git-helper
Performs git operations like status, diff, log, and branch management
Find the perfect capability for your agent.
Performs git operations like status, diff, log, and branch management
Git workflow guidance for commits, branches, and pull requests
Git worktree management with worktree.py CLI. Use for creating worktrees, teardown, merging PRs, syncing branches, and Docker service management.
Git 提交信息规范。着重于提交信息的格式化、风格统一。优先学习并沿用项目已有的提交历史风格,若无明显风格或为新项目,则遵循 Conventional Commits 规范。
完整功能開發工作流程 - 代碼審查→代碼簡化→知識管理→Git推送。三階段品質把控:1.review檢查 2.simplify優化 3.knowledge記錄,最後自動 commit & push
Operate and validate mjr.wtf observability endpoints (/health, /metrics) and logging-related behavior. Use when adding metrics, changing auth around metrics, or debugging production-like issues.
Manage full-stack observability using Logfire (logging/tracing) and OpenObserve (storage/visualization).
Instrument a webapp to send useful telemetry data to Azure App Insights
mystudy-handsonリポジトリのファイル・ディレクトリを作成・編集する際の背景知識です
Create new Marp presentations with proper structure. Use when the user wants to create a presentation, start a new deck, make slides, or set up a new Marp presentation.
Comprehensive research toolkit for discovering patterns, best practices, and technical knowledge across Web search, MCP servers, GitHub repositories, and documentation. Use when researching technologies, exploring codebases, finding examples, or gathering requirements for skill development.
This skill should be used when the user asks to "review code", "check quality", "assess implementation", "validate standards", "identify issues", or requests code review and quality assessment. Use for systematic code review, quality checks, and best practices validation. Do NOT use for writing code or making design decisions.
Generate evidence-based documentary reports by searching across Brain memory system, .agents/ artifacts, and GitHub issues. Produces investigative journalism-style analysis with full citation chains.
Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Documentation in llms.txt format, (3) GitHub repository analysis, (4) Documentation without direct llms.txt support, (5) Multiple documentation sources in parallel
Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy
Triage large log directories without loading everything into context by extracting and grouping errors, emitting a compact debug brief, and (optionally) chunking raw logs for LLM upload.
Comprehensive guide for writing technical documentation
Automatically detect and suggest appropriate MCP tools (context7, grep_app, web_search) based on user queries. Use when queries contain documentation keywords (how to use, docs, API, guide, tutorial, 如何使用, 文档, 教程); code search keywords (example, implementation, source code, github, 例子, 示例, 实现, 源码); or latest information/bug fixing keywords (latest, 2025, 2026, new, update, fix bug, error, 最新, 更新, 修复 bug, 报错).
This skill should be used when the user reports "error", "bug", "not working", "failing tests", "unexpected behavior", "investigate issue", or describes something broken or malfunctioning. Use for systematic debugging, root cause analysis, and problem diagnosis. Do NOT use for implementing new features, writing tests, or making design decisions.