agentleFS
Sign inStart free
qyndexqyndex/claude-init/.claude/skills/detect-stack/SKILL.md

detect-stack

Skill2 starsChanged 5 months agoMITView on GitHub

Detect the project's tech stack(s) — frameworks, ORMs, build tools, test runners — from lockfiles and config files. Returns a structured manifest. Used by atlas-refresh, lint dispatcher, stale-deps workflow. Round 8 C.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After detection completes, consult .claude/skills/framework-detector/SKILL.md which maps the detected frameworks.{web,api} pair to a seeded …

    line 122

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Detect stack

A pure-function skill: scan the repo, return a manifest of what's present.

Output schema

{
  "languages": ["typescript", "python"],
  "frameworks": {
    "web": "Next.js 14 (App Router)",
    "api": "tRPC 11",
    "orm": "Prisma 5",
    "styles": "Tailwind CSS 3"
  },
  "build_tools": ["pnpm", "turbo"],
  "test_frameworks": ["vitest", "playwright"],
  "lockfiles": ["pnpm-lock.yaml", "package.json", "tsconfig.json"],
  "monorepo": true,
  "monorepo_tool": "turborepo",
  "primary_stack": "typescript"
}

Detection rules

Languages (from lockfiles/manifests)

LockfileLanguage
package.json + (*.ts OR tsconfig.json)TypeScript
package.json (no TS)JavaScript
pyproject.toml / requirements.txt / setup.pyPython
Cargo.tomlRust
go.modGo
pom.xml / build.gradle(.kts)Java/Kotlin
GemfileRuby
composer.jsonPHP
*.swiftSwift
*.kt (Android)Kotlin
*.dart (Flutter)Dart

Web frameworks

SignalFramework
next.config.{js,mjs,ts} + app/ dirNext.js (App Router)
next.config.* + pages/ dirNext.js (Pages Router)
remix.config.*Remix
vite.config.* + ReactVite-React
vue.config.* / nuxt.config.*Vue / Nuxt
angular.jsonAngular
astro.config.*Astro
svelte.config.*SvelteKit

API frameworks

SignalFramework
@trpc/server in depstRPC
express in depsExpress
fastify in depsFastify
@nestjs/coreNestJS
honoHono
fastapi in pyprojectFastAPI
djangoDjango
flaskFlask
railsRails
actix-web / axum / rocketRust web
github.com/gin-gonic/gin / gofiber/fiberGo web

ORMs

SignalORM
prisma/schema.prismaPrisma
drizzle/schema.ts / drizzle.config.*Drizzle
typeorm in depsTypeORM
sqlalchemySQLAlchemy
alembic.iniAlembic (migrations)
activerecordActiveRecord
gorm.io/gormGORM
diesel.tomlDiesel

Monorepo tools

SignalTool
turbo.jsonTurborepo
nx.jsonNx
pnpm-workspace.yamlpnpm workspaces
lerna.jsonLerna
Workspace cargo + multiple Cargo.tomlCargo workspaces

Test frameworks

SignalFramework
vitest.config.* / vitest in depsVitest
jest.config.* / jest in depsJest
playwright.config.* / @playwright/testPlaywright
cypress.config.*Cypress
pytest.ini / pytest in depspytest
*_test.go filesgo test
cargo test (always available)cargo test
rspec in GemfileRSpec

Implementation

The detection logic lives in .claude/scripts/atlas-refresh.sh. This skill file documents the schema + rules. Direct script invocation: bash .claude/scripts/atlas-refresh.sh writes the atlas; bash .claude/scripts/detect-stacks.sh (Round 8 B) gives the simpler stacks-only list.

When this skill is invoked

  • Nightly via .claude/routines/atlas-refresh.yml
  • On-demand via /atlas refresh
  • Pre-spec via architect.md workflow step 1 (reads atlas)
  • Pre-implement via implementer.md workflow step 1 (reads atlas)

Hand-off to framework-specific skills

After detection completes, consult .claude/skills/framework-detector/SKILL.md which maps the detected frameworks.{web,api} pair to a seeded .claude/skills/<stack>/SKILL.md (e.g. react-vite, react-node, flask-realtime). The detector writes .claude/memory/atlas/SKILL_HINTS.md so the implementer/architect agents pick up the right skill without re-running detection.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free