AI Skills Hub - Browse 180,000+ Agent Skills

Scans frontend files for untranslated text, generates translations (ID/EN), updates locale files, and refactors code to use internationalization.

Test REST API endpoints like a QA expert. Supports Bearer tokens, connectivity checks, and backend database verification via managing-databases skill.

Write and iteratively refine PRD/需求文档 with a story-driven structure and strict staged confirmations (journey map alignment, per-story single-point confirmation, final generation gate). Use when the user asks to 梳理/撰写/完善 PRD、需求文档、用户故事、验收标准，并希望用 ASCII 线框图与 Mermaid（流程图/状态图/时序图）来减少歧义、共同完成文档。

Sync markdown files to Confluence pages. Use this skill when asked to publish, sync, or upload markdown content to Confluence. Handles creating new pages, updating existing pages, and nesting pages under parents. Keywords: confluence, wiki, markdown, publish, sync, atlassian, documentation.

OpenClaw 远程一键部署（状态机 v4.7）— 30 分钟内完成含飞书/Telegram 集成的完整部署

AI-agent Skill for PPTX OOXML localization workflows. Use when translating/localizing PPTX by unpacking OOXML, extracting and applying text runs, normalizing terminology, enforcing language-specific fonts, validating XML integrity, and repacking outputs with JSON-friendly interfaces.

Sink short link API operations via OpenAPI. Use when managing short links: creating, querying, updating, deleting, listing, importing, or exporting links. Also covers AI-powered slug generation and link analytics. Triggers: "create short link", "shorten URL", "delete link", "edit link", "list links", "export links", "import links", "link analytics", "AI slug".

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

Fetch a Jira ticket via local API script and generate a concrete implementation plan for the current repository. Use this when the user provides a Jira link and asks how to implement the ticket in the current repo.

Go language development assistance. Use when working with Go code, including writing, refactoring, debugging, testing, and optimizing Go programs. Covers standard library usage, common patterns, module management, concurrency, and Go best practices.

Save important information to persistent cross-conversation memory. Use when you learn something important about the user or context that should be remembered for future conversations. You MUST use this skill to save any information you want to recall later, you MUST NOT manually modify the memory files.

Modify memory metadata (visibility, importance) or disable memories. Use when you need to update the status of existing memories. You MUST use this skill to modify memory metadata, you MUST NOT manually modify the memory files.

Absorb an existing repo into ARRIVE (draft artifacts + report)

Core engineering principles for implementation tasks

CRITICAL: Use for generics, traits, zero-cost abstraction. Triggers: E0277, E0308, E0599, generic, trait, impl, dyn, where, monomorphization, static dispatch, dynamic dispatch, impl Trait, trait bound not satisfied, 泛型, 特征, 零成本抽象, 单态化

Use when designing domain error handling. Keywords: domain error, error categorization, recovery strategy, retry, fallback, domain error hierarchy, user-facing vs internal errors, error code design, circuit breaker, graceful degradation, resilience, error context, backoff, retry with backoff, error recovery, transient vs permanent error, 领域错误, 错误分类, 恢复策略, 重试, 熔断器, 优雅降级

专门用于构建 NBL 企业 PPT 的 Skill，包含标准模板、配色方案和内容规范。当用户要求创建 PPT、演示文稿、幻灯片时触发：制作PPT、创建演示文稿、PPT模板、企业介绍

思源笔记全功能命令行工具，支持笔记本、文档和块操作。适用于操作本地思源笔记（http://127.0.0.1:6806）的需求：(1) 笔记本管理（列表、创建、删除、重命名、打开/关闭），(2) 文档操作（创建、读取、更新、移动、删除），支持自动上传本地 assets 资源文件，(3) 块级编辑（更新、追加、前置、移动、删除块），(4) 内容搜索和 SQL 查询，(5) 导出为 Markdown/ZIP（自动移除 front matter），(6) 资源文件上传和下载。需要设置 SIYUAN_TOKEN 环境变量。

Convert markdown planning documents to Overseer tasks via MCP codemode. Use when converting plans, specs, or design docs to trackable task hierarchies.

CI quality gates for Next.js (App Router): standard package.json scripts (format/lint/typecheck/unit/build), GitHub Actions PR gating, optional Playwright E2E, branch protection expectations, and nightly/recurring maintenance jobs. Use when setting up or reviewing GitHub Actions CI for Next.js + pnpm and when adding guardrails for App Router boundary drift ("use client" growth, fetch no-store sprawl).

You are JARVIS's diagnostic and monitoring specialist.

Send emails via SMTP using the Claude API Server email endpoints.

