design-note
Skill0 starsChanged 5 months agoMITView on GitHub
Write a structured design note for a feature or change BEFORE building it — problem, the core reframe/insight, the design with options and tradeoffs, edge cases, and the open questions to decide at build time. Use when scoping a feature, weighing approaches, or capturing a design decision so it can be built (or resumed) later. Produces a <feature>-DESIGN.md.
In this repository10 other files it gives its agents.
- claude-md-auditSkill
- coverage-auditSkill
- failure-scanSkill
- handoffSkill
- memory-auditSkill
- noteSkill
- orchestrateSkill
- public-readySkill
- scaffold-mcpSkill
- verify-mcpSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Don't interrogate — pull what you can from the codebase, ask only the gaps.
≈ “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
/design-note
Capture a design as a structured note before building, so the thinking is
explicit and a future session — or another person — can build it cold. Produces
a <feature>-DESIGN.md in the repo.
Gather (ask only what you can't infer)
- What's being designed, and why now.
- The constraints that actually matter (existing system, scale, who uses it).
Don't interrogate — pull what you can from the codebase, ask only the gaps.
The note's structure — use these sections, in order
Open with a title and a status line:
# <Feature> — design note then **Status:** DESIGN, not built. <date>
- Problem / motivation — what's broken or missing, and why it's worth solving. Concrete, not abstract.
- Core reframe — the one insight that makes the right design obvious (often "it's actually X, not Y"). If you can't name one yet, that's a signal to think more before building.
- The design — options with tradeoffs — the real candidates, each with its tradeoff. Recommend one and say why. Never present a single path as if no alternative existed.
- Edge cases — the cases that break a naive version, named so they're handled on purpose.
- Open questions (decide at build time) — what you're deliberately not deciding yet, listed so it isn't forgotten.
- Rollout / cost (only if it touches a deployed or outward-facing surface) — what shipping it costs or risks, and what must be confirmed before deploy.
Principles
- Options with tradeoffs, not one path. A note presenting one option hasn't done the work.
- Name the reframe. The best designs hinge on a single insight — surface it.
- Honest about what's undecided. Open questions are a feature, not a gap.
- Don't pad. A short note that names the reframe and the key tradeoff beats a long one that lists everything.
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.

