MCP App StoreMCP App Store
from vexjoy-agent386
Orchestrate multiple agent skills into validated DAGs with dependency resolution, compatibility checks, and execution planning.
Orchestrates and validates multi-skill workflows by discovering applicable skills, building an execution DAG, validating compatibility and acyclicity, and presenting a dry-run plan before execution. It helps agents combine 2–3 skills safely into sequential or parallel phases while handling context passing and failures.
Use this when a user request requires chaining multiple skills (e.g., analyze code, run tests, and produce a report), when parallel tasks can speed up work, or when conditional branching and dependency resolution are needed across skills. Avoid it for single-skill tasks.
Best used with agents that support code/script execution and skill-level orchestration (Claude Code, Cursor/Copilot-style agents, or any runtime that can call skill scripts).
Skill Composer orchestrates multiple agent skills into validated DAGs with dependency resolution, compatibility checks, and execution planning. The SKILL.md is thorough with 4 clear phases (DISCOVER, PLAN, EXECUTE, REPORT) and gate conditions. The 3 Python scripts are well-structured but all require mandatory CLI arguments and don't run in isolation — they need a skill index and task description to operate. No security concerns found; all operations are local file I/O and graph manipulation.
Solid meta-tooling skill for DAG-based skill composition. Code quality is good with proper error handling, type hints, and docstrings. Architecture follows the skill spec well but loses points for unbundled references and Claude Code-specific env vars. Security is clean — no network calls, no credentials, no destructive commands.
Series Planner
Plans multi-part content series: assesses viability, selects structure and cadence, and generates detailed per-part plans with cross-linking and publishing sche
Pair Programming
Interactive micro-step pair-programming protocol: announce changes, show diffs, wait for user approval, apply, and verify (lint/tests).
Publish (Content Publishing Pipeline)
Umbrella skill for content publishing: outline posts, run pre-publish checks, optimize SEO, batch-edit frontmatter, audit links/images, manage taxonomy, and upl
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.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
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.