AI Skills Hub - Browse 180,000+ Agent Skills

Use when implementing ANY computer vision feature - image analysis, object detection, pose detection, person segmentation, subject lifting, hand/body pose tracking.

Express-inspired Go web framework built on fasthttp.

Build desktop apps with Rust backend and WebView frontend.

Module organization, Dependency Injection patterns, and Project Structure.

Distributed cron jobs and locking patterns.

Thread management, Executor framework, CompletableFuture, synchronization, and virtual threads.

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use PROACTIVELY for any Cloudflare development task.

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

View markdown files with calm, book-like reading experience via HTTP server. Use for long-form content, documentation preview, novel reading, report viewing, distraction-free reading.

Use when writing DAX, modeling Power BI data, or debugging Power BI formulas. Star schema, measures, optimization.

使用豆包 Seedance API 将静态图片转换为动态 GIF。从 scripts/key 文件读取 API 密钥，接收图片路径和动画描述作为参数，自动生成高质量 GIF 动图。使用 ffmpeg 两步调色板法优化颜色质量。

将 v2ray/clash 订阅或 URI 转换为 Sing-box 完整配置。

Create and maintain a single living Markdown plan file for TDD work using a strict checklist template. Use when a task needs a structured plan with TEST/IMPLEMENT/VERIFY steps, progress logging, and pause/resume protocol.

This skill teaches how to effectively analyze codebases using the codebase-analyzer MCP tools. Use when exploring new repositories, understanding architecture, detecting patterns, or tracing data flow.

This skill guides adding new MCP tools to the codebase-analyzer server. Use when extending the analyzer with new capabilities like new analysis types, query tools, or integrations.

Skills for searching ESS-DIVE datasets via the Dataset API

Bun runtime and package manager patterns. Applies to package management, Bun.file, Bun.write, Bun.Glob, bun test, scripts, workspaces, or migrating from npm/yarn/pnpm.

Run TypeScript exercises or validate markdown code blocks with hash-based caching. Only re-runs if content has changed. Use for testing book exercises, validating code examples, or running the full validation suite.

Generate and maintain high-quality GitHub Copilot instruction files (.github/copilot-instructions.md). Use this skill when asked to create copilot instructions, generate copilot-instructions.md, set up copilot config, or update copilot instructions for any project or tech stack.

Guide for performing Mendelian Randomization (MR) analysis using GWAS summary statistics. Use for: two-sample MR, instrument selection, data harmonization, and sensitivity analysis.

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

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

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

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Ozzo to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

使用实验性的产出物工作流启动一个新的 OpenSpec 变更。当用户想要通过结构化的分步方法创建新功能、修复或修改时使用。

Build BI dashboards from databases. Use when creating dashboards, charts, or analytics pages with Next.js + shadcn/ui + Recharts + Prisma.

Convert a Markdown file into a nicely formatted Google Doc and open it in the browser. Use when the user wants to create a Google Doc from a .md file, share markdown content as a Google Doc, or invoke /md2docs. Handles headings, bold, italic, inline code, fenced code blocks, tables, lists, links, horizontal rules, and mermaid diagrams.

Creates XAML unit tests for GitHub issues in the Controls.Xaml.UnitTests project. Tests XAML parsing, compilation (XamlC), and source generation. Use when testing XAML-specific behavior, not UI interactions.

Attempts ONE alternative fix for a bug, tests it empirically, and reports results. ALWAYS explores a DIFFERENT approach from existing PR fixes. Use when CI or an agent needs to try independent fix alternatives. Invoke with problem description, test command, target files, and optional hints.

Verifies UI tests catch the bug. Supports two modes - verify failure only (test creation) or full verification (test + fix validation).

Creates UI tests for a GitHub issue and verifies they reproduce the bug. Iterates until tests actually fail (proving they catch the issue). Use when PR lacks tests or tests need to be created for an issue.

Build-less ESM frontends that run directly in the browser without bundlers. Use this skill when creating static frontends, SPAs without build tools, prototypes, or when the user explicitly wants no Vite/Webpack/bundler. Covers import maps, CDN imports, cache-busting, hash routing, and performance patterns.

