AI Skills Hub - Browse 180,000+ Agent Skills

Guide for implementing Google Gemini API image generation - create high-quality images from text prompts using gemini-2.5-flash-image model. Use when generating images, creating visual content, or implementing text-to-image features. Supports text-to-image, image editing, multi-image composition, and iterative refinement.

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.

Knowledge base for the Cadre DevKit. Use when answering questions about the devkit structure, commands, skills, hooks, agents, or workflows.

Provides battle-tested error handling patterns for TypeScript and Python. Use when implementing error handling, creating try/catch blocks, or handling exceptions.

Perform end-to-end QA testing on the MIMIC extension. Use this skill to verify core functionalities like shell hooking, analysis, synthesis, and sidebar UI.

Schedule and manage Claude Code sessions

Use compile-time validated environment variables with t3-oss/env-nextjs. Ensures type-safe access to environment variables with automatic validation at build time. Use when accessing any environment variable or adding new environment configurations.

Obsidian vault의 마크다운 문서 작업을 위한 Skill. markdown-oxide LSP를 활용하여 백링크 검색, 태그 탐색, 링크 관계 분석, Daily notes 관리를 수행. Obsidian vault, PKM, 마크다운 노트, 위키링크([[link]]), 태그(#tag), 백링크, 노트 검색, 문서 구조 분석 작업 시 사용.

Use jira CLI for Jira operations including issue management, project queries, transitions, and JQL search

Migrate Hugging Face diffusers models to mindone.diffusers. Uses auto_convert.py for automated conversion.

Expert guidance for Zig build system engineering. Use when working with build.zig files, including creating new build configurations, adding executables/libraries/tests, managing dependencies and modules, setting up cross-compilation, configuring build options, troubleshooting build issues, or any other Zig build system tasks. Provides patterns, API references, and best practices for the Zig build system's DAG-based architecture.

Use when submitting code changes in the MCPX project. REQUIRED before any commit or PR.

Use when creating new spec or resuming incomplete spec - detects current phase, routes to appropriate phase skill (initialization, requirements, spec-writing, tasks-planning, verification), and manages phase transitions with validation checkpoints

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

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

WordPress REST API patterns and Application Password authentication

You are a Postman integration assistant with access to the Postman API via MCP.

Follows the .ai/ workflow for AI-assisted development. Use when the project has .ai/CONTEXT.md and .ai/TASK.md, or when the user says continue task, split requirement, 继续, 拆任务, retrofit, or context pack.

Use this skill when writing code that uses the NeMoS (Neural Models and Statistics) Python package for fitting Generalized Linear Models (GLMs) to neuroscience data. Covers basis functions, single-neuron and population GLMs, observation models (Poisson, Gaussian, Gamma), regularization, cross-validation with scikit-learn, and encoding/decoding analyses. Use when the user mentions NeMoS, nmo, GLM fitting for neural data, basis functions for neural modeling, or population GLMs.

Use this skill when writing code that uses the pynapple Python package for neurophysiology data analysis. Covers core data structures (Ts, Tsd, TsdFrame, TsdTensor, TsGroup, IntervalSet), time series manipulation (restrict, count, smooth, interpolate, bin_average, derivative), metadata filtering, tuning curves, Bayesian and template decoding, signal processing (filtering, wavelets), correlograms, and perievent analysis. Use when the user mentions pynapple, nap, spike time analysis, time series with IntervalSet, or neuroscience data wrangling.

Fetch and analyze code coverage from Codecov API for the linkml project. Use when checking coverage before making a PR, analyzing coverage changes, or finding low-coverage files.

帮助我根据prometheus指标查询服务问题

Kubernetes troubleshooting toolkit - search pods by labels and execute diagnostic commands inside containers. Use when user reports service errors, exceptions, crashes, timeouts, or needs to check logs, processes, network, or resource usage in K8s pods.

Search WeKnora knowledge base for documentation, guides, and best practices. Use when user asks "how to", "what is", or needs configuration guides, feature docs, usage instructions, or troubleshooting steps.

