Software Development AI agent skills

13,359 skills in the archive. Read a skill’s instructions or open its original repository.

• Agent Sort

  by @affaan-m

  並行リポジトリ対応のレビューパスを使用して、スキル、コマンド、ルール、フック、エクストラを DAILY と LIBRARY のバケットに分類することで、特定のリポジトリ向けのエビデンスに基づいた ECC インストール計画を構築します。プロジェクトが完全なバンドルをロードする代わりに実際に必要なものに ECC をトリミングする必要がある場合に使用します。

• Laravel Verification

  by @affaan-m

  Bucle de verificación para proyectos Laravel: verificaciones de entorno, linting, análisis estático, pruebas con cobertura, escaneos de seguridad y preparación para despliegue.

• Golang Testing

  by @affaan-m

  Patrones de pruebas Go incluyendo pruebas basadas en tablas, subpruebas, benchmarks, fuzzing y cobertura de código. Sigue la metodología TDD con prácticas idiomáticas de Go.

• Springboot Tdd

  by @affaan-m

  Desarrollo guiado por pruebas para Spring Boot usando JUnit 5, Mockito, MockMvc, Testcontainers y JaCoCo. Usar al agregar funcionalidades, corregir bugs o refactorizar.

• Springboot Verification

  by @affaan-m

  Bucle de verificación para proyectos Spring Boot: build, análisis estático, pruebas con cobertura, escaneos de seguridad y revisión de diff antes del lanzamiento o PR.

• Backend Patterns

  by @affaan-m

  Patrones de arquitectura backend, diseño de API, optimización de base de datos y buenas prácticas del lado del servidor para Node.js, Express y rutas API de Next.js.

• Jpa Patterns

  by @affaan-m

  Patrones JPA/Hibernate para diseño de entidades, relaciones, optimización de consultas, transacciones, auditoría, indexación, paginación y pooling en Spring Boot.

• Django Patterns

  by @affaan-m

  Patrones de arquitectura Django, diseño de API REST con DRF, buenas prácticas de ORM, caché, señales, middleware y aplicaciones Django de nivel producción.

• Agent Payment X402

  by @affaan-m

  タスクごとのバジェット、支出コントロール、ノンカストディアルウォレットを備えた x402 決済実行を AI エージェントに追加します。agentwallet-sdk を通じて Base をサポートし、OKX Payments / OKX エージェント決済プロトコルを通じて X Layer をサポートします。

• Rust Testing

  by @affaan-m

  Patrones de pruebas en Rust incluyendo pruebas unitarias, de integración, async, basadas en propiedades, mocking y cobertura. Sigue la metodología TDD.

• Python Patterns

  by @affaan-m

  Patrones idiomáticos de Python, estándares PEP 8, type hints y buenas prácticas para construir aplicaciones Python robustas, eficientes y mantenibles.

• Rust Patterns

  by @affaan-m

  Patrones idiomáticos de Rust, ownership, manejo de errores, traits, concurrencia y buenas prácticas para construir aplicaciones seguras y eficientes.

• Nextjs Turbopack

  by @affaan-m

  Next.js 16+ y Turbopack — bundling incremental, caché en sistema de archivos, velocidad de desarrollo y cuándo usar Turbopack frente a webpack.

• Backend Patterns

  by @affaan-m

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

• Laravel Tdd

  by @affaan-m

  Desarrollo guiado por pruebas para Laravel con PHPUnit y Pest, factories, pruebas de base de datos, fakes y objetivos de cobertura.

• Agentic Os

  by @affaan-m

  Claude Code 上に永続的なマルチエージェントオペレーティングシステムを構築します。カーネルアーキテクチャ、スペシャリストエージェント、スラッシュコマンド、ファイルベースのメモリ、スケジュールされた自動化、外部データベースなしの状態管理をカバーします。

• Golang Patterns

  by @affaan-m

  Patrones idiomáticos de Go, buenas prácticas y convenciones para construir aplicaciones Go robustas, eficientes y mantenibles.

• Frontend Patterns

  by @affaan-m

  Patrones de desarrollo frontend para React, Next.js, gestión de estado, optimización de rendimiento y buenas prácticas de UI.

• Python Testing

  by @affaan-m

  Estrategias de pruebas Python usando pytest, metodología TDD, fixtures, mocking, parametrización y requisitos de cobertura.

