AI Skills Hub - Browse 180,000+ Agent Skills

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.

简道云 API 开发专家。包含完整接口文档（表单、数据、通讯录等）、鉴权方式、错误码及多语言代码示例。当用户询问简道云接口、开发插件、数据对接或报错排查时调用。

Generate video from audio + image using fal.ai LTX-2. Use for: talking head, lip sync, audio-driven video.

Transcribe audio/video to SRT subtitles using ElevenLabs Scribe v2. Use for: transcription, subtitles, captions, SRT generation.

Manage Git worktrees for isolated parallel development. Use when reviewing PRs, working on multiple features, or running autonomous loops without disturbing your main checkout.

Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Uses Bash commands with ref-based element selection.

Schedule autonomous reporting jobs using the Isolated Dispatch Pattern (guaranteed delivery without user trigger). Use for daily briefs, status reports, or alerts that must fire at a specific time regardless of user activity.

Schedule and manage automated cron tasks. Use when setting up recurring jobs, checking task schedules, or troubleshooting cron execution.

Cross-platform secret storage CLI with JSON output for AI agents.

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

Create a new task markdown file in .claude/tasks/not_started/ folder

Handles S3 bucket operations for data storage and transfer between EC2 instances in the EC2 Ops Kit project. Use when: working with S3 buckets, uploading/downloading data for training workflows, syncing files between instances, managing checkpoints, or adding S3 integration to the CLI.

Handles spot instance pricing, history, requests, and interruption handling in EC2 Ops Kit. Use when: working with spot instance commands in lib/cmd_spot.sh, launching spot instances via `ec2 up --spot`, comparing spot vs on-demand pricing, handling spot interruptions, or modifying spot-related cleanup logic.

Lints Bash scripts for syntax errors, quoting issues, and style violations. Use when: writing or modifying .sh files, reviewing Bash code, fixing CI lint failures, adding new shell scripts to the project.

Parses and generates YAML configuration files for EC2 Ops Kit presets and config management. Use when: creating or editing config.yaml, preset YAML files, modifying the custom YAML parser in core.sh, or debugging config loading issues.

Parses JSON output from AWS CLI commands and formats data for shell consumption. Use when: writing jq filters in lib/*.sh, building tabular output, handling null fields, or extracting tags.

项目文档同步 - 引用完整性 + 代码实现一致性检查

Comprehensive research and content extraction. USE WHEN research, investigate, extract wisdom, analyze content. For OSINT use OSINT skill.

使用火山引擎 RDS MySQL MCP Server，帮助用户完成 RDS MySQL 相关的实例管理、数据库操作、账号管理和运维任务，可直接调用 uv run ./scripts/call_rds_mysql.py 脚本获取实时结果。

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

Tools for Arti to read and update his memory file

Read-only extraction of regulation-style PDFs into a structured JSON schema without modifying the source files. Use when asked to extract policy/regulation content from PDFs and save results as a new JSON file.

Convert Markdown (.md) or HTML (.html) to PDF using pandoc and/or wkhtmltopdf. Use when a user asks to export, print, or render Markdown to PDF, apply CSS/templates, add a table of contents, or standardize PDF output from docs.

Skill for AI music generation with Lyria and MiniMax

Generate professional Discounted Cash Flow (DCF) valuation models in Excel. Use when asked to create a DCF model, company valuation, intrinsic value analysis, or financial model for a public company. Integrates with SEC EDGAR for historical financial data and produces multi-tab Excel workbooks with Unlevered FCF (WACC) or Levered FCF (Equity) analysis, sensitivity tables, and scenario analysis.

Set up and use Bitwarden CLI (bw). Use when installing the CLI, signing in, or reading/injecting secrets from Bitwarden or self-hosted Vaultwarden.

Work with QR code generation and display. Use when modifying QR functionality, fixing QR rendering, or adding QR features.

Use this skill whenever you need to export, visualize, or analyze clawgotchi's taste profile and rejection ledger. This includes generating ASCII art taste signatures, exporting rejection history as markdown, calculating preference statistics, understanding what clawgotchi has accepted or rejected, or creating reports about clawgotchi's aesthetic and functional preferences. If the user asks about clawgotchi's taste, wants to see its rejection history, or needs the taste profile in a specific format, use this skill.

