Agent skill
library-detection
Detect project stack from package manifests (package.json, pyproject.toml, go.mod, Cargo.toml, pubspec.yaml, CMakeLists.txt). Auto-identify frameworks, test tools, and build systems for onboarding.
Install this agent skill to your Project
npx add-skill https://github.com/aiskillstore/marketplace/tree/main/skills/consiliency/library-detection
SKILL.md
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
| Variable | Default | Description |
|---|---|---|
| SCAN_DEPTH | 3 | Max directory depth to search for manifests |
| INCLUDE_DEV_DEPS | true | Include development dependencies in analysis |
| DETECT_FRAMEWORKS | true | Identify frameworks from dependencies |
| DETECT_TEST_TOOLS | true | Identify test frameworks and runners |
| OUTPUT_FORMAT | json | Output format: json, markdown, or toon |
Instructions
MANDATORY - Follow the Workflow steps below in order. Do not skip steps.
- Scan for package manifests in the project
- Parse each manifest to extract dependencies
- Classify dependencies into categories
- Detect frameworks and test tools from dependency patterns
- 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):
| File | Language | Parser |
|---|---|---|
package.json |
JavaScript/TypeScript | JSON |
pyproject.toml |
Python | TOML |
requirements.txt |
Python | Line-based |
go.mod |
Go | Go mod |
Cargo.toml |
Rust | TOML |
pubspec.yaml |
Dart/Flutter | YAML |
CMakeLists.txt |
C/C++ | CMake |
meson.build |
C/C++ | Meson |
WORKSPACE |
Bazel | Bazel |
pom.xml |
Java | XML |
build.gradle |
Java/Kotlin | Gradle DSL |
Gemfile |
Ruby | Ruby DSL |
composer.json |
PHP | JSON |
Also check for:
Dockerfile- containerizationdocker-compose.yml- container orchestration.github/workflows/*.yml- CI/CDMakefile- build systemtsconfig.json- TypeScript configvite.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.mdfor 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
| Dependency Pattern | Detected As |
|---|---|
react, react-dom |
React framework |
vue, @vue/* |
Vue framework |
next |
Next.js framework |
fastapi |
FastAPI framework |
django |
Django framework |
flask |
Flask framework |
express |
Express.js framework |
vitest, jest |
JavaScript test framework |
pytest |
Python test framework |
gtest, gmock, catch2 |
C/C++ test framework |
flutter, flutter_test |
Flutter framework |
@testing-library/* |
Testing utilities |
Category Mappings
| Category | Examples |
|---|---|
| frontend | react, vue, svelte, angular |
| backend | fastapi, django, express, gin |
| database | prisma, sqlalchemy, typeorm |
| testing | vitest, jest, pytest, playwright |
| build | vite, webpack, esbuild, rollup |
| linting | eslint, prettier, ruff, black |
| typing | typescript, mypy, pyright |
| build-native | cmake, meson, bazel |
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:
- Documentation discovery: Map detected frameworks to doc sources
- Onboarding: Generate quickstart guides tailored to the stack
- Tool configuration: Auto-configure linters, formatters, test runners
- 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)
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
perigon-backend
Perigon ASP.NET Core + EF Core + Aspire conventions
perigon-agent
Pointers for Copilot/agents to apply Perigon conventions
perigon-angular
Angular 21+ standalone/Material/signal conventions for Perigon WebApp
fastapi-mastery
Comprehensive FastAPI development skill covering REST API creation, routing, request/response handling, validation, authentication, database integration, middleware, and deployment. Use when working with FastAPI projects, building APIs, implementing CRUD operations, setting up authentication/authorization, integrating databases (SQL/NoSQL), adding middleware, handling WebSockets, or deploying FastAPI applications. Triggered by requests involving .py files with FastAPI code, API endpoint creation, Pydantic models, or FastAPI-specific features.
context7-efficient
Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.
browser-use
Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction.
Didn't find tool you were looking for?