Community Skills & Frameworks for AI Agent Builders | AI Agent Skills

f

Generate customizable widget plugins for the prompts.chat feed system

f

Translate The Interactive Book of Prompting chapters and UI strings to a new language

lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

lobehub

db-migrations is a skill for automating database migrations using AI agents, enabling multi-agent collaboration and effortless workflow design.

lobehub

Testing guide using Vitest. Use when writing tests (.test.ts, .test.tsx), fixing failing tests, improving test coverage, or debugging test issues. Triggers on test creation, test debugging, mock setup

lobehub

Zustand state management guide. Use when working with store code (src/store/**), implementing actions, managing state, or creating slices. Triggers on Zustand store development, state management quest

lobehub

Data fetching architecture guide using Service layer + Zustand Store + SWR. Use when implementing data fetching, creating services, working with store hooks, or migrating from useEffect. Triggers on d

lobehub

Guide for adding keyboard shortcuts. Use when implementing new hotkeys, registering shortcuts, or working with keyboard interactions. Triggers on hotkey implementation or keyboard shortcut tasks.

openai

Babysit a GitHub pull request after creation by continuously polling CI checks/workflow runs, new review comments, and mergeability state until the PR is ready to merge (or merged/closed). Diagnose fa

affaan-m

prompt-optimizer is a skill that refines and optimizes user prompts for AI agents, ensuring effective communication and improved outcomes.

affaan-m

api-design is a skill for creating well-structured REST APIs, following best practices for resource naming, HTTP methods, and error handling.

affaan-m

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

affaan-m

click-path-audit is a behavioural flow audit skill that traces every interactive touchpoint to find bugs where functions individually work but cancel each other out.

affaan-m

Codebase-onboarding is a skill that analyzes an unfamiliar codebase and generates a structured onboarding guide with architecture maps, key entry points, and conventions.

affaan-m

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.

affaan-m

C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices.

affaan-m

Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.

affaan-m

django-verification is a skill that automates the verification loop for Django projects, including migrations, linting, tests, security scans, and deployment readiness checks.

affaan-m

foundation-models-on-device is a skill that integrates Apple's on-device language model into apps using the FoundationModels framework for text generation, structured output, and custom tool calling.

affaan-m

kotlin-testing is a set of testing patterns for Kotlin, utilizing Kotest, MockK, and Kover for reliable and maintainable tests.

affaan-m

laravel-tdd is a test-driven development skill for Laravel applications, leveraging PHPUnit and Pest for unit, feature, and integration testing.

affaan-m

Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

affaan-m

nutrient-document-processing is a skill that enables automated document processing, including conversion, extraction, and redaction, using the Nutrient DWS API.

affaan-m

perl-security is a skill that enhances Perl application security through taint mode, input validation, and secure coding practices.

affaan-m

project-guidelines-example is a skill template for managing project architecture, file structure, and deployment workflows using AI-powered tools.

affaan-m

Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.

affaan-m

Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.

affaan-m

Rust-testing is a set of testing patterns including unit tests, integration tests, async testing, property-based testing, and mocking for reliable Rust code

affaan-m

santa-method is a multi-agent adversarial verification framework that enhances code review accuracy by using two independent agents with no shared context.

affaan-m

search-first is a research-before-coding workflow AI agent skill that invokes the researcher agent to find existing solutions before writing custom code.

affaan-m

Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.

affaan-m

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

affaan-m

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, bui

affaan-m

Translate visa application documents (images) to English and create a bilingual PDF with original and translation

affaan-m

# Canary Watch — Post-Deploy Monitoring ## When to Use - After deploying to production or staging - After merging a risky PR - When you want to verify a fix actually fixed it - Continuous monitoring during a launch window - After dependency upgrades ## How It Works Monitors a deployed URL for regressions. Runs in a loop until stopped or until the watch window expires. ### What It Watches ``` 1. HTTP Status — is the page returning 200? 2. Console Errors — new errors that weren't there befor

affaan-m

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

affaan-m

cpp-testing is a specialized AI agent skill for automating C++ test workflows using GoogleTest and CMake.

affaan-m

Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.

affaan-m

flutter-dart-code-review is a comprehensive AI agent skill for reviewing Flutter/Dart applications, ensuring best practices and optimal performance.

affaan-m

Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.

