AI Skills Hub - Browse 180,000+ Agent Skills

化學資訊學工具包，用於細粒度分子控制。SMILES/SDF 解析、描述子（MW、LogP、TPSA）、指紋、子結構搜尋、2D/3D 生成、相似性、反應。對於使用更簡單介面的標準工作流程，請使用 datamol（RDKit 的封裝器）。使用 rdkit 進行進階控制、自訂清理、專門演算法。

Security audit with fix recommendations for JS/TS projects

Generate and improve code quality scores for JS/TS projects

Send a message to a running agent

Add, remove, and manage Panopticon-managed projects

同步当前仓库的 skills 目录到多个预设的本地目录，以保持能力与文件一致。用于需要批量同步/更新本仓库技能到默认目录、避免手动复制或遗漏更新时使用。

Validates all URLs (internal relative links and external URLs) in markdown files. Use when adding new content, after making changes, or when asked to check/audit links.

Before submitting code or creating a Pull Request, when about to claim that work is complete, fixed, or passed, you must run verification commands and confirm the output results before making any success claims; evidence must appear before any assertions---

Validate Claude Skill structure and organization against official specifications. Use when developing, reviewing, or debugging Skills to ensure they follow correct file structure, naming conventions, and directory organization.

小红书旅行规划助手。爬取小红书搜索结果，按类别（交通、住宿、饮食、优惠等）筛选内容，生成思维导图。当用户需要从小红书收集旅行攻略信息时使用。

Use when testing Fusionaly features, checking for regressions, or verifying releases - supports OSS and Pro, install scripts, E2E tests, and feature testing

Sync AI coding sessions from 14 tools (Claude Code, Codex, Cursor, Aider, Cline, Gemini CLI, Continue, Copilot, Roo Code, Windsurf, Zed AI, Amp, OpenCode, OpenRouter) to Obsidian vault as markdown notes. Use when user wants to backup, export, or sync their AI chat sessions to Obsidian, set up automatic syncing, check sync status, or troubleshoot sync issues. Handles secret redaction automatically. Cross-platform (macOS, Linux, Windows).

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Generate a plan for how an agent should accomplish a complex coding task. Use when a user asks for a plan, and optionally when they want to save, find, read, update, or delete plan files in $CODEX_HOME/plans (default ~/.codex/plans).

Check and update GitHub Actions versions. Use when creating, modifying, or reviewing GitHub Actions workflow files (.github/workflows/*.yml), or when asked to ensure actions are up to date.

Build and deploy Spectro Cloud Palette Edge clusters using Appliance Mode. Covers CanvOS builds, provider images, ISOs, content bundles, 2-node deployments, and CI/CD integration patterns.

Create and manage Spectro Cloud Palette Edge clusters. Covers edge-native deployments including agent mode, appliance mode, and 2-node HA. Both API and Terraform.

Use this when smoke tests fail (binary/web assets, Playwright setup, server lifecycle, ports, env vars).

Search the JLCPCB electronic components database (~7 million parts) for hardware/electronics projects. Use when the user needs to: (1) Find electronic components (resistors, capacitors, inductors, ICs, connectors, diodes, transistors, MOSFETs, op-amps, microcontrollers, sensors, LEDs, etc.), (2) Look up specific part numbers, LCSC numbers (C-prefix), or manufacturer part numbers, (3) Find alternatives or equivalents for components, (4) Check component availability and stock at JLCPCB/LCSC, (5) Get component specifications (package type, footprint, description), (6) Search for parts for PCB assembly (PCBA) projects, (7) Find SMD or through-hole components, (8) Look up voltage regulators (LDO, linear, switching), audio jacks, connectors, or any other electronic parts. Keywords: JLCPCB, LCSC, electronic components, PCB parts, SMT assembly, BOM, bill of materials, component sourcing.

Reference documents and schema for generating custom game plans in the AI Learning App. Use when implementing the game plan generator feature (Stage 4 of the user flow), building the generation prompt, working on plan presentation UI, or debugging generation quality issues.

Interact with running Nodel instances via REST API - check node status, view console logs, invoke actions, debug nodes, manage deployments. Use when making curl commands, API calls, or troubleshooting Nodel.

Install Hanzo Dev skills into $HANZO_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).

Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.

Syncs skill metadata to AGENTS.md Auto-invoke sections. Trigger: When updating skill metadata (metadata.scope/metadata.auto_invoke), regenerating Auto-invoke tables, or running ./skills/skill-sync/assets/sync.sh (including --dry-run/--scope).

Show full session token usage, costs, TLDR savings, and hook activity

Create, edit, and analyze PowerPoint presentations. Use when working with .pptx files for text extraction, slide creation, or presentation editing.

