MCP App StoreMCP App StorePI (π) is a comprehensive problem-solving skill that provides a rigorous workflow for debugging, code review, product decisions and team coordination. It codifies a search→read→verify→deliver pipeline, stepwise debugging protocols, failure escalation (multi-stage), and evidence requirements for fixes and audits.
Use PI when tackling reproducible bugs, performing strict code reviews, coordinating multi-step deliveries, or when failures have occurred repeatedly and require escalation. It is designed for engineering and product teams demanding traceable, verifiable fixes.
Best used with agents that can run commands and attach outputs for verification (Claude Code, Copilot-style assistants, local exec-capable agents).
PI (Problem Iteration Engine) v23.2 is a comprehensive structured problem-solving and debugging framework for AI agents. The SKILL.md is very detailed (~29K chars) with protocols for search-read-verify workflows, debugging steps, code review checklists, anti-patterns, and MBTI-inspired cognitive routing. No bundled scripts. The content is genuinely useful for debugging methodology but extremely verbose with idiosyncratic MBTI/cognitive-matrix framing that adds cognitive overhead. No security concerns found — all instructions are standard agent debugging activities.
Well-intentioned debugging framework with genuine utility. The core protocols (search-read-verify, anti-patterns, debugging seven-step) are solid. Main issues are verbosity, monolithic structure, and the niche MBTI framing which limits broad appeal. No security concerns whatsoever.
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.
Java 25 & Spring Boot 4 Code Reviewer
Run focused, evidence-based code reviews for Java 25 and Spring Boot 4 projects — migration risks, architecture boundaries, null-safety (JSpecify), security, an
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
Juicebox Common Errors
Identify and remediate common Juicebox API errors (authentication, quotas, rate limits, invalid queries) with quick diagnostics and fixes.
