qyndexqyndex/claude-init/.claude/skills/framework-detector/SKILL.md

framework-detector

Skill2 starsChanged 5 months agoMITView on GitHub

Maps a detected stack (from `detect-stack` / atlas) to the framework-specific SKILL.md that should be activated for this session. Invoke once at session start, or whenever a new spec mentions a stack that isn't already loaded. Reads `.claude/memory/atlas/STACK.md` and emits a list of skills to consult.

In this repository60 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- animation-disciplineSkill
- api-versioningSkill
- autopilotSkill
- browser-e2eSkill
- characterizeSkill
- clarifySkill
- codemodSkill
- constitution-compactSkill
- constitutionSkill
- context-budgetSkill
- creative-webSkill
- db-migrationSkill
- debugSkill
- detect-stackSkill
- dispatch-criteriaSkill
- dreamSkill
- experimentSkill
- fastapiSkill
- flag-cleanupSkill
- flag-rolloutSkill
- flask-realtimeSkill
- front-end-designSkill
- grill-meSkill
- handoffSkill
- image-generationSkill
- implementSkill
- initiativeSkill
- instinctSkill
- loopSkill
- nextjsSkill
- observabilitySkill
- okr-alignSkill
- parallel-swarmSkill
- pivotSkill
- planSkill
- pr-bodySkill
- prime-disciplineSkill
- prod-observabilitySkill
- react-nodeSkill
- react-viteSkill
- release-trainSkill
- researchSkill
- reviewSkill
- security-guardSkill
- self-healSkill
- shipSkill
- skill-creatorSkill
- specifySkill
- tailwind-disciplineSkill
- tasksSkill
- tdd-loopSkill
- token-budgetSkill
- typographySkill
- verify-loopSkill
- verifySkill
- wip-checkpointSkill
- <kebab-case-skill-name>Skill

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

Very specific:
When detect-stack produces its manifest, it now also writes the *recommended skill list* to .claude/memory/atlas/SKILL_HINTS.md:
line 44

≈ “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

Framework detector

A routing skill. It does no work itself — it reads the atlas and tells you which framework-specific skill(s) to load.

Inputs

.claude/memory/atlas/STACK.md — produced by detect-stack (bash .claude/scripts/atlas-refresh.sh)
Optional override: spec frontmatter stack: field

Routing table

Detected `frameworks.web`	Detected `frameworks.api`	Skill to activate
Vite-React	(none)	`.claude/skills/react-vite/SKILL.md`
Vite-React	Express \| Fastify \| Hono \| NestJS	`react-vite` + `react-node`
Next.js (App or Pages)	Express \| Fastify \| Hono \| (same Next.js)	`react-node` (+ proposed `nextjs` when seeded)
Remix	any Node	`react-node` (+ proposed `remix` when seeded)
(any React)	tRPC	`react-node`
(none)	Flask	`flask-realtime` if SocketIO present, else proposed `flask-rest`
(none)	FastAPI	proposed `fastapi`
(none)	Django	proposed `django`
(none)	Rails	proposed `rails`
(none)	Gin / Fiber / Echo	proposed `go-web`
(none)	Axum / Actix / Rocket	proposed `rust-web`

How to use

Read the atlas:
```
cat .claude/memory/atlas/STACK.md
```
Look up the row in the routing table.
Reference the skill file by path in your reasoning — Claude Code's progressive disclosure loads it on demand. Do NOT inline the skill body.
If the row says "proposed": that skill isn't seeded yet. File a mcp__ccd_session__spawn_task to draft it, then proceed with general principles from the relevant .claude/rules/{frontend,backend}.md.

Update to `detect-stack`

When detect-stack produces its manifest, it now also writes the recommended skill list to .claude/memory/atlas/SKILL_HINTS.md:

# Recommended framework skills (auto-generated)
- React + Vite detected → load `.claude/skills/react-vite/SKILL.md`
- Flask + SocketIO detected → load `.claude/skills/flask-realtime/SKILL.md`

This file is short (10–20 lines), cheap to keep in context, and gives the architect/implementer agents an unambiguous "load this" signal on every session.

When NOT to invoke

Single-file scripts, throwaway repos, no package.json / pyproject.toml — atlas is empty, no routing to do.
The user explicitly says "ignore the stack, just edit this file".

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