Dynamic agent composition and management system. USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available traits, agent voices. Handles custom agent creation, personality assignment, voice mapping, and parallel agent orchestration.

Cross-platform image compression skill. Converts images to WebP by default with PNG-to-PNG support. Uses system tools (sips, cwebp, ImageMagick) with Sharp fallback.

Generate iOS App Icon assets from a source image. Creates all required sizes for iOS apps and generates the proper Contents.json for Xcode's Assets.xcassets. Use when you have a 1024x1024 source icon and need to prepare it for an iOS app release.

DO NOT invoke unless explicitly instructed. Core guidelines for orchestrating tasks with subagents.

Advanced patterns for Hono-based Electron IPC including CQRS, Zod validation, error handling, and reactive data with RxJS. Use when implementing complex IPC patterns or needing guidance on architecture decisions.

Generate detailed implementation plans for complex tasks. Creates comprehensive strategic plans in Markdown format with objectives, step-by-step implementation tasks using checkbox format, verification criteria, risk assessments, and alternative approaches. All plans MUST be validated using the included validation script. Use when users need thorough analysis and structured planning before implementation, when breaking down complex features into actionable steps, or when they explicitly ask for a plan, roadmap, or strategy. Strictly planning-focused with no code modifications.

Conduct comprehensive academic research using OpenAlex, PDF extraction, paper search MCPs, and web search. Always produces comprehensive reports with 5+ evidence cards covering conflicting ideas and best approaches. Integrates academic papers (high weight) and non-academic sources (blogs, docs - lower weight but valuable for SOTA). Use when: (1) Researching software architecture patterns, (2) Finding academic papers on technical topics, (3) Conducting literature reviews, (4) Analyzing research papers for evidence-based decisions, (5) Building evidence cards from papers, (6) Finding related works and citations, or (7) When you need grounded, paper-backed technical recommendations. Triggers: research, find papers, literature review, evidence-based, academic research, compare approaches, what does research say, find studies on, search for papers about.

Manage stacked PRs with Graphite CLI (gt) instead of git push/gh pr create. Auto-detects Graphite repos and blocks conflicting commands with helpful alternatives. Use when: (1) About to run git push or gh pr create in a Graphite repo, (2) Creating a new branch for a feature, (3) Submitting code for review, (4) Large changes that should be split into reviewable chunks, (5) Hook blocks your git command and suggests gt equivalent. NOT for: repos not initialized with Graphite, git add/commit/status/log. Triggers: git push blocked, gh pr create blocked, create branch, submit PR, stacked PRs, split large PR, gt create, gt submit, graphite workflow.

Add error boundaries to routes for handling 404s, 403s, and unexpected errors. Use when implementing error handling for routes or when asked to handle not found pages.

Comprehensive guide for building Agent Skills according to agentskills.io specification. Use when developers need to create, structure, or validate skills that follow the Agent Skills standard format and best practices.

Build mithril-cache for torch.compile caching. Use when implementing content-addressable storage, cache keys, eviction, or framework hooks.

Workflow for propagating penguiflow library changes to test agents. Use when modifying library code and need to test changes in test_generation agents.

Netlify API を使用したコードを書く際に使用。ZIPデプロイ、サイト作成、ky/fflate/zod を使った実装パターンを提供。

Product UI/UX design assistant for this repo. Use when Codex should propose UI/UX improvements, redesign flows/screens, define a lightweight design system (tokens/components/states), and produce actionable handoff artifacts (specs, backlog items, tasks) aligned with the `logics/*` workflow.

Write conventional commit messages with type, scope, and subject when the user wants to commit changes or save work.

Update PowerPoint templates with new content while preserving formatting, structure, and layout. Uses semantic analysis to understand template structure and intelligently map new content (from meeting transcripts, summaries, reports) to appropriate shapes. Use when the user asks to update a PowerPoint presentation, fill in a PPTX template, update slides with new data, or refresh a presentation with new content. Handles business reports, sales decks, status updates, and other template-based presentations.

通过 git-ai 的 MCP 工具检视/检索代码仓。用户要“找实现/定位符号/语义搜索/读取文件/重建索引/MCP 相关问题”时调用。

Provides detailed file statistics including lines, size, and modification time when user asks for file info or stats

Generate shareable http(s) links that redirect into Obsidian via the link-to-obsidian service. Use when sending Obsidian note links in chat apps (Discord/WhatsApp) that can’t open obsidian:// URLs, or when converting obsidian://open links to http(s) format.

Debug progression issues: locked content, missing badges, streak resets. Use when investigating why phase is locked, badge not awarded, or streak was lost.

