stack-rules
Skill8 starsChanged 3 months agoMITView on GitHub
Enforces this kit's standards for Next.js, React, Supabase and Vercel work. Use when writing or reviewing UI components, API routes, database schemas or queries, deployment config, styling, animations, accessibility, performance, state management or tests, or when running a pre-ship audit. Covers shadcn/ui patterns, Zod-validated App Router routes, RLS policies, Core Web Vitals budgets and WCAG contrast.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- MKS-01/appscreenmaptheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- MKS-01/appscreenmap★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- hud/CLAUDE.mdCLAUDE.md
- agent-setupSkill
- asaSkill
- audio-briefSkill
- call-coachSkill
- clone-siteSkill
- courseworkSkill
- creative-videoSkill
- debuggingSkill
- deep-researchSkill
- demoSkill
- graph-engineeringSkill
- gtm-engineeringSkill
- hudSkill
- interfaceSkill
- jev-browseSkill
- kit-builderSkill
- life-contextSkill
- life-opsSkill
- list-auditSkill
- mac-actSkill
- mac-appsSkill
- mac-briefSkill
- mac-controlSkill
- mac-debugSkill
- mac-followupsSkill
- mac-permissionsSkill
- mac-runtimeSkill
- mac-seeSkill
- peopleSkill
- prospect-briefSkill
- repo-healthSkill
- reviewing-changesSkill
- second-brainSkill
- setupSkill
- shippingSkill
- site-specSkill
- skill-forgeSkill
- skill-trainingSkill
- study-guideSkill
- study-systemSkill
- textsSkill
- what-can-this-doSkill
- your-dataSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 19
Read the specific file before writing code in its area.
- Very specific: line 43
When a task spans areas, read each relevant file.
≈ “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.
Files
Stack rules
Twelve standards files for the stack this kit assumes. They load only when the work actually touches the relevant area, which is the point: importing all of them on every session costs roughly 12,500 tokens, and a Python service that will never render a button should not pay for the Tailwind rules.
The six genuinely universal standards (git, security, writing, naming,
typescript, review-discipline) are not here. Those are @-imported by
CLAUDE.md and always in context, at about 3,700 tokens.
Which file to read
Read the specific file before writing code in its area. Do not read all twelve.
| Working on | Read |
| React components, shadcn/ui, loading/empty states | references/components.md |
| API routes, Zod validation, error shapes | references/api.md |
| Supabase schema, RLS, migrations, queries | references/database.md |
| Vercel deploys, env vars, pre-deploy checks | references/deployment.md |
| Color, typography, spacing, the visual system | references/design.md |
| Images, fonts, bundle size, Core Web Vitals | references/performance.md |
| React Query, URL state, Zustand, form state | references/state.md |
| Semantic HTML, focus, ARIA, WCAG contrast | references/accessibility.md |
| Scroll animations, parallax, reveal effects | references/scroll-effects.md |
| Unit, integration, and E2E tests | references/testing.md |
| Hick's, Fitts's, Miller's, layout decisions | references/ux-laws.md |
| Pre-ship audit across all six lenses | references/audit.md |
How to apply them
These are standards, not suggestions. When a file says "never build a custom button, use shadcn/ui," that is the expected output, not one option among several. If a rule genuinely does not fit the project, say so and explain why rather than quietly ignoring it.
When a task spans areas, read each relevant file. Building a settings page that
saves to Supabase means components.md, state.md, and database.md, plus
accessibility.md before it ships.
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
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.