MCP App StoreMCP App StoreThis skill is a meta-workflow orchestrator that guides an agent through bug investigation and resolution. It coordinates parallel investigation, diagnosis, risk premortems, TDD-based implementation, regression testing, and committing changes — with required human checkpoints before implementation and commit.
Use this skill when you need an end-to-end bug fix process: diagnosing unclear failures, planning low-risk fixes, running tests, and producing commits or handoffs. It supports scopes for general bugs, hooks, dependency issues, and addressing PR comments.
Best suited for multi-agent setups and developer-focused assistants (Claude Code, agent swarms, Codex-style implementers) that can run tests, edit code, and interact with humans for checkpoints.
Workflow orchestrator skill for bug investigation and resolution, routing to specialized sub-agents (sleuth, kraken, etc.) based on issue scope. No bundled scripts — purely instructional SKILL.md. Well-documented with clear phases, human checkpoints, and error handling. Depends heavily on the vibeeval ecosystem of sub-skills, limiting portability outside that environment.
No security concerns at all — the skill is purely instructional with strong human checkpoint requirements. Quality and architecture are good but the skill is verbose; chain details could be moved to references/. Usefulness is moderate due to ecosystem lock-in.
Django Development Patterns
Production-grade Django architecture and patterns: project layout, DRF APIs, ORM best practices, caching, signals, middleware and deployment guidance.
GCP Patterns
Practical GCP deployment and architecture patterns: Cloud Run Dockerfiles, BigQuery partitioning & clustering, Pub/Sub best practices, and IAM least-privilege g
Hook Developer
Reference for building Claude Code hooks: schemas, registration, and testing patterns.
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.
