specifications and Chrome DevTools MCP for iterative visual validation. Use this skill when a user provides a Figma link and wants an accurate HTML/CSS implementation. The skill includes formulas for correct positioning, iterative diff-based refinement, and achieves 98%+ pixel accuracy.

Supabase database operations, RLS policies, Edge Functions, and migrations. Use when working with Supabase, PostgreSQL queries, authentication, real-time features, or backend logic.

Create AI-assisted code reviews on GitHub, GitLab, or Forgejo. Use when asked to review a PR/MR, analyze code changes, or provide review feedback.

UX design guidance for user engagement and trust. Use when designing interfaces, improving conversions, building trust signals, implementing ethical engagement patterns, or evaluating UX decisions.

Specialized knowledge for creating, configuring, and managing ayo agents. Use when helping users design agent system prompts, configure agent options, or troubleshoot agent behavior.