Commit changes and monitor the deploy workflow. Use when pushing code and wanting to watch CI/CD status in real-time.

Structured escalation with evidence. Surfaces blocking issues for human decision, referencing the Manifest hierarchy.

Plan and execute releases with semantic versioning and bracket-based freezing. Use when: "how do I release", "bump the version", "write the changelog", "what version comes next", "release the plugin", or managing scope creep in monorepos. Prevents version thrashing; supports single projects, monorepos, and multi-component systems.

Specification management - creating, organizing, and maintaining spec items with acceptance criteria and traits.

Create new Claude Code skills for this project. Use when user asks to create a skill, add agent capabilities, or build reusable workflows for the codebase.

Generates protocol-based error/crash monitoring with swappable providers (Sentry, Crashlytics). Use when user wants to add crash reporting, error tracking, or production monitoring.

Sync .env files from git root repository to worktrees. Use when asked to sync env, copy env, environment file, or when working in a git worktree that is missing a .env file. Automatically detects missing .env in worktrees.

Claude Skill用SKILL.md生成AIエージェント。アーキタイプ駆動設計により、 勝利条件から逆算した高品質プロンプトを生成する。 **Trigger:** 以下のいずれかで起動 - 「〇〇用のスキル/プロンプトを作成」 - 「このプロンプトを診断/改善」 - 「〇〇AIエージェントを構築」

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When the Assistant 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

Guide you through creating a single Red Hat Showroom workshop module from reference materials (URLs, files, docs, or text) with business storytelling and proper AsciiDoc formatting.

Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Find and analyze stale TODO, FIXME, HACK comments in codebases using

Browser automation via Playwright MCP. Use for verification, browsing, web scraping, testing, screenshots, and all browser interactions.

Internal logic and data flow philosophy (The 5 Laws of Elegant Defense). Apply to backend, hooks, state management, and any code where functionality matters.

Manage Git worktrees for concurrent local development. Creates worktrees at ~/.worktrees/REPO/BRANCH. Wrapper for the `wt` CLI.

Work with Claude Code configuration at global (~/.claude) or project (.claude/) level. Use when editing settings.json (permissions, hooks, statusline, model), managing MCP servers, or creating agents/commands/skills. Determines context automatically and provides guidance on global vs project placement to avoid duplication.

SDD仕様書（overview.md, specification.md, technical-details.md, phase計画書）の構造・フォーマットガイド。以下の状況で使用する: (1) 仕様書を作成・編集する時、テンプレートを参照したい時 (2) 「**不明**」マーク、複数案提示、調査項目状態の書き方を確認する時 (3) specs/{taskname}/ のファイル構成を理解したい時 (4) Phase計画書（tasks/phase{N}-*.md）のフォーマットを確認する時 各ファイルのテンプレートはassets/templates/に配置。

TypeScriptで型安全なClaude Code Hooksを作成するためのガイド。cc-hooks-tsライブラリを使用してフックを実装する際に使用する。(1) Claude Code用の新しいhookを作成する時、(2) 既存のhookをTypeScriptで書き直す時、(3) PreToolUse/PostToolUse/SessionStart等のイベントフックを実装する時、(4) plugin.jsonにhooksを設定する時

Maintain the Claude Code plugin marketplace - create plugins, add skills, bump versions, update registry. Use when creating new plugins, adding skills/agents/commands to plugins, updating versions, or managing the marketplace registry.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Better Auth JWT verification for Python/FastAPI backends. Use when integrating Python APIs with a Better Auth TypeScript server via JWT tokens. Covers JWKS verification, FastAPI dependencies, SQLModel/SQLAlchemy integration, and protected routes.

TS/JS 程式碼智能重構工具。重命名、移動檔案、清理 dead code、修改函式簽章時自動更新所有引用。

Use PROACTIVELY for JMH benchmarks in this Spark protobuf project. Handles sbt commands, always cleans before benchmarking, saves output to /tmp logs, and uses log-reader agent to parse results.

Atlassian Server CLI (Jira/Confluence/Bitbucket). This skill should be used when working with Jira issues, Confluence page operations, Bitbucket pull requests, or any Atlassian Server tasks. Triggers on: issue tracking, wiki pages, PR management, CQL queries.

Pick and run the smallest correct validation step (checks → focused Jest by path → broader suites). Use whenever you modify code and need confidence quickly.

Use when modifying MCP servers that touch repo memory (especially docs-memory). Includes protocol guardrails, validation ladder, and how to store new capabilities as Skills so future agents don’t re-learn painful details. Triggers: docs-memory, mcp-server.js, tools/list, tools/call, stdio, headerless, JSON-RPC, protocol.