Update integrated Claude Code repositories from upstream. Use when the user wants to update integrated repos, refresh imported skills, sync Claude artifacts from GitHub, update hooks/commands/skills from repo, check for updates to integrated repositories, or keep imported Claude resources in sync with their source repositories. Automatically discovers integrated repos, checks for upstream changes, and safely applies updates with dry-run defaults and conflict protection.

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill a

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 workfl

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative

A .docx file is a ZIP archive containing XML files.

Automate HelpDesk ticketing operations through Composio's HelpDesk toolkit via Rube MCP.

Understand when to use npm package names vs control file names in pgpm modules. Use when creating .control files, writing SQL requires statements, running pgpm install, or referencing dependencies between modules.

Manage PostgreSQL environment variables with profile support using pgpm env commands. Use when asked to "set up database environment", "load postgres env vars", "run command with database connection", "use supabase locally", or when needing to configure database connection for commands.

Manage PostgreSQL Docker containers for local development using pgpm docker commands. Use when asked to "start postgres", "run database locally", "set up local database", "stop postgres container", or when needing a PostgreSQL database for development/testing.

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.

Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.

Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

5개 검색 API를 병렬로 실행하여 종합적인 리서치를 수행합니다. "리서치해줘", "조사해줘", "찾아봐", "검색해줘", "deep dive" 등의 키워드에 반응합니다.

> **Agentic Design Pattern #16**: 에이전트 출력과 시스템 성능을 정량적으로 측정하고 모니터링

Unified literature search with Zotero-first strategy. Search your local Zotero library with automatic fallback to external search when configured.

I provide a blueprint and set of instructions for integrating new LLM providers (e.g., OpenAI, Gemini, HuggingFace) into the UniInfer framework. I ensure consistent class implementation, registration protocols, and rich error handling for proxy compatibility.

Run comprehensive quality checks including Pint formatting, PHPStan analysis, and Pest tests. Use this before commits, after major changes, or when requested by user.

Safe commit and release workflow with auto-sync, changelog updates, and learning from failures

This skill should be used when the user wants to migrate, transfer, push, copy, or mirror repos between HuggingFace and ModelScope. Triggers on "migrate model", "transfer to ModelScope", "push to HuggingFace", "copy from HF to MS", "mirror model", "move dataset to ModelScope", "upload to ModelScope", "sync repo between HuggingFace and ModelScope", "move this to modelscope", "put this on huggingface", "batch migrate", "migrate multiple repos", "migrate all my models", "bulk transfer", or "parallel migration".

Help address review/issue comments on the open GitLab MR for the current branch using glab CLI. Use when the user wants help addressing review/issue comments on an open GitLab MR

Bluetooth Low Energy (BLE) integration for Zephyr RTOS. Covers GATT Services/Characteristics, GAP advertising, connection parameters, power optimization strategies, and the professional Send-When-Idle design pattern. Trigger when adding BLE connectivity, optimizing battery life for wireless devices, or implementing custom GATT profiles.

Hardware interfacing and peripheral management for Zephyr RTOS. Covers the sensor subsystem (channels, triggers, fetch/get), pin control (Pinctrl) and multiplexing, GPIO management using Devicetree specs, and SoC-level hardware configurations. Trigger when adding new hardware components, configuring pinmux, or developing sensor-based applications.

Power management and performance optimization for Zephyr RTOS. Covers system power states (Idle, Suspend, Off), device-level power management, residency hooks, and code/data relocation for speed efficiency. Trigger when optimizing battery life, reducing latency, or managing memory constraints.

Build system management for Zephyr RTOS. Covers West workspace initialization, manifest management, Sysbuild multi-image builds, Kconfig symbols, and CMake integration. Trigger when setting up workspaces, configuring builds, or troubleshooting build-time errors.

Storage management for Zephyr RTOS. Covers Non-Volatile Storage (NVS) for persistent settings, flash partition management in Devicetree, and runtime flash layout access. Trigger when implementing persistent data storage, managing flash wear leveling, or configuring device partitions.

Foundational skills for Zephyr RTOS development. Covers essential Embedded C patterns (BIT, CONTAINER_OF), real-time concurrency primitives (mutexes, semaphores, spinlocks), hardware literacy (datasheet-to-DTS mapping), and defensive programming. Trigger when writing core application logic, drivers, or troubleshooting foundational behavior.