affaan-m

laravel-patterns is a skill that provides Laravel architecture patterns, routing, controllers, Eloquent ORM, service layers, queues, events, caching, and API resources for production apps.

affaan-m

rules-distill is a skill that scans installed skills, extracts cross-cutting principles, and distills them into rules for efficient coding workflows.

affaan-m

safety-guard is a protective AI agent skill that intercepts and prevents destructive operations, providing a safe coding environment for developers.

affaan-m

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

affaan-m

springboot-verification is a skill that automates the verification loop for Spring Boot projects, including build, static analysis, tests, and security scans.

affaan-m

customs-trade-compliance is a specialized AI agent skill that automates customs operations, including tariff classification, duty calculations, and denied party screening, to ensure compliant and cost-effective international trade.

affaan-m

energy-procurement is a skill that utilizes AI to optimize energy procurement for commercial and industrial consumers, analyzing tariffs, managing demand charges, and negotiating contracts.

affaan-m

inventory-demand-planning is a skill that utilizes AI to forecast demand, calculate safety stock, and generate purchase orders, helping retailers optimize inventory levels and minimize costs.

affaan-m

production-scheduling is a skill that enables optimized production planning and scheduling, using technologies such as ERP, finite-capacity scheduling tools, and MES to maximize throughput and meet customer delivery commitments.

affaan-m

# Benchmark — Performance Baseline & Regression Detection ## When to Use - Before and after a PR to measure performance impact - Setting up performance baselines for a project - When users report "it feels slow" - Before a launch — ensure you meet performance targets - Comparing your stack against alternatives ## How It Works ### Mode 1: Page Performance Measures real browser metrics via browser MCP: ``` 1. Navigate to each target URL 2. Measure Core Web Vitals: - LCP (Largest Contentfu

affaan-m

Blueprint is a construction plan generator that creates step-by-step plans from one-line objectives for coding agents

affaan-m

# Browser QA — Automated Visual Testing & Interaction ## When to Use - After deploying a feature to staging/preview - When you need to verify UI behavior across pages - Before shipping — confirm layouts, forms, interactions actually work - When reviewing PRs that touch frontend code - Accessibility audits and responsive testing ## How It Works Uses the browser automation MCP (claude-in-chrome, Playwright, or Puppeteer) to interact with live pages like a real user. ### Phase 1: Smoke Test ``

affaan-m

coding-standards is a skill that provides guidelines for writing clean, readable, and maintainable code in TypeScript, JavaScript, and related frameworks.

affaan-m

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

affaan-m

Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.

affaan-m

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

affaan-m

exa-search is a neural search AI agent skill that enables efficient research via Exa MCP for web content, code examples, company intel, and people lookup.

affaan-m

kotlin-exposed-patterns is a skill that provides comprehensive patterns for database access with JetBrains Exposed ORM, including DSL queries, DAO, transactions, and production-ready configuration.

affaan-m

iOS 26 Liquid Glass design system — dynamic glass material with blur, reflection, and interactive morphing for SwiftUI, UIKit, and WidgetKit.

affaan-m

nextjs-turbopack is a skill that utilizes Turbopack for incremental bundling, enabling faster development and production optimization in Next.js 16+ applications.

affaan-m

Modern Perl 5.36+ idioms, best practices, and conventions for building robust, maintainable Perl applications.

affaan-m

plankton-code-quality is a write-time code quality enforcement system for Claude Code, utilizing auto-formatting, linting, and Claude-powered fixes.

affaan-m

Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.

affaan-m

tdd-workflow is a test-driven development skill that ensures all code development follows TDD principles with 80%+ test coverage.

affaan-m

Verification Loop is an AI tool that verifies the quality and reliability of Claude Code sessions

affaan-m

Interactive agent picker for composing and dispatching parallel teams

affaan-m

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

affaan-m

bun-runtime is a fast all-in-one JavaScript runtime and toolkit, providing a drop-in Node-compatible runtime, package manager, bundler, and test runner.

affaan-m

Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.

affaan-m

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

affaan-m

Deep research is a skill that produces thorough, cited research reports from multiple web sources using firecrawl and exa MCP tools.

affaan-m

Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.

affaan-m

Idiomatic Kotlin patterns, best practices, and conventions for building robust, efficient, and maintainable Kotlin applications with coroutines, null safety, and DSL builders.

