Каталог навыков агентов

CSS styles, color themes, and visual conventions for docs.cloudposse.com. Use when styling components, mermaid diagrams,...

Comprehensive guide to integrating DSPy with Microsoft Agent Framework in AgenticFleet, covering typed signatures, asser...

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for...

Plan work before coding: do repo research, analyze options/risks, and ask clarifying questions before proposing an imple...

Guide a safe git rebase of the current branch onto a target branch, including conflict triage and resolution steps. Use...

Build, test, and explain regular expressions against sample text or files using CLI tools (rg, python) and specific rege...

Draft release notes and changelog entries from git history or merged PRs between two refs (tags/SHAs/branches), includin...

Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported sit...

SSH into an Ubuntu VPS (Docker) for a read-only health/security/update report (UFW + fail2ban) and propose fixes; apply...

Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when needing algorithm implementati...

Comprehensive guide for initializing or reorganizing agent memory and project context. Use when setting up a new project...

Expert Python backend code reviewer that identifies over-complexity, duplicates, bad optimizations, and violations of be...

Enforces brevity and signal-over-noise in all outputs. Eliminates verbose explanations, filler phrases, and unnecessary...

Creates well-formed tasks following a template that engineers can implement. Use when creating tasks, defining work item...

Professional, skeptical communication style. Never over-enthusiastic, verifies before agreeing, challenges constructivel...

Aggregates and summarizes the latest AI news from multiple sources including AI news websites and web search. Provides c...

Guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle. Use when user asks to eliminate...

Research-driven investigation skill for validating solutions and exploring documentation. Never ask questions you can an...

This skill analyzes code for design quality improvements across 8 dimensions: Naming, Object Calisthenics, Coupling & Co...

This skill should be used when fixing bugs, implementing features, debugging issues, or making code changes. Ensures und...

FOLLOW THE STATE MACHINE IN SKILL.MD. When user says 'continue': (1) FIRST: Run pwd, (2) Announce STATE: CHECK_STATUS, (...

Systematic debugging methodology that eliminates guessing and speculation. Add instrumentation to gather specific data t...

Draft a repo-local plan using the plan skill template and optionally save it.

Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaborativel...

Object-oriented design principles including object calisthenics, dependency inversion, fail-fast error handling, feature...

Quick persona switching. Triggers: 'switch persona', 'switch to X', 'become X'. Lists personas, reads selected file, swi...

Strict test-driven development state machine with red-green-refactor cycles. Enforces test-first development, meaningful...

Write, configure, and run unit + integration tests using project-independent best practices; detect tooling; triage fail...

Principles for writing effective, maintainable tests. Covers naming conventions, assertion best practices, and comprehen...

Generate architecture diagrams as .excalidraw files from codebase analysis. Use when the user asks to create architectur...

Universal challenge tracker with flexible cadence, intelligent insights, and cross-challenge learning detection. Use whe...

Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor...

Implements authentication and payment features using Clerk, Supabase Auth, or Stripe. Use when user mentions ログイン, 認証, a...

Diagnoses and fixes CI/CD pipeline failures. Use when user mentions 'CI', 'GitHub Actions', 'GitLab CI', 'ビルドエラー', 'テスト失...

Cursorでclaude-memのMCPサーバーにアクセスし、過去のセッション記録を検索・新しい観測を記録。トリガー: 'メモリ検索', 'claude-mem', '過去の判断', '記録して', 'memory search', 'p...

Implements features and writes code based on Plans.md tasks. Use when user mentions 実装, implement, 機能追加, コードを書いて, 機能を作って...

Manages memory, SSOT files, and Plans.md operations. Use when user mentions メモリ, memory, SSOT, decisions.md, patterns.md...

Optimizes parallel execution of multiple tasks. Use when user mentions 並列で実行, 同時にやって, まとめてやって, run in parallel, do these...

Manages Plans.md tasks and marker operations. Use when user mentions タスクを追加, Plans.md更新, 完了マーク, タスク状態変更, add task, updat...

Provides development principles, guidelines, and VibeCoder guidance. Use when user mentions 原則, principles, ガイドライン, guid...

Reviews code for quality, security, performance, and accessibility issues. Use when user mentions レビュー, review, コードレビュー,...

Initializes session with environment check and task status overview. Use when user mentions セッション開始, 作業開始, 状況確認, what sh...

Manages cross-session learning and memory persistence. Use when user mentions 前回何をした, 履歴, 過去の作業, セッション記録, continue from...

Sets up new projects and generates workflow files like CLAUDE.md, AGENTS.md, Plans.md. Use when user mentions セットアップ, se...

Generate a specification template for non-trivial changes using Spec-Driven Development. Creates GitHub issue + spec fil...

