interface-critique
Skill0 starsChanged 3 months agoMITView on GitHub
Critique an existing interface against user goals and return prioritized, evidence-based improvements.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessible-interfaceSkill
- color-and-contrastSkill
- design-contextSkill
- design-system-auditSkill
- forms-and-validationSkill
- interaction-and-motionSkill
- layout-and-spacingSkill
- loading-empty-error-statesSkill
- responsive-designSkill
- typographySkill
- visual-hierarchySkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 9
Use this for a holistic critique of a page, flow, screenshot, prototype, or implementation.
- Distinctive: line 12
Do not replace evidence with taste.
≈ “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
Interface Critique
Evaluate how well an existing interface supports its intended users and task. Use this for a holistic critique of a page, flow, screenshot, prototype, or implementation.
Do not replace evidence with taste. Do not redesign everything, praise without analysis, or report a standards failure that was not actually tested.
Workflow
- Establish the user, job, surface, desired outcome, and available evidence. State missing context and bounded assumptions.
- Walk the main path and realistic alternatives. Inspect hierarchy, content, navigation, controls, feedback, states, responsiveness, accessibility, consistency, and trust.
- Record each finding as: observation, affected task or user, consequence, evidence, and recommended direction.
- Distinguish defects from preferences. Tie defects to broken goals, established patterns, system rules, or measurable access and usability risk.
- Prioritize blockers and irreversible loss first, then repeated friction, comprehension, consistency, and polish.
- Preserve what already works. Recommend the smallest coherent set of changes rather than an unrelated visual reinvention.
- Identify what needs live interaction, device, content, analytics, or user testing before it can be confirmed.
Output
Lead with the overall diagnosis, then prioritized findings and a sequenced improvement plan. Separate confirmed evidence, inference, and unverified tests.
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.