• Api Connector Builder

  by @affaan-m

  ターゲット リポジトリの既存統合パターンに正確に一致する新しい API コネクターまたはプロバイダーを構築します。2 番目のアーキテクチャを発明せずに、1 つ以上の統合を追加するときに使用します。

• Agent Eval

  by @affaan-m

  カスタムタスクでコーディングエージェント（Claude Code、Aider、Codex など）をヘッドツーヘッドで比較し、合格率、コスト、時間、一貫性のメトリクスを測定します

• Api Design

  by @affaan-m

  リソース命名、ステータス コード、ページネーション、フィルタリング、エラー応答、バージョン管理、およびレート制限を含む REST API デザイン パターン。

• Autonomous Loops

  by @affaan-m

  自動Claude Codeループのパターンとアーキテクチャ — シンプルな順序パイプラインからRFC駆動マルチエージェントDAGシステムまで。

• Agent Introspection Debugging

  by @affaan-m

  キャプチャ、診断、封じ込め回復、内省レポートを使用した AI エージェント障害のための構造化された自己デバッグワークフロー。

• Verification Loop

  by @affaan-m

  Sistema de verificación completo para sesiones de Claude Code.

• Benchmark

  by @affaan-m

  このスキルを使用して、パフォーマンスベースラインを測定し、PR前後の回帰を検出し、スタック代替案を比較します。

• Llama Cpp

  by @NousResearch

  llama.cpp local GGUF inference + HF Hub model discovery.

• System Atlas

  by @NousResearch

  Build explorable isometric architecture atlases as HTML.

• Obliteratus

  by @NousResearch

  OBLITERATUS: abliterate LLM refusals (diff-in-means).

• Agentmail

  by @NousResearch

  Use when an agent needs AgentMail CLI email inboxes.

• Fastmcp

  by @NousResearch

  Build, test, and deploy Python MCP servers.

• Serving Llms Vllm

  by @NousResearch

  vLLM: high-throughput LLM serving, OpenAI API, quantization.

• Huggingface Tokenizers

  by @NousResearch

  Fast BPE/WordPiece tokenization and custom vocab training.

• Watchers

  by @NousResearch

  Poll RSS, JSON APIs, and GitHub with watermark dedup.

• Torchtitan

  by @NousResearch

  Pretrain LLMs at scale with PyTorch 4D parallelism.

• Dspy

  by @NousResearch

  DSPy: declarative LM programs, auto-optimize prompts, RAG.

• Fitness Nutrition

  by @NousResearch

  Workout planning, macros, and body metrics via wger/USDA.

• Guidance

  by @NousResearch

  Constrain LLM output with grammars; guarantee valid JSON.

• Meme Generation

  by @NousResearch

  Create meme PNGs from templates with Pillow text overlay.

• Outlines

  by @NousResearch

  Outlines: structured JSON/regex/Pydantic LLM generation.

• Tldraw Offline

  by @NousResearch

  Drive and script tldraw offline canvases with an agent.

• Accelerate

  by @NousResearch

  Run PyTorch training across GPUs with minimal changes.

• Simpo

  by @NousResearch

  Reference-free preference alignment, simpler than DPO.

• Instructor

  by @NousResearch

  Structured LLM outputs validated with Pydantic.

• Segment Anything Model

  by @NousResearch

  SAM: zero-shot image segmentation via points, boxes, masks.

• Saelens

  by @NousResearch

  Train sparse autoencoders to interpret model features.

• Slime

  by @NousResearch

  RL post-training for LLMs with Megatron and SGLang.

• Modal

  by @NousResearch

  Serverless GPU cloud for ML jobs and model APIs.

• Qdrant

  by @NousResearch

  Vector search engine for production RAG systems.

• Lambda Labs

  by @NousResearch

  On-demand GPU cloud instances for ML training.

• Antigravity Cli

  by @NousResearch

  Operate the Antigravity CLI (agy): plugins, auth, sandbox.

• Hyperliquid

  by @NousResearch

  Hyperliquid market data, account history, trade review.

• Llava

  by @NousResearch

  Vision-language chat: VQA, captioning, image dialogue.

• Clip

  by @NousResearch

  Zero-shot image classification and image-text search.

• Solana

  by @NousResearch

  Query Solana wallets, tokens, txs, and NFTs in USD.

• Chroma

  by @NousResearch

  Embedding database for RAG and semantic search.

• Huggingface Hub

  by @NousResearch

  HuggingFace hf CLI: search/download/upload models, datasets.

• Openhands

  by @NousResearch

  Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).

• Adversarial Ux Test

  by @NousResearch

  Roleplay a hostile user to find and triage UX pain points.

• Blackbox

  by @NousResearch

  Delegate coding tasks to the Blackbox AI multi-model CLI.

• Dream Loop

  by @NousResearch

  Build stunning 3D scenes via a concept-art fidelity loop.

• Mcporter

  by @NousResearch

  List, auth, and call MCP servers/tools from the terminal.

• Brag Slim

  by @NousResearch

  Launch video from a project or URL, upstream-maintained.

• Heartmula

  by @NousResearch

  HeartMuLa: Suno-like song generation from lyrics + tags.