Review a PR (or current branch if no PR number given) and post comments on GitHub

Implement ChatKit widget embed in Docusaurus sites and define secure token/session flow between UI and FastAPI backend. Use when building RAG chatbots for textbooks, implementing chat interfaces in documentation sites, adding selected text capture functionality, setting up token-based authentication for chat widgets, or deploying chat features to GitHub Pages. Handles both normal (full-book query) and selection-only (query selected text) modes.

List the current running model, capabilities, and validate tools/skills. There is no function named 'diagnostics'; use the exec tool to run: node /app/scripts/diagnostics/cli.js --section <section>.

Generate slide images and final PDF/PPTX from v2 styled prompts (prompts/styled/*.md), storing intermediates in artifacts/<deck>/work/. Use when the user asks to render/generate/export slides from a Styled PROMPT into images/PDF/PPTX.

Generates professional slide deck images from content. Creates outlines with style instructions, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck", "slide deck", or "PPT".

Convert unstructured Markdown material/notes into a structured multi-slide SPEC (specs/*.md) by analyzing headings, bullets, and paragraphs, then dividing content into per-slide sections. Use when asked to 'turn notes into a SPEC', 'split this markdown into slides/pages', 'structure unstructured material into specs/<deck>.md', or 'organize content into per-page slide format'.

Use when about to claim work is complete, fixed, or passing — before committing or creating PRs. Evidence before assertions, always.

Use when executing a bead within ACFS infrastructure — starting, working on, or completing a bead task. Enforces proper ACFS integration.

This command should be used to investigate codebase patterns, frameworks, and existing implementations before planning. Third stage of the Kimchi planning pipeline. Produces .kimchi/RESEARCH.md.

This command should be used to convert the final plan into standalone bead YAML task specifications for multi-agent execution. Ninth stage of the Kimchi planning pipeline. Produces .beads/ directory.

Discord reaction-based selection handler for OpenClaw. Bridges the gap between Discord emoji reactions and agent turns by forwarding selections as triggering messages. Use when you need interactive emoji voting/selection on Discord (e.g., recipe selection, approval workflows, polls). Requires a separate Discord bot running alongside OpenClaw.

This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, etc.) when working with code in this repository.

This example demonstrates how to use the **Sub_LogError** reusable subflow to implement structured error logging in your flows. Structured error logging provides visibility into flow failures and accelerates debugging in production environments.

Use when ready to publish a new version. Triggers on "release", "publish", "ship it", or version bump requests. Runs quality checks, bumps version, tags, and creates GitHub release.

Analyze YouTube videos by extracting and processing transcripts. Triggers when user provides a YouTube URL (youtube.com, youtu.be) or asks to analyze, summarize, or extract insights from a YouTube video. Supports both existing captions and local AI transcription via whisper-cpp. Useful for learning from Dreamforce talks, Trail Together sessions, and Salesforce tutorials.

Generates index.md files listing .md documentation. Pure navigation — what exists and where. No code files. Triggers on "index", "catalog", "build index".

Coordinates perceiving and thinking skills to solve complex problems. Iterates between gathering information (perceiving) and reasoning about it (thinking) until a confident conclusion is reached. Use proactively for multi-step analysis, diagnosis, decisions, or any problem requiring both information gathering and reasoning.

Transform Skill_Seekers from creating **passive documentation dumps** into **active, intelligent skills** that load documentation on-demand. This eliminates context bloat (300k → 5-10k per query) while maintaining full access to complete documentation.

External Services in Salesforce auto-generate Apex classes from OpenAPI specifications, providing type-safe API integrations without manual HTTP code.

When and how to use Salesforce Bulk API operations.

If a user tells you there is a problem with the project, review the `target/run_results.json` file to identify which resources failed and why.

This skill automates the capture of high-quality screenshots for MicroSim visualizations using Chrome headless mode. Use this skill when working with MicroSims that need preview images for social media sharing, documentation, or quality assessment. The skill handles JavaScript-heavy visualizations that require proper rendering time and external CDN resources.

