MCP App StoreMCP App Store
from code-explainer74
Interactive code walkthroughs that scan a codebase, plan segments, and narrate highlights with configurable depth and VS Code integration.
The Code Explainer skill scans a repository to identify a feature or code path, builds a segmented walkthrough plan, and delivers interactive explanations with highlights and optional TTS narration. It supports a tiered model setup (scout/overview vs deep-dive planners), parallel segment generation, and a sidebar integration mode that routes output through a local HTTP API when available. The skill prescribes strict checklists for scout, plan, execute, and wrap-up phases to ensure reproducible, high-quality walkthroughs.
Use when a user asks to explain how code works, to "walk me through" a module, or to get an in-context walkthrough of a feature. Also use during active walkthrough sessions where the agent must answer follow-up Q&A based on the current segment state. Choose Deep Dive for thorough analysis and Overview for fast summaries.
explainer.sh state).Best for agents that can run Bash, manage subprocesses, and interact with editor sidecars (CLI-capable Claude/Codex/other code-specialised agents).
Code Explainer is an interactive walkthrough skill that scans a codebase, builds segment plans, and narrates code highlights via VS Code sidebar integration and TTS. SKILL.md is well-structured with model tier system, step-by-step checklist, and common mistakes table. Scripts include a sidebar communication shell script, a persistent TTS server, a podcast generator, and a VS Code extension installer — all failed to run due to missing dependencies (VS Code extension, mlx_audio model). Shell injection risk in explainer.sh's save/load commands where user input is interpolated into JSON without sanitization.
mlx_audiovscode-extension-ecosystemSolid skill conceptually. The shell injection in save/load is the main concern — should use proper JSON construction (jq or printf %s). Scripts are well-written otherwise with good error handling and documentation.
Monad Development
Practical developer skill for deploying and verifying smart contracts, configuring Foundry projects, and integrating frontends (viem/wagmi) on the Monad blockch
Teacher Inquiry Cycle Designer
Design a manageable, evidence-informed teacher inquiry cycle from question through data collection, analysis, and sharing to improve classroom practice.
Uloop: Execute Dynamic Code
Run small C# snippets in the Unity Editor via the uloop CLI for editor automation tasks like prefab wiring, AddComponent flows, and scene edits—without writing
Generate Multilingual Sentences with Contextual Definitions
Produce multiple example sentences using a target word in varied meanings, translate them into a target language, and show the contextual meaning of the word fo
Manim Idea to Export
Turn plain-language concepts into production-ready ManimCE scene blueprints, runnable code, preview renders, and final export commands for video assets.
Prompt Engineering Patterns
A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat
Claude Code (Clawdbot)
Wrapper to run the local Claude Code CLI in headless or interactive (tmux) modes for code analysis, refactors, tests, and structured output.
OSpec CLI
CLI-driven, document-first workflow for initializing and maintaining change-ready projects and project knowledge with OSpec.