design-judgment-scorecard
Skill4 starsChanged 20 days agoMITView on GitHub
Evaluate a product design against its user task, product intent, evidence, and quality bar, producing explainable findings rather than vague taste. Use for comparing or reviewing flows, prototypes, and implemented interfaces. Do not claim complete product evaluation when context is missing.
In this repository9 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 13
If the goal or task is missing, limit the review to observable craft and accessibility issues and state the limitation.
- Distinctive: line 16
When comparison helps, use 0–3 behavioral anchors within the current brief.
- Distinctive: line 34
Do not turn personal style preference into a universal UX law.
- Distinctive: line 35
Avoid labels such as “premium” or “clean” without observable criteria.
≈ “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
Design Judgment Scorecard
Turn “this feels wrong” into evidence, impact, tradeoffs, and a next decision while preserving human ownership of ambiguous taste.
Review
- Confirm the artifact, intended user, critical task, product decision, and known constraints.
- If the goal or task is missing, limit the review to observable craft and accessibility issues and state the limitation.
- Select only relevant dimensions: intent alignment, conceptual coherence, hierarchy, interaction clarity, state coverage, content, accessibility, visual craft, trust, and distinctiveness.
- For each finding, write
evidence → impact → recommendation → confidence → verification. - When comparison helps, use 0–3 behavioral anchors within the current brief. Do not calculate a context-free total score.
- Separate automatic fixes, human tradeoffs, and questions requiring user evidence.
- Recommend at most three next actions ranked by failure risk and learning value.
Output
## Decision under review
## Context and missing evidence
## Scorecard
| Dimension | 0–3 | Evidence | Impact | Confidence |
## Priority findings
## Human decisions required
## Next validationBoundaries
- Do not turn personal style preference into a universal UX law.
- Avoid labels such as “premium” or “clean” without observable criteria.
- Visual polish does not repair an incorrect conceptual model.
- Accessibility checks do not replace usability evidence.
- Record what should remain unchanged so revision does not erase confirmed intent.
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.

