design-architecture
Skill1 starsChanged 5 months agoMITView on GitHub
Define system structure, module boundaries, and data flow for the SaaS app. Record significant decisions as ADRs. Drafts architecture.md then awaits approval.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- etr/groundworktheir own version, first seen Nov 8, 2026
- foryouself83/harness-tiertheir own version, first seen Oct 13, 2026
- Omerfaruk-aydn/Agent_OStheir own version, first seen Jul 20, 2026
- SenolIsci/mykgtheir own version, first seen May 27, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- SenolIsci/mykg★ 81same name
- etr/groundwork★ 45same name
- foryouself83/harness-tier★ 10same name
- Omerfaruk-aydn/Agent_OS★ 1same 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 repository22 other files it gives its agents.
- build-featureSkill
- code-reviewSkill
- compliance-checkSkill
- design-pricingSkill
- design-schemaSkill
- design-uiSkill
- helpSkill
- launch-checklistSkill
- map-flowsSkill
- qa-planSkill
- scope-checkSkill
- security-auditSkill
- setup-billingSkill
- setup-deploySkill
- setup-stackSkill
- startSkill
- studio-statusSkill
- test-setupSkill
- threat-modelSkill
- validate-ideaSkill
- write-prdSkill
- write-testsSkill
The file
Files
Produce a lightweight but durable architecture document that records how the Next.js, Supabase, and Stripe layers interact, where the module boundaries sit, and why key decisions were made. Non-autonomous: every significant decision is surfaced as an option before it is recorded.
Phases
- Load context — read
docs/specs/prd.mdanddocs/specs/flows.md. If neither exists, stop and direct the user to earlier skills. Identify the top architectural concerns implied by the feature list (e.g., multi-tenancy, file uploads, scheduled jobs, real-time updates). - Propose system layers — present a concise layer diagram in text: (1) Next.js App Router pages and server components, (2) server actions / route handlers as the API surface, (3) Supabase Postgres with RLS as the data store, (4) Supabase Auth for identity, (5) Stripe for billing. Ask the user to confirm or amend this model.
- Define module boundaries — propose the top-level directory structure under
app/,lib/,components/, andsupabase/. Call out which paths are tenant-scoped and how the tenant ID flows through the request. Present for approval. - Surface and decide ADRs — for each significant decision (e.g., "use server actions vs. route handlers for mutations", "use Supabase Realtime vs. polling", "row-level security strategy"), present the options with trade-offs, recommend one, and record the user's choice as an ADR using
.claude/templates/adr.md. Each ADR goes indocs/specs/adr/NNNN-{slug}.md. - Write architecture doc — fill
docs/specs/architecture.mdwith the approved layer diagram, module map, and ADR index. Underfullreview, present each section; underlean/solo, write after a single confirmation. - Next step — on approval, point to
/design-schemato translate the architecture into database tables.
Output
docs/specs/architecture.md + one docs/specs/adr/NNNN-{slug}.md per decision. Writes nothing without approval.
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.

