stack-designer
Skill8 starsChanged 14 days agoMITView on GitHub
Design the layered technology stack shown in the System tab.
In this repository22 other files it gives its agents.
- development/AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- backbone-designerSkill
- contract-designerSkill
- control-flow-designerSkill
- deployment-designerSkill
- gui-designerSkill
- module-designerSkill
- storage-contract-designerSkill
- use-case-designerSkill
- tandemSkill
- backbone-designerSkill
- contract-designerSkill
- control-flow-designerSkill
- deployment-designerSkill
- gui-designerSkill
- module-designerSkill
- stack-designerSkill
- storage-contract-designerSkill
- use-case-designerSkill
- brainstorm-whiteboardSkill
- tandemSkill
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 9
Use this method only when technologies, frameworks, or protocols materially shape the design or require user review.
- Very specific: line 34
After incorporating any Module or Deployment method output, persist { systemStacks } through submit_system_block.
≈ “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 Designer
Use this method only when technologies, frameworks, or protocols materially shape the design or require user review. Omit it when implementation-agnostic or already determined.
Emit exactly one systemStacks[0] with two to six ordered layers. Each layer contains:
- a stable ID and short name;
- one responsibility;
- one to four concrete technologies, each with a short role.
Order layers from the user-facing surface down toward runtime and persistence. Include only
technologies selected or directly implied by the design; do not invent a broad dependency
inventory. Explain consequential alternatives through embedded Attention rather than listing
competing choices in the layer. Produce one concise system aspect. Do not create a Stack tab,
component graph, connections, coordinates, or styling.
Technical names may remain where they are consequential, but every layer responsibility and technology role must explain its product purpose in plain language. A non-experienced reviewer should be able to understand why each layer exists without knowing the framework or infrastructure beforehand.
Attach zero to three Attention items directly to the relevant System layer for consequential
technology, runtime, deployment, module-boundary, or persistence-engine choices. Each item has
id, impact, question, whyItMatters, and two or three { option, implication }
alternatives. JSON versus SQLite belongs here.
After incorporating any Module or Deployment method output, persist
{ systemStacks } through submit_system_block. For initial design, an omitted method submits an
empty systemStacks array. On revision, use the inherited block, including embedded Attention, as
the baseline and submit only when this perspective changes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