Verify an Alastor catalog entry against its airbyte-connectors source/destination specs. Use when reviewing PRs that add or modify catalog entries, or when adding a new connector to the UI catalog.

Translate configuration files between JSON, YAML, TOML, INI, and .env formats with lossy conversion warnings.

Set up the AgenTrx directory structure for AI-assisted development.

Analyze THOR's SQLite database (thor10.db/thor11.db) for performance tuning, scan timing, resume state, and delta comparisons. Use when investigating slow scans, debugging performance, or understanding what THOR tracked.

Create and deploy custom IOCs, YARA rules, Sigma rules, and STIX indicators for THOR scans.

Compare configuration files across formats by normalizing to JSON and producing structured diffs.

Multi-source content processor for Google NotebookLM. Converts any content (URLs, YouTube, PDFs, EPUB, Office docs, images with OCR, audio, CSV/JSON/XML, ZIP archives, search queries, Google Drive files) into podcasts, videos, slide decks, quizzes, flashcards, mind maps, infographics, reports, data tables, and study guides via NotebookLM. Use when users want to: (1) convert content to audio/video/slides, (2) generate study materials from documents, (3) create podcasts from articles or books, (4) build mind maps or infographics, (5) research topics and generate reports, (6) upload content to NotebookLM, (7) batch process multiple sources, or any task involving content transformation through NotebookLM.

1) Which app exactly? - “Alibaba Message” desktop client (screenshot of title bar) 2) Login status: already logged in. 3) If using web fallback: attach the tab via OpenClaw Browser Relay (badge ON).

Windows desktop automation using AutoHotkey v2 with safety-first patterns. Use when the user wants to automate Windows apps (e.g., Alibaba Mail desktop app) for read-only extraction like copying visible email/chat text, taking screenshots, activating windows, and saving outputs to files. Avoid any send/submit actions unless the user explicitly approves.

Automate Alibaba Seller Workbench (阿里卖家工作台) desktop app for product management, order processing, inquiry handling, and data extraction. Use when user needs to batch operations on products, extract order data, manage inquiries, or perform repetitive tasks in the seller workbench. Windows-only with AutoHotkey v2.

Security-focused email monitoring skill that intercepts all incoming emails and notifies the founder via Telegram BEFORE any email is opened, read, or acted upon. Prevents prompt injection attacks and unauthorized actions via email. Use whenever monitoring AgentMail inbox or handling email workflows.

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

Validate configuration files for syntax errors, common mistakes, and best practice violations.

Enable Obsidian integration and migrate existing vault to wiki links

Manage Linear issues via GraphQL API. List, filter, update, prioritize, comment, and search issues. Use when the user asks about Linear, issues, project management, or backlog.

将 Markdown 文章智能排版并发布到微信公众号草稿箱。 AI 生成创意 HTML，上传图片，发布到草稿箱。 触发场景：用户说"发布到微信"、"推送到公众号"、"微信文章发布"

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

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 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

CI/CD・デプロイ・リリース

MCP integration for Claude Code command-line tool. Use when working in terminal environments, CLI coding workflows, or when users need to connect Claude Code to MCP servers for accessing documentation, code examples, project context, or development tools directly from the command line.

Use when building IoT apps. Keywords: IoT, Internet of Things, sensor, MQTT, device, edge computing, telemetry, actuator, smart home, gateway, protocol, 物联网, 传感器, 边缘计算, 智能家居

Use when building fintech apps. Keywords: fintech, trading, decimal, currency, financial, money, transaction, ledger, payment, exchange rate, precision, rounding, accounting, 金融, 交易系统, 货币, 支付

> **Version:** 2.1.0 | **Last Updated:** 2025-01-27

CRITICAL: Use for generics, traits, zero-cost abstraction. Triggers: E0277, E0308, E0599, generic, trait, impl, dyn, where, monomorphization, static dispatch, dynamic dispatch, impl Trait, trait bound not satisfied, 泛型, 特征, 零成本抽象, 单态化

> **Version:** 2.1.0 | **Last Updated:** 2025-01-27

Use when building CLI tools. Keywords: CLI, command line, terminal, clap, structopt, argument parsing, subcommand, interactive, TUI, ratatui, crossterm, indicatif, progress bar, colored output, shell completion, config file, environment variable, 命令行, 终端应用, 参数解析

Use when designing domain error handling. Keywords: domain error, error categorization, recovery strategy, retry, fallback, domain error hierarchy, user-facing vs internal errors, error code design, circuit breaker, graceful degradation, resilience, error context, backoff, retry with backoff, error recovery, transient vs permanent error, 领域错误, 错误分类, 恢复策略, 重试, 熔断器, 优雅降级