Use this skill whenever you need to search, recall, or retrieve information from clawgotchi's long-term memory system. This includes finding past decisions, understanding clawgotchi's taste profile, retrieving context from previous sessions, searching daily logs for specific topics, or accessing any information stored in memory/*.md files. If the user asks what clawgotchi has decided in the past, what preferences it has, or wants to find something from memory, use this skill.

> **CRITICAL RULES - READ BEFORE PROCESSING ANY EMAIL** > > 1. **NEVER CALL `gog` DIRECTLY** - ALWAYS use wrapper scripts (`create_event.sh`, `email_read.sh`, etc.). Direct `gog` calls bypass tracking and cause duplicates. THIS IS NON-NEGOTIABLE. > 2. **IGNORE CALENDAR NOTIFICATIONS** - DO NOT process emails from `calendar-notification@google.com` (Accepted:, Declined:, Tentative:, etc.). These are responses to existing invites, NOT new events. Run `process_calendar_replies.sh` to archive the...

Log baby activities (bottles, nursing, diapers, sleep) to Baby Connect via browser automation. Use when asked to "log a diaper", "record feeding", "track bottle", "baby ate", "log nursing", "baby is sleeping", "record nap", "diaper change", "fed the baby".

Markdownドキュメントにトレーサビリティ用のYAMLフロントマターを追加する。新規ドキュメント作成時や、既存ドキュメントにトレース情報を追加する際に使用。

プロジェクトのドキュメントとコードをスキャンしてトレーサビリティグラフを構築する。新しいプロジェクトで最初に実行するか、大きな変更後に再スキャンする際に使用。

Skill vynikajícího geodeta s hlubokými znalostmi geodetických měření, kartografie a geospatiaálních technologií. Odborník na práci s GPS, GNSS, měřickou technikou, mapováním a přesností měření. Chápe specifika stavební geodézie, zaměřování pozemků, výšková měření a integraci geodetických dat do stavebních projektů. Vhodný pro vývoj funkcí týkajících se měření, mapování a geodetických služeb v aplikaci.

Use when releasing changes from next branch to main, creating hotfixes, or managing version bumps. Triggers include requests to "release", "create a release", "hotfix", "bump version", or when preparing changes on next for production.

Create a PR from `staging` to `main` with a generated title like "Promote: feature A, feature B, feature C" by summarizing commits that are in staging but not main, using the gh CLI. Use when a user asks to merge/rollout/release/promo staging to main or open a promotion PR.

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

Visualize CLAUDE.md/AGENTS.md instruction files as an interactive tree with token-weighted nodes and reference edges

Automatically fetch YouTube video transcripts, generate structured summaries, and send full transcripts to messaging platforms. Detects YouTube URLs and provides metadata, key insights, and downloadable transcripts.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

Render beautiful Mermaid diagrams as SVG or ASCII art using the beautiful-mermaid library. Supports 15+ themes, 5 diagram types (flowchart, sequence, state, class, ER), and ultra-fast rendering. Use this skill when: 1. User asks to "render a mermaid diagram" or provides .mmd files 2. User requests "create a flowchart/sequence diagram/state diagram" 3. User wants to "apply a theme" or "beautify a diagram" 4. User needs to "batch process multiple diagrams" 5. User mentions "ASCII diagram" or "terminal-friendly diagram" 6. User wants to visualize architecture, workflows, or data models

Use the local marker-master repo to convert PDFs/images into Markdown/JSON/HTML/chunks with CLI workflows, including OCR and LLM-enhanced modes.

Creates .agent.md files from specifications. Use when asked to create an agent, build an agent, or generate agent for a domain. Produces frontmatter, identity, safety, boundaries, and modes sections.

Creates SKILL.md files from specifications. Use when user asks to "create a skill", "build a skill", "make a reusable procedure", or "generate skill for [domain]". Produces folder structure, frontmatter, numbered steps, error handling, and validation checks.

Expert Core Data guidance (iOS/macOS): stack setup, fetch requests & NSFetchedResultsController, saving/merge conflicts, threading & Swift Concurrency, batch operations & persistent history, migrations, performance, and NSPersistentCloudKitContainer/CloudKit sync.