• One Three One Rule

  by @NousResearch

  1-3-1 decision briefs: problem, three options, one pick.

• Agent Merge Conflict Arbiter

  by @NousResearch

  Neutral arbiter for merge conflicts between two agents.

• Docker Management

  by @NousResearch

  Manage Docker containers, images, volumes, and Compose.

• Dynamic Workflow

  by @NousResearch

  Plan-in-code fan-outs, adversarial verification, waves.

• Hermes S6 Container Supervision

  by @NousResearch

  Modify or debug s6 services in the Hermes Docker image.

• Comps Analysis

  by @NousResearch

  Build comparable-company valuation workbooks in Excel.

• Grok

  by @NousResearch

  Delegate coding to xAI Grok Build CLI (features, PRs).

• Minecraft Modpack Server

  by @NousResearch

  Host modded Minecraft servers (CurseForge, Modrinth).

• Honcho

  by @NousResearch

  Configure and troubleshoot Honcho memory for Hermes.

• Ascii Art

  by @NousResearch

  ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.

• Jupyter Notebook

  by @NousResearch

  Iterative Python via live Jupyter kernel (hamelnb).

• Pinggy Tunnel

  by @NousResearch

  Zero-install localhost tunnels over SSH via Pinggy.

• Migrate Customizations

  by @microsoft

  Guide a safe, reversible migration of VS Code local agent customizations when launched from the Agent Customizations Migrations page with VS Code-generated migration context.

• Launch

  by @microsoft

  Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code…

• Launch

  by @microsoft

  Launch and automate VS Code Insiders with the Copilot Chat extension using @playwright/cli via Chrome DevTools Protocol. Use when you need to interact with the VS Code UI, automate the chat panel, test the extension UI, or take…

• Create Canvas

  by @microsoft

  Create a project Copilot extension canvas for the current workspace.

• Github Copilot Upgrader

  by @microsoft

  Use this to update the Github Copilot CLI/SDK

• Agent Customization

  by @microsoft

  **WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). USE FOR: saving coding preferences;…

• Project Setup Info Context7

  by @microsoft

  Comprehensive setup steps to help the user create complete project structures in a VS Code workspace. This tool is designed for full project initialization and scaffolding, not for creating individual files. When to use this…

• Project Setup Info Local

  by @microsoft

  Comprehensive setup steps to help the user create complete project structures in a VS Code workspace; this tool is designed for full project initialization and scaffolding, not for creating individual files. When to use this…

• Chronicle

  by @microsoft

  Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past…

• Update Skills

  by @microsoft

  Create or update repository skills and instructions when major learnings are discovered during a session. Use when the user says "learn!", when a significant pattern or pitfall is identified, or when reusable domain knowledge…

• Troubleshoot

  by @microsoft

  Investigate unexpected chat agent behavior by analyzing direct debug logs in JSONL files. Use when users ask why something happened, why a request was slow, why tools or subagents were used or skipped, or why…

• Sync

  by @microsoft

  Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase onto upstream, push current branch, publish…

• Commit

  by @microsoft

  Commit staged or unstaged changes with an AI-generated commit message that matches the repository's existing commit style. Use when the user asks to 'commit', 'commit changes', 'create a commit', 'save my work', or 'check in…

• Sync Upstream

  by @microsoft

  Update a stale session branch by rebasing onto the latest origin. Use when the upstream has moved significantly and the session needs to catch up, resolving conflicts by preserving upstream changes and adapting session work to…

• Install Vscode Extension

  by @microsoft

  How to install a VS Code extension from an extension ID. Useful when the user wants to add new capabilities to their VS Code environment by installing extensions.

• Code Review

  by @microsoft

  Perform a code review of the current session's changes. Use when the user requests a code review via the Run Code Review button in the Changes toolbar.

• Act On Feedback

  by @microsoft

  Act on user feedback attached to the current session. Use when the user submits feedback on the session's changes via the Submit Feedback button.

• Merge

  by @microsoft

  Merge changes from the topic branch to the merge base branch. Use when the user wants to merge their session's work back to the base branch.

• Fix Ci

  by @microsoft

  Fix the failed CI checks for the current session. Use when the user requests a CI fix via the Fix Checks button in the Changes toolbar.

• Create Draft Pr

  by @microsoft

  Create a draft pull request for the current session. Use when the user wants to open a draft PR with the session's changes.

• Create Pr

  by @microsoft

  Create a pull request for the current session. Use when the user wants to open a PR with the session's changes.

• Update Pr

  by @microsoft

  Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.

• Create Instructions

  by @microsoft

  Create an instructions file (.instructions.md) for a project rule or convention.

• Init

  by @microsoft

  Generate or update chat customization files for AI coding agents