affaan-m

# Product Lens — Think Before You Build ## When to Use - Before starting any feature — validate the "why" - Weekly product review — are we building the right thing? - When stuck choosing between features - Before a launch — sanity check the user journey - When converting a vague idea into a spec ## How It Works ### Mode 1: Product Diagnostic Like YC office hours but automated. Asks the hard questions: ``` 1. Who is this for? (specific person, not "developers") 2. What's the pain? (quantify

affaan-m

Spring Security best practices for authn/authz, validation, CSRF, secrets, headers, rate limiting, and dependency security in Java Spring Boot services.

affaan-m

springboot-tdd is a test-driven development workflow for Spring Boot services using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo.

affaan-m

swift-concurrency-6-2 is a skill that enables Approachable Concurrency in Swift 6.2, providing a safe and efficient way to handle concurrency in iOS and macOS app development.

affaan-m

swift-protocol-di-testing is a skill that enables protocol-based dependency injection for testable Swift code, using focused protocols and Swift Testing.

affaan-m

continuous-learning-v2 is a cutting-edge AI agent skill that enables instinct-based learning, allowing developers to automate coding tasks and improve productivity.

affaan-m

# Design System — Generate & Audit Visual Systems ## When to Use - Starting a new project that needs a design system - Auditing an existing codebase for visual consistency - Before a redesign — understand what you have - When the UI looks "off" but you can't pinpoint why - Reviewing PRs that touch styling ## How It Works ### Mode 1: Generate Design System Analyzes your codebase and generates a cohesive design system: ``` 1. Scan CSS/Tailwind/styled-components for existing patterns 2. Extra

affaan-m

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines

affaan-m

Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.

affaan-m

>

affaan-m

>

affaan-m

carrier-relationship-management is a skill that automates and optimizes freight management processes using AI-powered tools.

affaan-m

logistics-exception-management is a specialized AI agent skill for managing and resolving freight exceptions, including shipment delays, damages, and disputes, using advanced technologies and workflows.

affaan-m

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

affaan-m

configure-ecc is an interactive installation wizard for Everything Claude Code, using AskUserQuestion to guide users through selective installation and verification.

affaan-m

deployment-patterns is a skill that provides deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, and production readiness checklists for web applications.

affaan-m

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

affaan-m

e2e-testing is a comprehensive AI agent skill for building stable, fast, and maintainable end-to-end test suites using Playwright patterns and Page Object Model.

affaan-m

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m

Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.

affaan-m

laravel-verification is a comprehensive AI agent skill for verifying Laravel project integrity and readiness for deployment.

affaan-m

perl-testing is a skill that enables developers to write efficient tests for their Perl applications using industry-standard testing frameworks and methodologies.

affaan-m

python-testing is a skill that enables developers to write efficient tests for their Python applications using pytest, fixtures, mocking, and parametrization.

affaan-m

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

affaan-m

strategic-compact is a skill that enables manual context compaction at logical intervals, preserving context and improving workflow efficiency for developers using Claude Code.

affaan-m

continuous-learning is a skill that automatically extracts reusable patterns from Claude Code sessions, enabling developers to improve their coding efficiency and productivity.

affaan-m

frontend-patterns is a skill that provides modern frontend development patterns for React, Next.js, and performant user interfaces.

affaan-m

documentation-lookup is a skill that fetches current documentation via Context7 MCP for libraries, frameworks, and APIs, using tools like resolve-library-id and query-docs

affaan-m

market-research is a skill that conducts thorough analysis with source attribution for decision-oriented summaries.

affaan-m

RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.

affaan-m

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics

affaan-m

database-migrations is a skill that enables developers to perform safe, reversible database schema changes for production systems using PostgreSQL, MySQL, and popular ORMs.

affaan-m

eval-harness is a formal evaluation framework implementing eval-driven development principles for Claude Code sessions

affaan-m

laravel-security is a skill that provides Laravel security best practices for authn/authz, validation, CSRF, mass assignment, file uploads, secrets, rate limiting, and secure deployment.

affaan-m

nuxt4-patterns is a skill for optimizing Nuxt 4 applications with best practices for server-side rendering, routing, and data fetching.

affaan-m

PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.

affaan-m

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.

affaan-m

architecture-decision-records is a skill that captures and logs architectural decisions made during coding sessions, providing a structured record of the decision-making process.

affaan-m

compose-multiplatform-patterns is a skill for building shared UI across Android, iOS, Desktop, and Web using Compose Multiplatform and Jetpack Compose.

