MCP App StoreMCP App Store
from bdfinst205
A four-phase debugging protocol (reproduce → investigate → root-cause → fix) that forces evidence-based fixes and avoids guess-and-check thrashing when tests fa
Systematic Debugging gives agents a repeatable four-phase protocol to diagnose and fix software defects: reproduce the failure, investigate and gather facts, form and test a root-cause hypothesis, then apply a minimal verified fix. The skill prevents the common LLM-driven failure mode of speculative changes by requiring reproduction, observation points, hypothesis testing, and single-variable fixes. It includes practical gating steps and red flags to stop low-quality attempts.
Use this skill whenever a test that previously passed begins failing, an error appears during implementation, a bug report arrives, or a fix attempt did not resolve the issue. It's also recommended under time pressure to avoid wasted cycles.
This is a purely procedural skill usable by worker agents and code assistants (Copilot-style, Codex/Claude/Agent-based orchestrators). It requires no special tooling and complements agents that can run tests, read logs, or modify small code snippets.
Systematic Debugging is a four-phase debugging protocol skill (reproduce, investigate, root-cause, fix) with no bundled scripts. The SKILL.md body was unavailable (404 on GitHub), so scoring is based solely on metadata which includes good tags, a clear description, and structured naming. The concept is useful but the actual content couldn't be verified.
No scripts to run or analyze. SKILL.md body returned 404 from source URL. Scored conservatively on quality and architecture since the actual instructions could not be reviewed.
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.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.
Tmux Bridge
Give an agent controlled access to a local tmux terminal bridge so it can run shell commands, capture output, and manage sessions on the user's machine.
Cursor Hello World Tutorial
A concise 10-minute hands-on tutorial demonstrating Cursor's Tab completion, Chat, Inline Edit, and Composer features for getting started quickly.
Supabase SDK Patterns (TypeScript & Python)
Production-ready patterns for using Supabase clients in TypeScript and Python: client initialization, typed queries, auth, realtime, storage, RPC, and error-han
Replit — Advanced Troubleshooting
Step-by-step diagnostics and debugging techniques for deep Replit issues: Nix build failures, container crash loops, memory leaks, and platform vs app isolation