heuristic-evaluation
Skill32 starsChanged 49 days agoMITView on GitHub
Audit a design against Nielsen's ten usability heuristics, tying every finding to a specific element with a specific fix. Use on a built screen or a detailed mockup.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- henrique-simoes/Istaratheir own version, first seen Sep 27, 2026
- JoaoMonteiro100/ux-design-skillstheir own version, first seen Jul 27, 2026
- miovrag/claude-skillstheir own version, first seen Jun 12, 2026
- launchapp-dev/animus-clitheir own version, first seen Mar 15, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- launchapp-dev/animus-cli★ 39same name
- henrique-simoes/Istara★ 15same name
- miovrag/claude-skills★ 1same name
- JoaoMonteiro100/ux-design-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- application-packSkill
- brief-to-tasksSkill
- design-briefSkill
- design-reviewSkill
- design-tokensSkill
- frontend-designSkill
- grill-meSkill
- information-architectureSkill
- persona-acid-testSkill
- pick-upSkill
- stuckSkill
- wrap-upSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
5
Distinctive
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 8
Ask the user to provide: (1) the design output (HTML file, Figma link, or screenshot), and (2) the target user and their primary task.
- Distinctive: line 25
Do similar elements behave the same way across the product?
- Distinctive: line 43
If a user gets stuck, is there a clear path to help?
- Distinctive: line 45
After all ten heuristics, give a summary:
- Distinctive: line 50
Do not soften findings. A Fail is a Fail.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are running a structured usability audit. Do not produce a general list of suggestions. Every finding must reference something specific and visible in the design the student has shared.
Ask the user to provide: (1) the design output (HTML file, Figma link, or screenshot), and (2) the target user and their primary task. If either is missing, ask for it before starting.
Review against Nielsen's 10 usability heuristics. For each heuristic, give:
- Rating: Pass / Needs work / Fail
- Evidence: one specific example from this design. Name the element, the screen, the exact behaviour
- Fix: one concrete recommendation (not "improve feedback", but "add a spinner to the Submit button when the form is processing so the user knows the action was received")
1. Visibility of system status Does the interface always tell the user what is happening? Are loading states, success states, and error states communicated in real time?
2. Match between system and real world Does the language match what the user already knows? Are icons and metaphors familiar? Does the flow follow conventions the user has encountered elsewhere?
3. User control and freedom Can the user undo, go back, or exit without being punished? Are there clear escape routes from every state?
4. Consistency and standards Do similar elements behave the same way across the product? Does the design follow platform conventions (mobile tap targets, web link underlines, form field labels)?
5. Error prevention Does the design prevent mistakes before they happen? Are destructive actions protected by confirmation? Are required fields marked before submission?
6. Recognition over recall Does the user have to remember things from one screen to apply them on another? Are options visible rather than requiring the user to type them from memory?
7. Flexibility and efficiency of use Can an experienced user move faster? Are there shortcuts, filters, or bulk actions for power users that do not get in the way of first-time users?
8. Aesthetic and minimalist design Does every element on screen serve the current task? Is there anything the user has to process that does not help them complete their goal?
9. Help users recognise, diagnose, and recover from errors Are error messages in plain language? Do they name the problem, explain why it happened, and tell the user exactly what to do next?
10. Help and documentation If a user gets stuck, is there a clear path to help? Are tooltips, empty states, and onboarding written to answer the most common question, not to fill space?
After all ten heuristics, give a summary:
- Total counts: Pass / Needs work / Fail
- Priority fix list: Fail items first, Needs work second, ordered by user impact
- One sentence on the biggest risk if this ships without changes
Do not soften findings. A Fail is a Fail.
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.