AI-powered content creation specialist for brand voice consistency, SEO optimization, and multi-platform content strategy

Skriv, omskriv eller redigér tekst i Kaspers personlige skrivestil. Brug når brugeren beder om at skrive "som Kasper" eller ønsker stil-efterligning/tilpasning baseret på konkrete skriveeksempler.

Detailed OAuth flow patterns, configuration examples, and implementation guidance for the sf-connected-apps skill.

Skills are folders of instructions that give AI agents new capabilities. This guide helps you create, test, and share a skill with minimal ceremony.

Sage is a WordPress theme framework by Roots that provides modern development practices including Blade templates, dependency management with Composer, and build tools with Vite/Bud.

Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.

✅ The `/skills` command is working using the shell script fallback ⚠️ Using ~1,000 tokens per call 🎯 Goal: Reduce to **0 tokens** using MCP

Creates and manages Salesforce Connected Apps and External Client Apps with 120-point scoring. Use when configuring OAuth flows, creating connected apps, setting up JWT bearer auth, or managing API access policies.

Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.

Added a "help" feature to the book-installer skill that displays a comprehensive catalog of MkDocs features that can be added to intelligent textbooks. When users ask "what does book-installer do?" or request specific features like "add math support", the skill now routes to a new `mkdocs-features.md` reference file.

If you are prompted to fix a bug, start by reviewing the logs and artifacts from the most recent dbt invocation. See `scripts/review_run_results.md` for an example.

This document covers conventions and patterns for working on the `skill-eval` CLI tool.

Add a skill to the project with validation and README generation

GitHub generates heading anchors by: 1. Lowercasing the heading text 2. Replacing spaces with `-` 3. Removing special characters 4. Stripping emojis (each emoji leaves a `-` in its place) 5. Appending `-N` suffix for duplicate anchors (where N = 1, 2, 3...)

The `/skills` slash command in Claude Code was slow and consumed thousands of tokens because it required: 1. Reading multiple SKILL.md files 2. Parsing YAML frontmatter 3. Formatting output 4. All processing done by Claude's LLM

Create API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'.

This skill installs a complete Claude Code skill tracking system using hooks to automatically log skill usage, execution duration, token usage, and user prompts for later analysis. Use this skill when setting up activity tracking in a Claude Code project to identify patterns, monitor costs, and discover opportunities for new skills.

Technology stack evaluation and comparison with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, evaluating technology stacks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.

Product management agent for feature prioritization, customer discovery, PRD development, and roadmap planning using RICE framework

This document describes the architecture and design decisions behind the skills-lister MCP server.

Reference mindsets are philosophical foundations for simplicity. They explain *why* less is more, giving agents deeper calibration beyond the mechanical checkpoints.

Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists.

Comprehensive SOQL relationship patterns for complex data retrieval.

Design or refactor skills by separating deterministic and non-deterministic steps. Use when creating or improving skills, especially to move repeatable workflows into scripts/ and update SKILL.md to call them.

Using anonymous Apex for complex data operations.

This guide explains how to use the standards library for consistent quality across all skills and agents.

Get up and running with MCP servers in 5 minutes.

Generates and reviews Salesforce Apex code with 2025 best practices and 150-point scoring. Use when writing Apex classes, triggers, test classes, batch jobs, or reviewing existing Apex code for bulkification, security, and SOLID principles.

Create `plugins/plugin-name/.claude-plugin/plugin.json`:

Pause session and save current work state for later resume

Systematically trace bugs backward through call stack to find original trigger

Run verification commands and confirm output before claiming success

No description available

Build production Rust CLIs with Clap: subcommands, config layering, validation, exit codes, shell completions, and testable command surfaces

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

Extract actionable items from messy meeting transcripts or notes.

Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.

The most popular container images for homelab, maintained by LinuxServer.io.

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

Caddy is the easiest reverse proxy with automatic HTTPS.

Text-to-speech and speech-to-text using fal.ai audio models. Use when the user requests "Convert text to speech", "Transcribe audio", "Generate voice", "Speech to text", "TTS", "STT", or similar audio tasks.

Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT models with parameters, values, and constraints for valid scenarios using pairwise testing. Outputs the PICT model, markdown table of test cases, and expected results.