affaan-m

kotlin-coroutines-flows is a skill that enables developers to leverage Kotlin Coroutines and Flows for structured concurrency, reactive data streams, and efficient error handling in Android and KMP projects.

affaan-m

Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.

affaan-m

X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants t

affaan-m

agent-harness-construction is a skill that optimizes AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

affaan-m

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.

affaan-m

clickhouse-io is a skill for optimizing ClickHouse database performance, providing patterns for high-performance analytics, query optimization, and data engineering.

affaan-m

iterative-retrieval is a pattern for progressively refining context retrieval to solve the subagent context problem in AI agent ecosystems.

affaan-m

java-coding-standards is a skill that provides guidelines for writing high-quality Java code in Spring Boot services, following best practices for naming, immutability, and error handling.

affaan-m

JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in Spring Boot.

affaan-m

Ktor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing.

affaan-m

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

affaan-m

SwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance optimization, and modern iOS/macOS UI best practices.

affaan-m

frontend-slides is a skill for creating zero-dependency, animation-rich HTML presentations that run entirely in the browser, inspired by visual exploration approaches.

affaan-m

continuous-agent-loop is a canonical loop skill for creating continuous autonomous agent loops with quality gates, evals, and recovery controls.

affaan-m

Article-writing is a skill that generates long-form content, such as articles, guides, and tutorials, in a distinctive voice derived from supplied examples or brand guidance.

affaan-m

content-engine is a powerful AI agent skill that generates platform-native content systems for multiple platforms, including X, LinkedIn, TikTok, YouTube, and newsletters.

affaan-m

nanoclaw-repl is a zero-dependency session-aware REPL built on claude-p for operating and extending NanoClaw v2.

affaan-m

enterprise-agent-ops is a skill for operating long-lived agent workloads with advanced controls and security.

affaan-m

investor-materials is a skill that generates and updates investor-facing documents, including pitch decks, one-pagers, and financial models, to help developers and founders secure funding.

affaan-m

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

affaan-m

ai-first-engineering is a skill that enables teams to effectively integrate AI agents into their development workflow, focusing on agent-friendly architectures and rigorous testing.

affaan-m

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

getsentry

Set up and manage the Sentry development environment using devenv. Handles fresh setup, updating existing environments, starting dev services, and troubleshooting. Use when asked to set up sentry, set

getsentry

Sentry JavaScript frontend bug pattern review based on real production errors. Use when reviewing React/TypeScript frontend code for common bug patterns. Trigger keywords: javascript bug review, front

qwibitai

Debug container agent issues. Use when things arent working, container fails, authentication problems, or to understand how the container system works. Covers logs, environment variables, mounts, and

qwibitai

Add WhatsApp as a channel. Can replace other channels entirely or run alongside them. Uses QR code or pairing code for authentication.

qwibitai

Read and extract text from PDF files — documents, reports, contracts, spreadsheets. Use whenever you need to read PDF content, not just when explicitly asked. Handles local files, URLs, and WhatsApp a

qwibitai

Run initial NanoClaw setup. Use when user wants to install dependencies, authenticate messaging channels, register their main channel, or start the background services. Triggers on setup, install, con

JetBrains

Debugging techniques and tools for IntelliJ development. Use when debugging IDE issues or investigating failures.

JetBrains

Guidelines for using the IntelliJ Registry API. Use when working with registry keys or feature flags.

mountain-loop

Check out a GitHub pull request for review in this repo, either in the current directory or in a new isolated worktree at ../yaak-worktrees/pr-<PR_NUMBER>. Use when asked to run or replace the old Cla

comet-ml

TypeScript SDK patterns for Opik. Use when working in sdks/typescript.

comet-ml

Local development environment setup and commands. Use when helping with dev server, Docker, or local testing.

ruvnet

Agent skill for gossip-coordinator - invoke with $agent-gossip-coordinator

udecode

[DEPRECATED] Use /ce:compound instead — renamed for clarity.

udecode

Reviews Python code with an extremely high quality bar for Pythonic patterns, type safety, and maintainability. Use after implementing features, modifying code, or creating new Python modules.

udecode

Creates or updates README files following Ankane-style template for Ruby gems. Use when writing gem documentation with imperative voice, concise prose, and standard section ordering.

udecode

Full autonomous engineering workflow