write-architecture
Skill1 starsChanged 15 days agoMITView on GitHub
Write a system architecture document — boundaries, data, control flow, and quality attributes. Use when the user asks for architecture, system design, or how the system is shaped. Do not write product code. Do not architecture a local rename.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- rpraharaj/ai-sdlcedited, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- rpraharaj/ai-sdlc★ 036% same
Wrote their own version · 0
None found.
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 repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/AGENTS.mdAGENTS.md
- commitSkill
- cut-releaseSkill
- data-changeSkill
- debugSkill
- engineering-barSkill
- explain-codeSkill
- explore-codebaseSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- lean-reviewSkill
- open-prSkill
- performanceSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- resolve-conflictsSkill
- revert-changeSkill
- review-changeSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- start-projectSkill
- upgrade-depsSkill
- verify-uiSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- write-prdSkill
- write-testsSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Do not implement. Do not invent services, stores, or quality targets this product does not have.
- Very specific: line 26
If the ask is a single feature inside a settled system, say so and offer write-design.
- Very specific: line 28
Read AGENTS.md if present.
- Very specific: line 32
Use the first that exists: docs/architecture/, docs/arch/, architecture/, a path AGENTS.md names.
- Very specific: line 34
If none: write in the reply, and offer to create docs/architecture/ in this repo's markdown style.
- Distinctive: line 46
Quality attributes: use numbers this repo already has, or label them as targets the user set.
- Distinctive: line 55
No secrets, no invented vendors.
- Very specific: line 63
Do not implement. Next is usually record-decision for sticky choices, then write-design for the first initiative.
≈ “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
Write architecture
Describe the durable shape of a system or area. This is not a PRD (write-prd), not a per-initiative design (write-design), and not a one-page ADR (record-decision).
Do not implement. Do not invent services, stores, or quality targets this product does not have.
Is this the right skill?
| Signal | Do this instead |
| What / why for users | write-prd |
| How this feature will be built | write-design |
| One sticky choice (store, API family) | record-decision |
| One implementable slice | shape-work |
| Local rename, one-file change | stop — no architecture doc |
If the ask is a single feature inside a settled system, say so and offer write-design.
Read AGENTS.md if present. If you have not mapped the repo, run explore-codebase first or say the picture is incomplete.
Find the home
Use the first that exists: docs/architecture/, docs/arch/, architecture/, a path AGENTS.md names.
If none: write in the reply, and offer to create docs/architecture/ in this repo's markdown style.
Name the file like existing architecture docs. If there are none, docs/architecture/<area>.md.
Write
Copy headings from references/architecture-template.md in this skill directory. Keep every heading; write n/a when a section does not apply. Do not invent extra sections. If that file is missing, use the same headings: Summary, Context, Scope of this doc, Goals and non-goals, Current state, Actors and systems, Proposed shape (Boundaries, Data, Control flow, Identity and tenancy, External), Deployment and environments, Quality attributes, Data classification, Migration and coexistence, Alternatives considered, Decisions, Risks and operability, Evolution, Open questions, Next.
Fill from evidence:
- Current state names real apps, packages, stores. Greenfield: say so.
- Boundaries are things that can fail or deploy apart — not every folder.
- Quality attributes use numbers this repo already has, or label them as targets the user set. Do not invent SLOs.
- Alternatives considered — at least two, including keep-current when a system exists.
- Decisions point at
record-decisionfor anything expensive to reverse. Do not hide an ADR inside this doc.
Quality
- A new engineer could name where a request enters and where data lives.
- Proposed shape is smaller than a platform rewrite unless the user asked for that.
- Unused sections are
n/a, not deleted. - No secrets, no invented vendors.
Done
- Path or the full text in the reply
- The proposed shape in three to six sentences
- Which ADRs should follow (or none)
Do not implement. Next is usually record-decision for sticky choices, then write-design for the first initiative.
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.