build-app
Skill0 starsChanged 45 days agoMITView on GitHub
Build full-stack applications using the ATLAS framework (5-phase process). Architect, Trace, Link, Assemble, Stress-test. Use when asked to build an app, create a dashboard, make a tool, or develop a full-stack application with database and backend logic. For static websites and landing pages, use build-website instead.
- Reads credentials
11 other projects use a version of this.
Adopted by
Most recently taken up by
- RogyMD/craftappstheir own version, first seen Nov 15, 2026
- playcanvas/skillstheir own version, first seen Oct 12, 2026
- kyle-chalmers/streamsnowtheir own version, first seen Oct 11, 2026
- Pdiamondz1/hma_project_foundationtheir own version, first seen Oct 9, 2026
- butterbase-ai/butterbase-plugintheir own version, first seen Oct 8, 2026
- adventurebeast/concoursetheir own version, first seen Sep 9, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- butterbase-ai/butterbase-plugin★ 535same name
- butterbase-ai/butterbase-skills★ 535same name
- playcanvas/skills★ 43same name
- cm-wada-yusuke/claude-code-product-workshop-kit★ 18same name
- kyle-chalmers/streamsnow★ 17same name
- day-ai/gtm-brain★ 9same name
- RogyMD/craftapps★ 8same name
- geod/oneprompt★ 4same name
- tymrtn/tomorrowkit-for-minds★ 4same name
- adventurebeast/concourse★ 3same name
1 more not listed
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 repository24 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analystSkill
- build-websiteSkill
- business-setupSkill
- content-pipelineSkill
- content-writerSkill
- email-assistantSkill
- email-digestSkill
- ksuite-setupSkill
- meeting-prepSkill
- memorySkill
- odooSkill
- plugin-builderSkill
- qfieldcloudSkill
- qgisSkill
- quarto-slidesSkill
- research-leadSkill
- researchSkill
- r-sessionSkill
- schedulerSkill
- scrum-masterSkill
- skill-creatorSkill
- task-managerSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 64
Rule: Don't write UI until the data layer is validated.
- Distinctive: line 80
Every page needs: loading state, error state, empty state, populated state
- Distinctive: line 82
Never hardcode data — always query the real source
- Distinctive: line 110
Always start with Architect — never jump to code
- Distinctive: line 113
Every state matters — loading, error, empty, populated
“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Build App — ATLAS Framework
Build full-stack applications with databases, auth, and backend logic.
When to Use
- Dashboards and admin panels
- SaaS applications
- Internal tools
- Client portals
- Applications with user accounts and data persistence
NOT for: Static websites, landing pages, portfolios → use build-website instead.
The ATLAS Framework
A — Architect
Define the problem space before writing code.
- Problem statement — What problem does this solve? For whom?
- User stories — 3-5 key user stories (As a [role], I want [action], so that [benefit])
- Success metrics — How do we know it works? (specific, measurable)
- Constraints — Timeline, budget, tech requirements, integrations
- Non-goals — What this app explicitly does NOT do (prevents scope creep)
Output: Architecture document with problem, users, stories, metrics, constraints.
T — Trace
Map the data and integration layer.
- Data schema — Tables, relationships, constraints (draw the ERD mentally)
- API design — Endpoints, methods, request/response shapes
- Integrations — External services, webhooks, OAuth providers
- Auth model — Who can do what? (roles, permissions, row-level security)
- Stack proposal — Framework, database, hosting (justify each choice)
Recommended stack:
- Frontend: Next.js or React + Tailwind
- Backend: Supabase (Postgres + Auth + Realtime + Storage + Edge Functions)
- Alternative: SQLite + Express for simple tools
Output: Schema diagram, API spec, stack decision with rationale.
L — Link
Validate connections before building.
- Database setup — Create tables, enable RLS policies, test queries
- Auth flow — Sign up, sign in, role assignment, session handling
- API test — Hit each endpoint, verify response shapes
- Integration test — Connect external services, verify data flow
- Environment — All keys in .env, all configs in config/
Rule: Don't write UI until the data layer is validated. Nothing is worse than building a frontend on a broken backend.
A — Assemble
Build the application, layer by layer.
Build order:
- Database migrations and seed data
- Backend API / Edge Functions
- Auth integration
- Core UI layout (navigation, routing)
- Feature pages (one at a time, fully functional before moving on)
- Polish (loading states, error states, empty states)
Rules:
- One feature at a time — complete before starting the next
- Every page needs: loading state, error state, empty state, populated state
- API calls should have proper error handling and user feedback
- Never hardcode data — always query the real source
S — Stress-test
Quality assurance before shipping.
- Functional tests — Every user story works end-to-end
- Edge cases — Empty data, missing fields, expired tokens, concurrent users
- Security — SQL injection, XSS, auth bypass, RLS verification
- Performance — Page load < 2s, API response < 500ms, no N+1 queries
- Mobile — Responsive at all breakpoints
- User acceptance — Does it actually solve the problem from step A?
Extensions
+V — Validate (Security Deep Dive)
- OWASP Top 10 checklist
- Penetration testing for auth flows
- Rate limiting and abuse prevention
+M — Monitor (Production Readiness)
- Error tracking (Sentry or equivalent)
- Logging for critical operations
- Uptime monitoring
- Analytics for usage patterns
Rules
- Always start with Architect — never jump to code
- Database before frontend — validate data layer first
- One feature at a time — resist the urge to parallelize
- Every state matters — loading, error, empty, populated
- Security is not optional — RLS, input validation, auth checks
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.

