MCP App StoreMCP App Store
from multi-agent-shogun1,248
Design, validate and review Claude Code-style SKILL.md files: frontmatter guidance, trigger design, testing patterns, and recommended file structure for robust
This skill provides guidance and tooling patterns for authoring high-quality SKILL.md files for Claude Code and compatible agent systems. It documents frontmatter fields, security constraints, trigger design, execution patterns (inline/fork/manual), testing strategies, and recommended repository layout.
Use when creating a new skill, reviewing or improving existing SKILL.md files, designing trigger tests, or preparing validation scripts. Activate on prompts like 'create a skill', 'review SKILL.md', or 'design skill triggers'. Not intended to execute other skills — it helps author and validate them.
Targets authors and agent platforms that implement Claude Code-style skill loading; applicable to Claude Code, other Claude-compatible runtimes, and agent systems that support frontmatter-driven skills.
A comprehensive skill-authoring guide for creating Claude Code SKILL.md files, based on Anthropic's official guide (2026-03). Written entirely in Japanese, it covers frontmatter design, description writing, execution patterns, file structure, and anti-patterns. No bundled scripts — purely a documentation/reference skill. Well-structured content but limited audience due to Japanese-only text and niche scope (Claude Code skill authoring).
Security: No scripts, no network calls, no destructive commands. Minor concern: mentions dynamic context via `!`command`` execution pattern which could be misused, but it's instructional guidance not executable code. Deducted 15 for the dynamic context execution pattern encouraging shell command embedding without strong safety guards. Quality: Well-written and thorough guide with clear structure, tables, and examples. However it's entirely in Japanese which reduces accessibility, and mixes general skill-authoring guidance with team-specific (shogun) conventions. Architecture: Good progressive disclosure structure, clear frontmatter, follows skill spec well. Uses standard file structure conventions. Usefulness: Niche audience — only useful for people authoring Claude Code skills in Japanese. Broader English-language skill-creator skills already exist.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
ds-fix — data-science mid-analysis fixer
Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.
SourceSage CLI
Generate concise, LLM-friendly repository summaries (Markdown) using the SourceSage CLI — supports lite mode, language switching, and targeted repo analysis.
Visualization Best Practices
Provides step-by-step guidance and production-ready patterns for creating clear, accurate, and effective data visualizations in analytics workflows.
Make Scenario Creator
Assist with creating and validating 'make' scenario creator workflows for business automation: generate configurations, produce code, and recommend best practic