Create or repair SVG diagrams without overlapping text/shapes. Use when shipping new SVGs, editing WLILO-styled diagrams, or when collision checks report overlaps/clipping.

Autonomous UI inspection using a dual channel: (1) visual screenshots via Playwright MCP tools, (2) numeric layout metrics via Puppeteer scripts. Includes server --check standardization so agents can start/stop reliably.

Use repo lab experiments (src/ui/lab) to answer jsgui3 “how should we do this?” questions, then distill the validated result into durable docs + Skills.

Use when you need the WLILO look (White Leather + Industrial Luxury Obsidian) across HTML, SVG, and jsgui3. Covers token schema, palette, and how to write back design learnings so other agents reuse them. Triggers: wlilo, white leather, industrial luxury, obsidian, design system, palette, theme tokens, diagram styling.

Understand and debug how jsgui3 SSR markup becomes activated client-side, including persisted fields (data-jsgui-fields) and ctrl_fields (data-jsgui-ctrl-fields), and where to patch/plugin.

Use when you need SVGs with selectable/customisable appearance: multiple palettes (WLILO / Obsidian / light), consistent typography, and repeatable agent-friendly pipelines. Triggers: svg theme, tokens, palette, WLILO, obsidian, design system, dark mode, diagram styling.

Convert Claude Code exported txt files to clean Markdown format and save to Obsidian vault. Use when the user wants to convert an export file to markdown.

Download ERA5 climate reanalysis data from the Copernicus Climate Data Store using cdsapi. Use this skill when users request ERA5 data, climate forcing data, meteorological variables, or need to download atmospheric/land surface data for ecosystem modeling, climate analysis, or model validation.

Use when testing Nango syncs locally - runs dry-run command with proper parameters for integration testing without affecting production data

Use renovate-dryrun to test Renovate configuration locally. Use this skill when debugging or validating renovate.json5 changes.

Use `a gh issue-agent` to view and edit GitHub Issues. Use this skill when working with GitHub Issues - viewing issue content, editing issue body/title/labels, or adding/editing comments.

Deploy to Railway and debug deployment issues. Use when deploying the application, checking deployment status, or debugging deployment failures.

Use when about to claim work is complete, fixed, passing, or done - requires running verification commands and confirming output before making any success claims. Evidence before assertions.

Create CVA + DaisyUI components following Iridium patterns. Use when asked to create UI components, buttons, inputs, cards, modals, alerts, or any reusable UI element.

Add PostHog feature flags for gradual rollouts, A/B tests, or beta features. Use when implementing feature toggles, experiments, or canary releases.

Blocks destructive git and filesystem commands before execution. Prevents accidental loss of uncommitted work from git checkout --, git reset --hard, rm -rf, and similar destructive operations. Works as a Claude Code PreToolUse hook with fail-open semantics.

Best practices for creating Claude Code slash commands. Use this skill when creating, editing, or improving custom slash commands for Claude Code. Covers frontmatter configuration, dynamic features ($ARGUMENTS, bash execution, file references), command patterns (git workflows, multi-agent orchestration, code review), and helps decide when to use slash commands vs skills vs subagents.

Expert-level Vercel AI SDK v5 patterns for production chatbots. Use for: (1) Chat persistence with Drizzle/PostgreSQL, (2) Generative UI with typed tool parts, (3) Human-in-the-loop tool confirmations, (4) Custom data streaming with reconciliation, (5) Anthropic provider with extended thinking/reasoning, (6) Type-safe message metadata with token tracking. Covers advanced patterns only - assumes basic AI SDK knowledge. NOT for AI SDK v6.

Toolkit for creating and managing server clusters on Hetzner Cloud using Terraform. Use this skill when users request deploying VMs, creating test infrastructure, or setting up server clusters on Hetzner Cloud. The skill provides Terraform templates optimized for network testing with strict firewall rules, public and private network interfaces, and support for ZeroTier VPN.

Guide for implementing LionFire workspace documents with Blazor MVVM patterns, including ObservableDataView component usage, workspace-scoped service injection, and reactive persistence. Use this skill when creating Blazor pages for workspace documents, fixing workspace service scoping issues, or implementing list/detail views with ObservableReader/Writer.

Explore denmark statistics subject hierarchy for all fact tables

Complete Redis installation guide for all platforms - Linux, macOS, Docker, and cloud deployments with configuration templates

Master Redis Strings - SET, GET, INCR, DECR, atomic counters, binary-safe operations, and caching patterns

Fetch and cluster PR comments

Fix F821 undefined name errors for optional dependencies using TYPE_CHECKING