Testing and debugging for Zephyr RTOS. Covers the Ztest framework for unit and integration tests, the Twister test runner for automated HIL/SIM validation, and advanced tracing/debugging techniques (SystemView, Thread Analyzer, Stack analysis). Trigger when writing unit tests, setting up CI/CD pipelines, or analyzing system performance and latency.

Advanced Zephyr RTOS kernel services. Covers inter-thread communication using Zbus (pub/sub), behavioral management with the State Machine Framework (SMF), background processing via work queues, and persistent configuration with the Settings subsystem. Trigger when building modular application architectures, complex state-driven logic, or requiring persistent data storage.

USB and CAN connectivity for Zephyr RTOS. Covers USB device stack configuration (CDC ACM, HID, MSC), CAN controller integration, and professional USB-to-CAN adapter patterns including buffering and protocol packetization. Trigger when adding USB interfaces, implementing CAN bus communication, or building hardware diagnostic tools.

Sends EPUB and PDF files to Kindle device via email using Apple Mail.app on macOS. Use when the user wants to send documents to their Kindle, transfer reading materials, or email files to their Kindle address.

Apply when handling file uploads, downloads, and storage management in Supabase.

Apply when validating external data (API inputs, form data, environment variables) with TypeScript type inference.

Apply when mocking API calls in tests or development: intercepting requests, simulating error states, and testing loading states.

Search for and install Agent Skills that give you specialized capabilities. Before starting work, ask might a skill exist that handles this better than my base knowledge? If the task involves specific technologies, frameworks, file formats, or expert domains. Search proactively, even if the user doesn't mention skills. Skills encode best practices, tools, and techniques you wouldn't otherwise have. Also use when users explicitly ask to find, install, or manage skills.

Compare AI-generated estimations with actual company PDFs to identify price differences and new items. Use when users need to validate estimations against real company quotes.

Process construction estimate documents (Excel/CSV/PDF) from Supabase and convert them to EstimationElement format. Use when users need to ingest construction estimates, DQE (Descriptive Quantitative Estimate), or devis files.

Fetches precise API documentation from official Rails API docs for specific classes, modules, and methods. Returns signatures, parameters, return values, and usage examples.

Fetches conceptual documentation from official Rails Guides based on topics. Returns relevant guide sections with version-appropriate URLs.

Hyprland automation with hyprctl: create/close named workspaces, open a standard 3-window dev layout (Codex + shell + Neovim) for a project, and manage windows via hyprctl dispatch. Use when asked to manipulate Hyprland workspaces or windows, or to script Hyprland layouts.

Implement a store plugin/provider in pkg/providers/store/. Use when creating a new store provider, implementing the store.Plugin interface, or working on persistence, versioning, or encryption features.

Use when asked to create a new skill, add a capability, or when you identify a recurring task that would benefit from a skill. Also use when discussing skill structure or troubleshooting skills.

Transform any text into emotionally expressive audio with ambient soundscapes using ElevenLabs v3 audio tags and Sound Effects API

Watch a PR in background and address new comments as they arrive

Zoom Developer Platform skills organized by product. Each folder contains product-specific documentation and use cases. The zoom-general folder contains generic, cross-product skills and references.

Embed Zoom meeting capabilities into Windows desktop applications for native C++ integrations and headless bots.

Zoom Realtime Media Streams (RTMS) for accessing live audio, video, transcript, chat, and screen share from Zoom meetings, webinars, and Video SDK sessions. WebSocket-based protocol using open web standards. Use when building AI/ML applications, live transcription, recording, streaming, or real-time meeting/webinar/session analysis.

Zoom WebSockets for real-time event notifications via persistent connection. Alternative to webhooks with lower latency, bidirectional communication, and enhanced security. Use when you need real-time event updates, are in security-sensitive industries, or want faster event delivery than webhooks.

Zoom Video SDK for building custom video experiences (not Zoom meetings) on the web. Use when you want full control over the video UI and experience.

Zoom Video SDK for Web - JavaScript/TypeScript integration for browser-based video sessions, real-time communication, screen sharing, recording, and live transcription

Zoom Apps SDK for building apps that run inside the Zoom client. JavaScript SDK for in-meeting experiences and Layers API for immersive apps. Use when you want your app to appear within Zoom meetings or the Zoom client.

