MCP App StoreMCP App Store
from vexjoy-agent386
Interactive micro-step pair-programming protocol: announce changes, show diffs, wait for user approval, apply, and verify (lint/tests).
Implements a disciplined pair-programming micro-step protocol for collaborative coding sessions. The skill enforces an Announce-Show-Wait-Apply-Verify loop so users see planned diffs and confirm before any file modifications. It tracks step counts, enforces size limits per step, and runs verification checks after changes.
Use this skill for interactive coding when the user wants fine-grained control over changes — code reviews, incremental feature work, or safe refactors where each change must be inspected before applying. It runs in the main session and requires user confirmation for each step.
Agents that support interactive read/write/edit operations and can show diffs (Copilot-like or Claude Code) will best implement this skill. It is primarily a process/interaction skill rather than automation tooling.
Pair Programming skill defines an interactive micro-step protocol (Announce-Show-Wait-Apply-Verify) for collaborative coding with an AI agent. No scripts included — purely a protocol/instruction skill. Well-structured SKILL.md with clear triggers, error handling guidance, speed adjustment mechanics, and concrete examples. No security concerns; uses standard agent tools appropriately.
Clean skill with no scripts to run. The SKILL.md is thorough and well-organized. GitHub source URL in DB points to skills/pair-programming/SKILL.md but actual path is skills/process/pair-programming/SKILL.md — URL may be stale. The skill_md_body was null in the fetch output, had to retrieve from GitHub API directly.
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
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
Skill Composer
Orchestrate multiple agent skills into validated DAGs with dependency resolution, compatibility checks, and execution planning.
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.
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
SourceSage CLI
Generate concise, LLM-friendly repository summaries (Markdown) using the SourceSage CLI — supports lite mode, language switching, and targeted repo analysis.
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