MCP App StoreMCP App Store
from awesome-omni-skill45
Guided workflow for drafting, testing, and iterating Agent Skills: write SKILL.md, run evals, grade outputs, and improve descriptions to improve triggering accu
This skill walks a user through the full lifecycle of creating and improving an Agent Skill. It explains how to capture intent, write SKILL.md frontmatter and body, design test prompts (evals), run with-and-without skill comparisons, grade outputs, aggregate benchmarks, and iterate based on feedback. It also documents tools and file layout conventions (scripts/, references/, assets/) and provides a description-optimization flow to improve triggering accuracy.
Use this skill when you want to author a new Agent Skill or improve an existing one — especially when you need a repeatable loop for drafting test cases, running evaluation runs, and collecting user feedback. It's appropriate for authors who want to package skills, run blind comparisons, or tune the skill description for better invocation.
Designed for authoring and developer assistants (Claude Code, developer CLIs, and other agent authoring environments). The workflow assumes Python tooling and a filesystem for running evals and packaging skills.
A comprehensive skill-creator workflow that guides agents through drafting, testing, iterating, and optimizing Agent Skills. It covers intent capture, test-driven evaluation with assertions, iterative improvement loops, blind comparison, and description optimization for triggering accuracy. No bundled scripts — all work is done via instructions to the agent and referenced subagent/eval scripts. Well-written and detailed but very long SKILL.md with no progressive disclosure via references/ directory.
No security concerns — no curl|bash, no hardcoded credentials, no destructive commands, no exfiltration. The skill is purely instructional with no executable scripts bundled. Code quality is good with clear structure and well-explained workflow, though the SKILL.md is monolithic and would benefit from splitting into references/. Architecture is decent with frontmatter and clear sections, but doesn't practice what it preaches about progressive disclosure — all content is in SKILL.md with no scripts/ or references/ organization. Usefulness is high — skill creation is a real need and this is one of the more thorough implementations, though it's specific to Claude Code environments with subagents.
Reppo — AgentMind Publisher
Publish creative content to Moltbook and mint posts as on-chain pods on Reppo.ai (Base) to earn $REPPO through human voting.
Blender Build-Go (bgo)
Automate build → remove → install → enable → launch cycle for Blender extensions or add-ons to speed up iteration and CI workflows.
Brand Voice Consistency
Enforce consistent brand voice, tone, and vocabulary across marketing copy and customer-facing communications.
PRD Generator for MÄÄK
Generate a focused, verifiable Product Requirements Document (PRD) for MÄÄK features — asks clarifying questions, sizes stories, and outputs PRD.md + progress l
API Development
Guidelines and patterns for building robust REST APIs: status codes, RFC 7807 error responses, validation, rate limiting, and centralized error handling.
Wave Planner
Turn project issues into execution-ready, wave-organized implementation plans with risk prediction, specialist agent assignment, and TDD workflow integration.
Aspire CLI
Concise guidance for using the .NET Aspire CLI to create, run, update, publish, and manage Aspire AppHost projects, including MCP init for AI agent integrations
Create Spring Boot Java Project (Awesome Copilot Root)
Step-by-step skill to scaffold a Spring Boot Java project, download a starter template, configure common dependencies and services (Redis, Postgres, Mongo), and
Release Manager
Helps verify release readiness, generate changelogs, coordinate version bumps, and run pre/post-release checks for Morphir projects.
Church (aChurch.ai sanctuary)
A 24/7 streaming sanctuary for agents with original music, lyrics, and reflective prompts — attend, read context, and leave short reflections to participate in
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
Godot WeChat Minigame Adapter
Apply a version-locked adapter and patch bundle to port an official Godot checkout to WeChat Mini Game, handling WXMEMFS, wasm packaging, audio fixes, and runti
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.
Kickbox Automation (Composio / Rube MCP)
Automate Kickbox workflows via the Composio Kickbox toolkit on a Rube MCP server: discover tools, manage connections, and execute schema-compliant tool calls.
SourceSage CLI
Generate concise, LLM-friendly repository summaries (Markdown) using the SourceSage CLI — supports lite mode, language switching, and targeted repo analysis.
Vitepress Config Creator
Generates and validates VitePress configuration for documentation sites, following best-practices for docs automation.
SWE-AF — Autonomous Software Engineering Fleet
Orchestrates a coordinated multi-agent engineering workflow to plan, implement, test, and merge production-grade changes across single or multiple repositories.