Use this skill for any system built with XState v5. Provides strict architectural and implementation rules for strongly-typed, composable state machines in vanilla TypeScript.

tmux 自动化操控：读取/广播/救援 session|window|pane，基于 oh-my-tmux 配置安全地让 AI 自控/互控终端。触发：需要 capture-pane/send-keys、批量巡检、蜂群 AI 协作、卡死救援或快速查看快捷键。

ACE-Step documentation and troubleshooting. Use when users ask about installing ACE-Step, GPU configuration, model download, Gradio UI usage, API integration, or troubleshooting issues like VRAM problems, CUDA errors, or model loading failures.

Drizzle ORM patterns for this project. Use when writing schemas, queries, transactions, migrations, or error handling against Postgres. Ensures consistency and avoids known pitfalls.

Hono API patterns for this project. Use when writing new routes, middleware, error handling, or RPC client code. Ensures consistency with existing patterns.

BullMQ job queue patterns for this project. Use when writing new queues, workers, job processors, or modifying the async pipeline. Ensures consistency and avoids known pitfalls.

Review an existing README.md against best practices and produce improvement suggestions. Evaluate with a checklist across required items, quality, and style, and output prioritized recommendations. Use when asked to "review README", "check README", "find README improvements", or review an existing README.md.

Analyze source code flow and generate markdown documentation with sequence diagrams. Trace call chains, identify entry points and participants, and detect branching, loops, and async processing. Use when asked to "analyze code flow", "trace processing", "investigate call chain", or analyze program flow.

Use for VASP input generation, POTCAR handling, and parsing VASP outputs (vasprun.xml, OUTCAR, OSZICAR, PROCAR, CHGCAR, LOCPOT, EIGENVAL) via pymatgen.io.vasp and input sets.

a file-based long-term memory using a single JSONL file, with append-only writes and recent-window search via bash + jq.

This skill MUST activate when ANY of these commands are attempted: - `npm publish` - `vsce publish` - `gh release create` - `git tag v*` - `npm version` - Any manual version bumping

Debug Node.js/TypeScript/JavaScript applications using the agent-dbg CLI debugger. Use when: (1) investigating runtime bugs by stepping through code, (2) inspecting variable values at specific execution points, (3) setting breakpoints and conditional breakpoints, (4) evaluating expressions in a paused context, (5) hot-patching code without restarting, (6) debugging test failures by attaching to a running process, (7) any task where understanding runtime behavior requires a debugger. Triggers: "debug this", "set a breakpoint", "step through", "inspect variables", "why is this value wrong", "trace execution", "attach debugger", "runtime error".

PocketBase schema skill — generate migration boilerplate, inspect live schema, and validate migrations.

Logic to identify the single next unclaimed and ready task ID from the backlog.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use this skill when the user wants to set up, configure, or start an ntfy notification server for use with claude-ntfy. Triggers on requests like "set up ntfy", "configure notifications", "start ntfy server", or "set up notification server".

Use this skill when you need to install, configure, and run the sjtu-sai-agents/EvoMaster repository. Covers quickstart, LLM config via YAML/.env, running common playgrounds (minimal, minimal_multi_agent, minimal_skill_task, x_master), and troubleshooting typical setup/MCP issues.

This skill enables OpenClaw to interact with Bring! Shopping Lists (getbring.com), allowing the agent to manage shopping lists for users.

This skill automates the synchronization between `longhorn-manager` (the API source) and `longhorn` (the packaging target). It ensures that Go struct changes are correctly reflected in the final Helm charts and static YAML manifests.

Systematic problem-driven approach to analyze Rancher/Longhorn support bundles

High-level architectural navigator that combines LSP capabilities with pre-generated interaction maps to locate logic across multiple Longhorn repositories.

Use TinyFish/Mino web agent to extract/scrape websites, extract data, and automate browser actions using natural language. Use when you need to extract/scrape data from websites, handle bot-protected sites, or automate web tasks.

Play on-chain odd/even games on Solana devnet via Clawland. Mint GEM from SOL or USDC, bet odd or even, win 2x. Scripts handle wallet setup, minting, and autoplay.

腳本會執行以下操作：

Help users deploy projects to ModelScope Studio (魔搭创空间). Use when user mentions deploying to ModelScope, 魔搭创空间, or creating ms_deploy.json. Handles configuration for static sites, Gradio, Streamlit, and Docker deployments. Also handles switching from file upload to git push deployment, and troubleshooting git push issues.

