MCP App StoreMCP App Store
from claude-code-minoan38
Guidance and tooling for creating, reviewing, and packaging Agent Skills (SKILL.md) — frontmatter quality, triggers, evals, scripts, and packaging best practice
Provides a comprehensive guide and procedural toolkit for authoring high-quality Agent Skills. Covers frontmatter conventions, trigger design, progressive disclosure, bundling scripts/references/assets, eval creation and benchmarking, packaging, and iterative improvement flows. Includes scripts to initialize, package, run evals, and benchmark skills.
Use when creating a new skill, reviewing an existing SKILL.md for quality, designing triggers, writing evals, packaging for distribution, or optimizing descriptions to improve invocation accuracy. Also useful for maintainers preparing skills for publication.
Designed for Claude Code and development-focused agents that can run scripts and manage files.
A comprehensive skill optimization/CSO diagnostic tool that analyzes skill trigger rates, user reactions, workflow completion, and static quality across 8 dimensions. Well-structured SKILL.md with clear triggers, detailed workflow, and research-backed rationale. No bundled scripts — relies on agent executing Python scripts against session JSONL data. Read-only by design, no security concerns.
No scripts to run or evaluate. SKILL.md is thorough and well-organized with proper frontmatter, clear sections, and a detailed 8-dimension scoring framework. The skill is read-only by rule ('never modify skill files, only output report'). Quality docked slightly for referencing platform-specific paths without graceful fallback messaging, and for the heavy word count (>500 words) which it itself flags as an anti-pattern in dimension 4.8. Architecture docked for not using a references/ directory for the detailed rubric tables and research background.
Ancient Near East Research
Academic research assistant for Biblical Hebrew, Semitic linguistics, and comparative Ancient Near Eastern studies — fetch texts (Sefaria), query cuneiform DBs
Summon Fable 5
Invoke the high-resource Claude Fable 5 model for complex, long-horizon architectural tasks and large-scale refactors.
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.
Retriever (Membrane CLI)
Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
FastAPI Project Templates
Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.
Chinese Software Copyright Application
Generate complete Chinese software copyright application materials (application form, code documentation, user manual, design docs) and export them to PDF from
CTF Write-up Generator
Generate a concise, reproducible submission-style CTF writeup with a one-path solution script, metadata, and a short checklist for fast verification.
Skill Issue — Skill Auditor
Scan and audit installed agent skills to produce a health report covering inventory, usage, dependency checks, version status, and actionable recommendations.
Verifying Markdown Formatting
Checks Markdown files for structural and stylistic formatting issues (headings, lists, code blocks, links) and applies deterministic fixes.