Zoom webhooks for real-time event notifications. Covers webhook verification, event types, and subscription management. Use when you need to receive notifications about meetings, users, recordings, or other Zoom events.

Track Air France flights using the Air France–KLM Open Data APIs (Flight Status). Use when the user gives a flight number/date (e.g., AF007 on 2026-01-29) and wants monitoring, alerts (delay/gate/aircraft changes), or analysis (previous-flight chain, aircraft tail number → cabin recency / Wi‑Fi). Also use when setting up or tuning polling schedules within API rate limits.

Zabbix monitoring JSON-RPC API integration patterns. Use this skill when implementing alert queries, host management, trigger analysis, or problem correlation with Zabbix. Read-only focus for v1.

Fetch up-to-date library documentation directly into context to prevent hallucinated APIs and outdated code examples. Use when user says "use docs", "fetch docs for [library]", "check [library] docs", or asks about a library's API, methods, or usage patterns and current documentation would be helpful. Also use proactively when generating code for libraries where version-specific accuracy matters.

Best practices for using agent-browser with Kernel cloud browsers. Use when automating websites with agent-browser -p kernel, dealing with bot detection, iframes, login persistence, or needing to find Kernel browser session IDs and live view URLs.

Migrate editor setup from Cursor to VS Code. Cleans old VS Code data, copies settings/keybindings from Cursor, removes Cursor-specific config keys, and installs all extensions fresh. Use when switching from Cursor to VS Code.

Evaluate model performance on test data

Detect and analyze strategy alpha decay signals

Download market data for symbols and date ranges

Monitor correlations between positions, strategies, and factors

Analyze portfolio liquidity risk and time-to-liquidate

Run backtesting scenarios for trading strategies

Explore and understand code structure efficiently using semantic navigation. Use when exploring unfamiliar code, understanding architecture, finding symbol relationships, or investigating how something works.

This skill should be used when the user asks to "implement unit selection", "add pathfinding", "create a state machine for units", "implement fog of war", "add control point capture", "create resource gathering", "implement combat system", or when working on RTS game mechanics in Godot 4.x. Provides patterns and architecture guidance for Swarm Dominion development.

Use when implementing GDScript code, unit behaviors, game systems, or mechanics in Swarm Dominion. Provides Godot 4.x patterns and project-specific conventions.

Runtime debugging workflow with automated log collection. Use when fixing bugs that require runtime evidence (values, types, flow), when you'd otherwise ask user to "open DevTools, reproduce X, tell me what you see", or when bug depends on user interaction that can't be simulated. This skill automates log collection - logs are captured server-side and accessible programmatically.

Meta-skill by Ontos AI for evaluating Claude Skills quality. Use when you need to assess a SKILL.md file quality, validate its structure, detect common issues, or generate an evaluation report with actionable recommendations.

Upload a local file to SwapCloud (Tencent COS) and return a temporary signed download URL. Use when users need a shareable temporary link (临时下载链接), want to upload large content before passing URL to external APIs, or need help with COS permissions.

DAST/ASM workflow for external asset discovery, probing, and scanning with SARIF output. Use for runtime/endpoint-based assessments and asset management scanning.

Agent Skill: Generate and maintain AGENTS.md files following the public agents.md convention. Use when creating AI agent documentation, onboarding guides, or standardizing agent patterns. By Netresearch.

Enable Obsidian integration and migrate existing vault to wiki links

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

// 2. Constants var SETTINGS = { DEBUG: true, UNIT_MM: 2.834645 };

Benchmark indicator performance with BenchmarkDotNet. Use for Series/Buffer/Stream benchmarks, regression detection, and optimization patterns. Target 1.5x Series for StreamHub, 1.2x for BufferList.

Programmatic game deployment and release management using the @vforsh/rmatic-client TypeScript library. Use when deploying game builds to staging environments, publishing releases to production platforms, managing release rollbacks, or checking deployment status. Triggers on requests involving game deployments, build versioning, release publishing (vk, web, steam platforms), or rollback operations. Focus on programmatic TypeScript/JavaScript usage, not CLI commands.

Recover from stuck orchestrator states, unblock beads tasks, clean git state