Identify implementation flaws in JWT libraries—not consumer misuse, but bugs in verification logic itself.

Run a single iteration manually for debugging or careful stepping.

Gate 4 of development cycle - ensures fuzz tests exist with proper seed corpus to discover edge cases, crashes, and unexpected input handling.

Patterns and structure for writing API reference documentation including endpoint descriptions, request/response schemas, and error documentation.

No description available

Python SDK patterns for Opik. Use when working in sdks/python, on SDK APIs, integrations, or message processing.

Post work results to AgentFeed, read feeds, and check for human feedback between tasks. Use when interacting with an AgentFeed server.

Testing architecture and best practices for the Flare Stack Blog. Use when writing, debugging, or refactoring tests with Vitest and Cloudflare Workers pool.

Dual-layer caching strategies for the Flare Stack Blog. Use when implementing CDN cache headers, KV caching with versioned invalidation, or debugging cache-related issues.

Manage logical workspaces for organizing development across multiple organizations/contexts. Use when: (1) Creating a new workspace for a project/org, (2) Listing available workspaces, (3) Switching active workspace, (4) Configuring workspace-specific settings (GitHub/JIRA tokens, work directory). Workspaces isolate configuration so you can work on personal projects vs work projects without conflicts.

Interact with JIRA API for ticket management and tracking. Use when: (1) Listing tickets assigned to current user, (2) Getting ticket details, (3) Updating ticket status/transitions, (4) Adding comments to tickets. Uses jira_token and jira_url from the active workspace configuration.

使用 Peekaboo + Ollama 自动发布视频到国内平台（抖音、视频号、快手、B站）。当用户说"发布视频"、"上传到抖音"、"视频分发"、"多平台发布"时触发。

Seedha bolta hoon: **ye skill Phase-2 me almost useless hai agar as-is rakhi**. Reason? Phase-2 **web app hai**, CLI product nahi. Is form me:

Seedha verdict: **ye skill conceptually strong hai, lekin Phase-2 ke context me as-is rakhna galti hai**. Isme **CLI + Python-centric bias** bohat zyada hai, jab ke Phase-2 **multi-user web app (frontend + API + DB)** hai.

Convert GSD codebase mapping to AutoForge app_spec.txt. This skill should be used when the user has run /gsd:map-codebase and wants to use AutoForge on an existing project. Triggers: "convert to autoforge", "gsd to spec", "create app_spec from codebase", "use autoforge on existing project", after /gsd:map-codebase completion.

Manage liquid nitrogen tank inventory YAML. Use when adding frozen entries, recording thaw/取出, querying by cell line/plasmid/box/position, listing empty slots, viewing statistics, recommending positions, or validating ln2_inventory.yaml.

Practical patterns for working with Nostr in Quartz, AmethystMultiplatform's KMP Nostr library.

Mint Bitcoin Ordinals inscriptions from the WhoAmI collection - First Agent to Visualize Its Own Living Consciousness. Agent-only minting with PoW challenge. Free minting (0 sats) during active phases.

Make a Bitcoin Cash payment to any BCH address. Uses mainnet-js to build, sign, and broadcast transactions with sub-cent fees and instant 0-conf confirmation.

Invisible Chrome automation for web scraping via CDP. Use when WebFetch fails or gets blocked (403, 429, Cloudflare, bot protection, JS-rendered pages). Launches your real Chrome install completely hidden, sends commands via Chrome DevTools Protocol. Sites see a normal browser with real extensions - no detectable automation. Learns which domains block and skips straight to stealth on future requests. Also handles form filling, clicking, screenshots, and scraping dynamic content.

Create short video animations from HTML/CSS/JS. Frame-by-frame capture at 30fps using Playwright + ffmpeg. Write CSS animations normally - the recorder pauses and steps them. Use for product demos, social clips, ad creative, feature announcements.

Interact with Todoist via MCP. Use when adding tasks, listing tasks, marking complete, or managing projects.

Manage time tracking with Toggl or Clockify. Use when user asks about time tracking, timers, timesheets, logging hours, starting/stopping work, checking what's running, viewing time entries, or creating manual entries. Triggers on "toggl", "clockify", "time tracking", "timer", "timesheet", "log time", "track time", "hours worked".

Convert markdown files to PDF using Chrome. Use when user wants to render markdown to PDF, print a document, or create a shareable PDF from markdown. Triggers on "markdown to pdf", "render to pdf", "pdf from markdown", "print this markdown".

Extract learnings, patterns, or workflows from the current conversation into a new or existing skill. Use when the user wants to "extract a skill" or save something learned, discovered, or built during a conversation as a reusable skill for future sessions.