docs-generator
Autonomously analyzes a repository, detects architectural and coding patterns, and generates/updates a docs/ folder with a root CLAUDE.md as table of contents. Use when asked to generate documentation, create C...
Discover DevOps skills, compare source repositories and read the instructions for each workflow.
Autonomously analyzes a repository, detects architectural and coding patterns, and generates/updates a docs/ folder with a root CLAUDE.md as table of contents. Use when asked to generate documentation, create C...
Autonomously completes Linear tickets via git worktrees. Use when user says "fix ENG-123", "complete LIN-456", "work on linear ticket", provides a linear.app URL, or mentions a ticket ID pattern like ABC-1234....
Search Linear issues and projects. Use when finding issues, looking up bugs, or searching the backlog.
Review and improve repository documentation including both human-readable docs (`docs/`), `README.md`, and AI agent memory context files (`CLAUDE.md`, `CODEX.md`, `AGENTS.md`, `.cursorrules`, etc.) for clarity,...
Manage Linear issues - list, create, update, start/stop work. Use when working with Linear issues, viewing tasks, creating bugs, or updating issue status.
ユーザーに質問を投げかけるアシスタント。AskUserQuestionツールを使って選択肢付きの質問を提示します。
Agent Browser CLIを使ってブラウザ操作を自動実行するスキル。npx経由でブラウザ自動化タスクを委譲します。
Codex CLIを使ってコードレビュー・分析を自動実行するスキル。Claude Codeの相棒として複雑な問題解決やセカンドオピニオンの取得に活用できます。
マネージャーエージェント。自分では作業せず、全ての作業をサブエージェントに委譲します。
現在の作業状況を整理し、次のセッションに引き継ぐための情報をまとめます。
Remove AI-generated code slop from a branch. Use to delete unnecessary comments/docs, defensive checks, broad try/catch blocks, type-cast hacks, lint suppressions, dead code, duplication, and style drift. Diff...
Creates well-formatted conventional commit messages from your git changes. Analyzes git diff and status to generate proper commit messages following conventional commits format. Use when the user wants to commi...
Analyzes files and provides detailed statistics including line counts, file size, detected language, and complexity. Use when the user wants to analyze a file or get file statistics.
Performs thorough code reviews with actionable feedback. Analyzes code for quality, bugs, security vulnerabilities, performance issues, and best practices violations. Use when the user wants a code review or as...
Generates comprehensive unit tests for code. Detects the testing framework, creates tests with edge cases and mocks, and follows best practices. Use when the user wants to generate tests for their code or needs...
A friendly greeting skill that shows the current date, time, working directory, and a motivational message. Use when the user asks for a greeting or wants to test if skills are working.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications using Astro and Tailwind CSS. Generates creat...
Context-driven development methodology for organized, spec-first coding. Use when: - Project has a `conductor/` directory - User mentions specs, plans, tracks, or context-driven development - Files like `conduc...
deeply review a system/architecture area and propose a simplification plan (Elon’s Algorithm).
guidance on how to properly do data migrations in Convex
Generate and edit images using either OpenAI GPT Image 1.5 or Google's Nano Banana Pro (Gemini 3 Pro Image). Use when the user asks to generate/create/edit/modify images. Supports image-to-image editing for bot...
recenter on where we are, what's done/left, and where necessary reflect on our work's principle compliance, performance, and pristineness.
Systematically explore a codebase area and find/fix obvious issues with fresh eyes.
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.