MCP App StoreMCP App Store
from llm-autonomous-agent-plugin-for-claude21
Guidelines and communication patterns for coordinating four agent groups (analysis, decision, execution, validation) to enable reliable feedback loops, knowledg
This skill codifies best practices for inter-group collaboration in a four-tier agent architecture: Group 1 (analysis), Group 2 (decision), Group 3 (execution), and Group 4 (validation). It defines communication schemas, handoff protocols, feedback loop practices, and patterns for knowledge transfer and specialization.
Apply this skill when designing or operating multi-agent systems that require clear handoffs, measurable feedback cycles, or when orchestrating complex workflows that benefit from confidence scores, prioritized execution plans, and iterative improvement. Useful for orchestrators, coordinator agents, and teams building agent pipelines.
Aimed at agent frameworks and orchestrators (Claude Code, autonomous agent runners, and systems that can call Python integration libraries).
This skill documents communication patterns and coordination strategies for a four-tier agent architecture (analysis→decision→execution→validation). It is entirely instructional—no scripts, no runnable code, just SKILL.md guidelines with Python code examples referencing library modules (lib.group_collaboration_system, etc.) that don't ship with the skill. Well-structured writing with clear anti-patterns and best practices, but the referenced libs are vaporware—users cannot actually use any of the demonstrated functions. Niche audience: only useful for teams building this exact four-tier architecture.
Pure documentation skill. No security concerns at all—no scripts, no network calls, no commands. Code quality is decent for what's there (clear structure, good examples) but the Python snippets reference non-existent modules, making them copy-paste unusable. Architecture is mid: frontmatter is present, but no scripts/ or references/ directories, and output contracts are implicit. Usefulness is limited because the skill describes an opinionated architecture that requires a specific codebase to implement.
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.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
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.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.
StateTree Behavior
Tools to create, inspect, and edit Unreal Engine StateTree assets (hierarchical state machines) and Blueprint task workflows.