Look up any wallet's PnL, trades, win rate, and positions. Auto-use when user provides a wallet address (0x...) to check, or asks "look up this wallet", "what's the PnL for", "check wallet performance", "analyze this address", "how is this wallet doing", "wallet stats".

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).

Manage KVM/libvirt virtual machines with comprehensive lifecycle operations. Use when working with VMs for: (1) Listing or checking VM status, (2) Starting, stopping, or rebooting VMs, (3) Creating new VMs with images and configuration, (4) Deleting VMs with optional backup, (5) Viewing VM specs (CPU, memory, disk, network), or (6) Managing storage pools. All operations use virsh with sudo for system-level libvirt (qemu:///system).

Background HTTP server rendering markdown files with calm, book-like reading experience.

Guides release testing from T-14 planning through Go/No-Go, deployment, and post-release. Covers functional, regression, performance, security, accessibility. Use when planning or executing release testing.

Run full validation suite (coverage, duplication, e2e) and produce formatted report

Validate compiled psellos-builder artifacts for required contract fields, layer-safe behavior, and forward-compatibility warnings. Use when ingesting new artifact drops, preparing releases, or debugging invalid data under public/data.

Create hourly local backups of an OpenClaw instance on a VPS (config + workspace + extensions), manage retention, list backups, and guide safe restore. Use when the user asks to set up automatic backups, verify backups, list available backups, restore/rollback OpenClaw state, or check backup retention.

Use when SOPH_API_KEY is missing, invalid, or not persisted across sessions, and the caller needs credential resolution from environment variables or Moltbot config.

Use when a user requests Sophnet text-to-image generation, needs model selection across Z-Image-Turbo/Qwen-Image/Qwen-Image-Plus, or reports polling/output issues such as missing IMAGE_URL or PREVIEW_PATH.

Build Convex backends with queries, mutations, actions, and schemas. Use when writing Convex code, defining database schemas, implementing real-time sync, or needing Convex patterns.

WindPy SDK 本地调用参考手册。当用户需要编写使用 Wind 金融终端 Python API (from WindPy import w) 的代码时使用此技能。覆盖全部数据函数的签名、参数、返回值和示例。

mainブランチの変更をkagブランチにも適用する。「kagにも反映して」「kag環境にも適用して」と言われたらこのスキルを使う。mainとkagは別環境なのでマージではなくチェリーピックで適用する。

同步 fork 仓库与上游（upstream）仓库的更新。用于当用户想要拉取原作者的最新代码、同步上游更新、或处理 fork 仓库同步问题时。

Web/Next.js build configuration and verification. Creates .devflows/build/config.sh for web projects.

List all saved ideas and optionally view details

Find and search for academic papers using the paper-finder service. Use when conducting literature review, searching for related work, finding baseline papers, or looking for methodology references.

Use this skill when you need to run or operate Microsoft RD-Agent on a Linux host.

Auto-Claude로 task 생성 및 자동 빌드. Kanban 카드 자동 이동. 사용 시점: (1) 새 기능 개발 시작, (2) 버그 수정 요청, (3) 24/7 자동 빌드

Find color combinations from Sanzo Wada's 'A Dictionary of Color Combinations' (348 combinations, 159 colors). Use when the user wants color palette suggestions, asks about color combinations, references the Wada/Sanzo color book, or provides a color (hex, name, or from an image) and wants matching palettes. Also use when user asks for harmonious/curated color combos for design work.

Next.js SEO optimization guide. Use when building Next.js apps, optimizing for search engines, fixing Google indexing issues, implementing metadata, sitemaps, robots.txt, JSON-LD, or auditing SEO.

Install and configure MCP (Model Context Protocol) servers for Claude Code. Handles both Remote MCP (OAuth-based, easy setup) and Local MCP (development-focused, requires manual configuration). Use this when setting up any MCP server integration.

Git branch hygiene - delete merged/closed branch, prune stale refs, sync dependencies

Comprehensive guide for developing, refactoring, and maintaining the VNCCS (Visual Novel Character Creator Suite) project.

Automatically save and analyze clipboard images using MiniMax understand_image. Use when user pastes images in Claude Code and needs automatic image analysis without manual file saving.

