nielsen-heuristics
Nielsen Heuristics Validator
Mascot:
assets/jakob-nielsen.png— a line-art portrait of Jakob Nielsen. Surface it (embed or attach) when producing a rendered/HTML report or a shareable summary, as the evaluation's signature. It is an output asset, not context to read while evaluating.
Run a rigorous, evidence-disciplined heuristic evaluation against Jakob Nielsen's 10 usability heuristics (Nielsen & Molich 1990, refined 1994). The value over an ad-hoc "critique this UI" prompt is a consistent rubric plus honesty guards: sharp per-heuristic probes, a per-finding severity scale, a mandatory evidence-locator requirement, and correct handling of artifacts that have no observable interface.
Scope guard (read first)
This skill does ONE thing: a formal heuristic inspection. It does NOT run a parallel accessibility (WCAG) audit, performance audit, or general design critique. Flag an accessibility issue only when it is also a heuristic violation (e.g., an invisible focus state violates H1: visibility of system status). If the user wants comprehensive multi-dimension auditing, defer to the impeccable:audit skill instead.
Step 1 — Detect artifact type and select a mode
Heuristic evaluation is an inspection of an interface. Some inputs have one to observe; some only describe one that does not yet exist. Detect the input type, then announce the mode and why.
Evaluation mode (observable interface → findings are severity-scored):
- Screenshot / image — read it visually.
- Live URL — drive it with browser tools to observe states and flows.
- Codebase / HTML page — grep and read the UI source.