ask-before-architecture
Skill0 starsChanged 2 months agoMITView on GitHub
Do not choose stack, framework, or architecture alone — ask the user with 2–4 concrete options and a recommendation. Use for greenfield work, major dependencies, or specs with open implementation decisions.
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/automate-before-manual.mdcCursor rule
- .cursor/rules/finish-task-dev-server.mdcCursor rule
- brainstormingSkill
- caveman-commitSkill
- find-skillsSkill
- semantic-versionSkill
- systematic-debuggingSkill
- verification-before-completionSkill
- writing-plansSkill
- automate-before-manualSkill
- caveman-commitSkill
- diagrams-mermaidSkill
- dont-be-lazySkill
- dont-forgetSkill
- find-jobSkill
- finish-with-dev-serverSkill
- google-calendar-mcpSkill
- init-fmzSkill
- instagram-chrome-postSkill
- project-initSkill
- recapSkill
- semantic-versionSkill
- skills-sh-maintainerSkill
- ui-change-e2eSkill
- validate-before-shareSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Before implementing or locking technical decisions, do not choose alone.
- Distinctive: line 18
Test stack, monorepo layout when alternatives exist
- Distinctive: line 19
Default ports or proxy vs CORS when not already in ADR/spec
- Very specific: line 28
Use structured choices (AskQuestion when available): 2–4 options, mark one (Recommended) with one-line why.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Ask before architecture
Before implementing or locking technical decisions, do not choose alone. Ask and wait.
Counts as a decision (must ask)
- Language, framework, UI library, state management
- ORM, migration strategy, API style (REST vs RPC)
- Test stack, monorepo layout when alternatives exist
- Default ports or proxy vs CORS when not already in ADR/spec
Does not need asking
- Following an approved spec or ADR in this repo
- Reading existing conventions from
AGENTS.md,docs/stack.md, code
How to ask
- Use structured choices (
AskQuestionwhen available): 2–4 options, mark one (Recommended) with one-line why. - One decision per message unless the user asked to decide everything at once.
- Stop until the user answers — do not implement in the same turn.
- Record the answer in
docs/superpowers/specs/or an ADR before coding.
Forbidden shortcuts
- "Same as the last project" without confirmation
- Publishing a spec with invented Implementation Decisions after no discussion
- Inferring stack from a single example file
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.

