Library Detection Skill

Automatically detect the technology stack of a project by analyzing package manifests and configuration files. Returns structured data for use in onboarding, documentation discovery, and tool configuration.

Variables

Instructions

MANDATORY - Follow the Workflow steps below in order. Do not skip steps.

1. Scan for package manifests in the project
2. Parse each manifest to extract dependencies
3. Classify dependencies into categories
4. Detect frameworks and test tools from dependency patterns
5. Output structured stack summary

Red Flags - STOP and Reconsider

If you're about to:

• Assume a framework without checking imports or config files
• Skip manifest files because "the project is simple"
• Hardcode framework versions instead of reading from manifests
• Report a library without verifying it's actually used

STOP -> Read the manifest files -> Verify with imports/configs -> Then report

Workflow

1. Discover Manifests

Scan for these files (in order of priority):

package.json

pyproject.toml

requirements.txt

go.mod

Cargo.toml

pubspec.yaml

CMakeLists.txt

meson.build

WORKSPACE

pom.xml

build.gradle

Gemfile

composer.json

Also check for:

• Dockerfile

  - containerization

• docker-compose.yml

  - container orchestration

• .github/workflows/*.yml

  - CI/CD

• Makefile

  - build system

• tsconfig.json

  - TypeScript config

• vite.config.*

  /

  webpack.config.*

  - bundlers

2. Parse Dependencies

For each manifest, extract:

• Production dependencies: runtime requirements
• Development dependencies: build/test tools
• Peer dependencies: expected host environment
• Optional dependencies: feature flags

3. Classify Stack

Group findings into:

{
  "languages": ["typescript", "python", "go", "rust", "dart", "cpp"],
  "frameworks": [
    {"name": "react", "version": "^18.0.0", "category": "frontend"},
    {"name": "fastapi", "version": "^0.100.0", "category": "backend"}
  ],
  "test_frameworks": [
    {"name": "vitest", "version": "^1.0.0"},
    {"name": "pytest", "version": "^7.0.0"}
  ],
  "build_tools": ["vite", "uv", "docker"],
  "databases": ["postgresql", "redis"],
  "cloud_providers": ["aws", "vercel"],
  "ci_cd": ["github-actions"]
}

4. Framework Detection Patterns

Use the cookbook for specific detection logic:

• Read

  ./cookbook/manifest-parsing.md

  for parsing rules
• Match dependency names against known framework patterns

5. Output

Return the structured stack summary in the requested format.

Cookbook

Manifest Parsing

• IF: Parsing any package manifest
• THEN: Read and execute

  ./cookbook/manifest-parsing.md

Quick Reference

Detection Patterns

react

react-dom

vue

@vue/*

next

fastapi

django

flask

express

vitest

jest

pytest

gtest

gmock

catch2

flutter

flutter_test

@testing-library/*

Category Mappings

Output Schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "type": "object",
  "properties": {
    "project_root": {"type": "string"},
    "scanned_at": {"type": "string", "format": "date-time"},
    "languages": {
      "type": "array",
      "items": {"type": "string"}
    },
    "frameworks": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {"type": "string"},
          "version": {"type": "string"},
          "category": {"type": "string"}
        }
      }
    },
    "test_frameworks": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {"type": "string"},
          "version": {"type": "string"}
        }
      }
    },
    "build_tools": {
      "type": "array",
      "items": {"type": "string"}
    },
    "databases": {
      "type": "array",
      "items": {"type": "string"}
    },
    "cloud_providers": {
      "type": "array",
      "items": {"type": "string"}
    },
    "ci_cd": {
      "type": "array",
      "items": {"type": "string"}
    },
    "manifests_found": {
      "type": "array",
      "items": {"type": "string"}
    }
  }
}

Integration

Other skills and commands can use this skill for:

1. Documentation discovery: Map detected frameworks to doc sources
2. Onboarding: Generate quickstart guides tailored to the stack
3. Tool configuration: Auto-configure linters, formatters, test runners
4. Agent routing: Select appropriate AI providers based on stack

Example usage in another skill:

## Prerequisites

Before implementing, run the `library-detection` skill to identify:
- Test frameworks (for writing tests)
- Build tools (for verification)
- Database libraries (for data layer work)