Guides diagnosis and resolution when problems occur. Use when user mentions 動かない, エラーが出た, 壊れた, うまくいかない, broken, doesn't...

Generates UI components and feedback forms. Use when user mentions コンポーネント, component, UI, ヒーロー, hero, フォーム, form, フィードバ...

Verifies builds, recovers from errors, and applies review fixes. Use when user mentions ビルド, build, 検証, verify, エラー復旧, e...

Provides guidance on Cursor ↔ Claude Code 2-agent workflow. Use when user mentions ワークフローについて, Cursorとの連携, 作業の流れ, 2-agen...

The universal registry for AI coding tools

Renders and validates Crossplane compositions with security and policy checks. Automatically activates when testing comp...

EnforceScript component patterns, networking, persistence, and memory management for Enfusion engine

Validates KCL Crossplane compositions with comprehensive checks including formatting, syntax validation, and rendering t...

Overthrow mod architecture patterns, naming conventions, and project structure

The universal registry for AI coding tools

Arma Reforger Workbench workflow, testing guidelines, and debugging patterns

System architecture: modules, project structure, ADRs, and testing. Use when designing or reviewing systems.

CI/CD and operations practices including GitHub Actions, Kubernetes, and operational tooling. Use when working with depl...

Code quality practices: error handling, validation, logging, and DRY. Use when writing or reviewing code.

Code design patterns: pure functions, immutability, composition, and async. Use when designing code or functions.

Manages practice rules. Use when user states a preference or approach, or asks to add/modify rules for coding, architect...

Go conventions for hexagonal architecture, project structure, error handling, testing, and observability. Use when writi...

JS/TS conventions for syntax, modules, and types. Use when writing or reviewing JavaScript/TypeScript code.

Security practices including secrets management, input validation, SSRF prevention, and production hardening. Use for se...

Development tooling standards including Deno runtime, JSR package registry, and configuration files. Use when setting up...

Workflow rules for task execution, respecting user code, and git commits. Use when planning or executing development tas...

Evaluate Clojure code via nREPL using clj-nrepl-eval. Use this when you need to test code, check if edited files compile...

Create a new Agent Skill for specialized tasks.

REQUIRED for editing any skill file. Ensures changes sync to Claude, Codex, and Cursor. Never edit .claude/skills/ files...

Verify API requests in tests. Use when testing that correct API calls are made for create, update, or delete operations....

Start here for all API mocking in tests. Covers auto-generation, fixtures, and when to use other skills. Required readin...

Expertise in calculating and specifying hardware requirements for local AI deployments, including GPU selection, server...

Adds visual descriptions to transcripts by extracting and analyzing video frames with ffmpeg. Creates visual transcript...

Creates compressed ZIP backups of libraries directory. Backs up library.yaml, transcripts, and roughcuts (not video file...

Use when user asks to leverage claude or claude code to do something (e.g. implement a feature design or review codes, e...

Interactive feature development workflow from idea to implementation. Creates requirements (EARS format), design documen...

Creates syntactically correct mermaid diagrams (flowchart, sequenceDiagram, classDiagram, stateDiagram, erDiagram, gantt...

Generate or edit images using Google Gemini API via nanobanana. Use when the user asks to create, generate, edit images...

Creates video rough cut yaml file for use with Buttercut gem. Concatenates visual transcripts with file markers, creates...

GitHub Spec-Kit integration for constitution-based spec-driven development. 7-phase workflow (constitution, specify, cla...

Transcribes video audio using WhisperX, preserving original timestamps. Creates JSON transcript with word-level timing....

A skill to automatically download and install the latest ButterCut version from GitHub while preserving libraries. Use w...

Extract subtitles/transcripts from a YouTube video URL and save as a local file. Use when you need to extract subtitles...

Unity 引擎 HybridCLR + YooAsset的热更新，基于GameFramework框架开发的塔防游戏；Game Jam

Create or edit a Cline Skill with guided assistance and best practices

Guide for adding a new AI coding agent analyzer to Splitrail. Use when implementing support for a new tool like Copilot,...

Guide for Splitrail's terminal UI and file watching. Use when modifying the TUI, stats display, or real-time update logi...

OpenClaw plugin skill for X/Twitter search, account reads, monitored workflows, and approval-gated TweetClaw actions thr...

Use bdg CLI for browser automation via Chrome DevTools Protocol. Provides direct CDP access (60+ domains, 300+ methods)...

Code-Standards. Use when reviewing code style or formatting.

Expert-level Home Assistant configuration management with efficient deployment workflows (git and rapid scp iteration),...

APP从启动到显示流程

Interactive browser automation via Chrome DevTools Protocol. Use when you need to interact with web pages, test frontend...

Google Calendar CLI for listing calendars, viewing/creating/updating events, and checking availability.