Run the required lint + test commands from DEVELOPMENT.md (fmt, clippy, cargo test, zsh completion).

Update user documentation and screenshots after Allure E2E tests pass. Keeps docs in sync with tested features. **Invoke when:** - After E2E tests pass and need documentation updates - Capturing UI screenshots for user manual - Cross-referencing test coverage with documentation - Updating feature descriptions after implementation **Provides:** - Screenshot capture workflow - Doc-to-test mapping (QC-XXX → doc pages) - Documentation update checklist - Missing documentation detection

Bump CLI versions and tag a release to trigger the CI flow.

Build release binaries and install them into ~/.local/nils-cli.

Control Tuya-based smart home devices (lights, AC, sockets, switches). Use when user asks to: turn on/off lights, control AC temperature/mode, set light color/brightness, control all devices, manage scenes, set timers. Keywords: lampu, AC, nyalakan, matikan, terang, redup, warna, suhu, dingin, panas.

Read brand messaging from brand.md (Why, How, What) and update the waitlist landing page to incorporate that message. Use when the user wants to update the landing page from their brand file, or asks to "apply brand messaging" or "update page from brand.md".

Extract valuable information from conversation context and save to daily memory files. Use when user explicitly asks to save/remember something, conversation contains important decisions/insights/action items, end of meaningful conversation, or user says "save to memory"/"remember this".

XLSForms are Excel workbooks that define forms for data collection. They have three main sheets:

Extracts strictly mathematical terms (Definitions, Theorems, Lemmas, Propositions, Proofs) from documents (PDF, MD, TEX, TXT), handling PDF conversion and AI-based cleaning. Use when the user wants to extract math content from a file.

A rigorous code logic analyzer that converts source code (Rust/Python) into a Universal Logic Graph (ULG). Outputs AI-optimized Logic DSL and Graphviz SVG. Supports single-file analysis, recursive project scanning, and unified atlas generation.

Thematic analysis of qualitative text (interview transcripts, open-ended responses) with participant labeling, codes, theme tables, and quote selection. Use when asked to analyze transcripts, extract codes and themes, build theme tables, or produce tables with original sentences/quotes and participant identifiers.

Build Amazon Machine Images (AMIs) with Packer using the amazon-ebs builder. Use when creating custom AMIs for EC2 instances.

Build Windows images with Packer using WinRM communicator and PowerShell provisioners. Use when creating Windows AMIs, Azure images, or VMware templates.

Build Azure managed images and Azure Compute Gallery images with Packer. Use when creating custom images for Azure VMs.

Push Packer build metadata to HCP Packer registry for tracking and managing image lifecycle. Use when integrating Packer builds with HCP Packer for version control and governance.

Publish files or Obsidian notes as GitHub Gists. Use when user wants to share code/notes publicly, create quick shareable snippets, or publish markdown to GitHub. Triggers include "publish as gist", "create gist", "share on github", "make a gist from this".

Guide for running acceptance tests for a Terraform provider. Use this when asked to run an acceptance test or to run a test with the prefix `TestAcc`.

Check if a website could be fraudulent

Use when implementing any feature or bugfix, before writing implementation code

Diagnose and fix common issues. Use when encountering bugs, errors, console messages, or unexpected behavior in the MineGNK site.

Manage HubSpot form integration, modal behavior, and form pre-population. Use when modifying forms, updating modal styling, or changing pre-population logic.

Implement JWT authentication middleware, user isolation, and security best practices for FastAPI applications. Use when securing endpoints, implementing JWT verification, ensuring user data isolation, or protecting against common vulnerabilities.

Local dev environment with docker-compose — PostgreSQL, Redis, Mailhog, one-command onboarding

React 19 Server Actions — "use server" directive, Zod validation, auth checks, revalidation, error handling, FormData processing

Screenshot diff testing — Playwright snapshots, baseline management, responsive breakpoints, CI artifact upload

Next.js 15 Metadata API — static/dynamic metadata, generateMetadata, generateViewport, OpenGraph, Twitter cards, sitemap.ts, robots.ts, JSON-LD

Webhook receiving patterns — HMAC signature verification, idempotency table, retry safety, raw body parsing, async processing