mcpField
D
detect-stack

detect-stack

github.com/jordancoinDevelopment1167 installsUpdated 35w ago
Repository

About detect-stack

detect-stack is a coding skill that scans a project and writes a concise `.agents/stack-context.md` file. It helps coding agents understand the codebase’s languages, frameworks, tests, CI checks, and conventions, and can be rerun when the context becomes stale.

Key features

  1. 01Language and framework detection
  2. 02Test and CI check discovery
  3. 03Convention and structure review
  4. 04Stack context file generation
  5. 05Stale-context rerun guidance

Use cases

  1. 01Preparing an unfamiliar project for coding work
  2. 02Refreshing context after dependency changes
  3. 03Reviewing project checks and conventions

MCP support

It recommends using context7 MCP for framework documentation when specific API details are needed, with web search as a fallback.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/jordancoin/codingskills --skill detect-stack

After installing, type/detect-stackin Claude Code to confirm it loaded.

Details

From the project README

Detect Stack

Analyze the current codebase and generate .agents/stack-context.md. Run this on first use in a project, or when the stack context is missing or stale.

What to Detect

Scan the project root for these signals:

Language — Count file extensions (.rs, .py, .ts, .go, .swift, .java, .rb, .cs, .ex, etc.). Primary = most files. Note secondary languages.

Framework — Read the package manifest:

  • Cargo.toml → check [dependencies] for axum, actix, rocket, sqlx, diesel, tokio
  • package.json → check for react, next, svelte, express, fastify, prisma
  • go.mod → check for gin, echo, fiber, chi, sqlc
  • pyproject.toml / requirements.txt → check for django, flask, fastapi, sqlalchemy
  • Gemfile → check for rails, sinatra
  • Package.swift → check for Vapor; scan for SwiftUI imports
  • mix.exs → check for phoenix, ecto

Tests — Look for test directories, test file naming patterns, test config files.

CI gates — Scan .github/workflows/, .gitlab-ci.yml, etc. for blocking checks (format, lint, type check, test).

Conventions — Check for CLAUDE.md, AGENTS.md, CONTRIBUTING.md. Note directory structure and naming patterns.

Output

Write .agents/stack-context.md — keep it short (under 40 lines):

# Stack Context

Generated: YYYY-MM-DD

## Stack
- **Language**: [primary] [version if pinned]
- **Framework**: [web framework], [db layer]
- **Build**: [build tool]
- **Test**: [test command + framework]
- **Lint**: [linter] [CI gate: yes/no]
- **Format**: [formatter] [CI gate: yes/no]

## Secondary Languages
- [language] ([what it's used for])

## Conventions
- Error handling: [pattern]
- Module structure: [pattern]
- Naming: [pattern]
- Tests: [where they live, how they're organized]

## CI Gates
- [list of blocking checks]

Stack-Specific Principle Application

After writing the stack context, do not generate static reference files. Instead:

  1. Use your built-in knowledge of the detected language/framework to apply each coding principle idiomatically
  2. If you need specific framework API details, use context7 MCP (resolve-library-id then query-docs) to pull live documentation
  3. If context7 doesn't cover it, use web search as fallback

The coding principle skills are language-agnostic by design. You are the bridge between the principles and the stack.

When to Re-Run

  • .agents/stack-context.md doesn't exist
  • Major dependency changes (new framework, language version bump)
  • Project structure significantly changes
  • Context file is older than 30 days

Comments

Markdown supported