Structured UX evaluation: heuristic scoring, walkthroughs, dark-pattern scans
Run structured UX evaluations — Nielsen heuristic evaluation with every heuristic scored 0–4 and a 0–100 UX Health Score, every finding rated P0 to P3, cognitive walkthroughs, anti-pattern/dark-pattern detection with severity, task success analysis — and route every finding to the Intent specialist skill that fixes it
- What
- Run structured UX evaluations — Nielsen heuristic evaluation with every heuristic scored 0–4 and a 0–100 UX Health Score, every finding rated P0 to P3, cognitive walkthroughs, anti-pattern/dark-pattern detection with severity, task success analysis — and route every finding to the Intent specialist skill that fixes it
- Cost
- Free
- Needs
- a user experience to evaluate (a live product, a prototype, or a design); nothing else — no accounts or keys required. This skill is an evaluation methodology the agent follows, not software to install.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @ghaida's Evaluate skill, the diagnostic entry point of the Intent design-strategy system (the UX doctor that diagnoses and refers to specialists): a systematic methodology, not a vague design review. Five core capabilities — heuristic evaluation against Nielsen's 10 heuristics, every heuristic scored 0 to 4 (0 no issues, 1 cosmetic, 2 minor, 3 major, 4 catastrophic) with specific evidence, rolled up into a 0–100 UX Health Score composite across heuristics, task success, and anti-patterns, and every finding rated on the P0 to P3 severity scale; cognitive walkthroughs, asking four questions per task step (will the user try the right effect? notice the action is available? associate the action with the effect? see progress afterward? — rated Pass/Hesitation/Failure); anti-pattern detection across the Intent catalog (deceptive patterns, prechecked consent, fake urgency/scarcity, addictive design, attention exploitation, weaponized accessibility, vulnerable-user exploitation, AI-specific dark patterns — dark-pattern findings are always P0 or P1, with regulatory implications noted); task success analysis (completion, efficiency, error rate, recovery, satisfaction — estimated explicitly when no live data exists); and assessment-to-action routing, where every finding maps to the specialist skill that owns the fix (/organize, /articulate, /journey, /fortify, /include, /blueprint, /measure, /investigate, /strategize, /specify, /philosopher). A fixed output format (UX Health Score, Anti-Pattern Verdict, priority issues grouped P0–P3, Heuristic Scores, walkthrough results, positive findings, recommended actions grouped by skill), plus the protagonist-arc storytelling pattern applied to failure points. Honest caveats: diagnosis only — it identifies and prioritizes problems but does NOT fix them; the specialist skills are not bundled here; score honestly by design (a health score of 85 means the experience is genuinely good — don't inflate, don't deflate). Updated November 18, 2026: the previous description wrongly said the numeric scores were gone and each heuristic ended in a word verdict — that described the unscored 1.7.1 methodology, not the pinned 1.6.0, which scores. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Structured UX evaluation is a free Muse skill that runs structured UX evaluations. It performs heuristic evaluation against Nielsen's ten heuristics, rating every violation from P0 to P3 and closing each heuristic with a verdict in words, plus cognitive walkthroughs, anti-pattern and dark-pattern detection with severity, and task success analysis, routing every finding to the Intent specialist that fixes it.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit b89a519Before you start: tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead. Prerequisites: a user experience to evaluate (a live product, a prototype, or a design); nothing else — no accounts or keys required. This skill is an evaluation methodology the agent follows, not software to install. Install "Structured UX evaluation: heuristic scoring, walkthroughs, dark-pattern scans" for me. It gives my agent @ghaida's Evaluate methodology, version 1.6.0, the diagnostic entry point of the Intent design system. It runs a heuristic evaluation against Nielsen's 10 heuristics: every heuristic is scored 0 to 4 — 0 no issues found, 1 cosmetic, 2 minor, 3 major, 4 catastrophic (must fix before release) — and the scores roll up into a UX Health Score, a 0–100 composite across heuristics, task success, and anti-patterns. Every finding is also rated by severity, P0 critical (blocks core task completion or violates regulations) to P3 cosmetic. It runs cognitive walkthroughs (four questions per step — will the user try the right effect? notice the action is available? associate the action with the effect? see progress afterward? — each step rated Pass, Hesitation, or Failure). It scans the experience against the Intent anti-pattern catalog (deceptive patterns, prechecked consent, fake urgency, addictive design, weaponized accessibility, AI-specific dark patterns — dark patterns are always P0 or P1). It analyzes task success (completion, efficiency, error rate, recovery, satisfaction — estimated explicitly when no live data exists), and documents what works well, not just what fails. Every finding states what the issue is, where it occurs, why it matters, and which Intent specialist skill owns the fix; the report follows a fixed format — UX Health Score, Anti-Pattern Verdict, Priority Issues (P0 to P3), Heuristic Scores, Cognitive Walkthrough Results, Positive Findings, Recommended Actions — and states what was evaluated and what was not. Score honestly: a health score of 85 means the experience is genuinely good — don't inflate scores to be polite, don't deflate them to seem rigorous. Source: https://raw.githubusercontent.com/ghaida/intent/b89a519eb570fe7ec61de1eb51f553af0306b515/skills/evaluate/SKILL.md (the skill is the single SKILL.md file in the skills/evaluate folder of the ghaida/intent repository) Pinned version: install the code at commit b89a519eb570fe7ec61de1eb51f553af0306b515 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Updated November 18, 2026: Skill Harbor rewrote this install prompt because the previous version described a different, newer, unscored version of the methodology — version 1.7.1, regenerated on October 11, 2026 from the upstream file of the day — while the pinned install is version 1.6.0, which scores. The old prompt's note that the numeric scores had disappeared is withdrawn: it is false for the pinned version, which scores every heuristic 0–4 and reports a 0–100 composite UX Health Score. The fingerprint in the old prompt did not match the pinned file, so its integrity check would have failed on the file this prompt installs. This version describes the pinned version exactly: 27,307 bytes, 296 lines, version 1.6.0, at commit b89a519eb570fe7ec61de1eb51f553af0306b515. What changed: the scores are back — 0–4 per heuristic, UX Health Score 0–100, Heuristic Scores as a report section — and the word verdicts per heuristic are gone. What did not change: the P0–P3 severities with dark patterns always P0 or P1, the four-question walkthroughs rated Pass/Hesitation/Failure, the anti-pattern catalog, the task success analysis, the routing to the specialist Intent skills, and the rule to state what was evaluated and what was not. 1. Download the SKILL.md file into a temporary folder. 2. Compare the file with the fingerprint from Skill Harbor's review of 2026-11-18: - SKILL.md: SHA-256 9d791c3aed3efd444f26eacc878a8f2f07ba198b5b2e4ef31176c7f1a5d3100f If it does not match, the file changed since the review: do not install it yet — tell me what you found and let me decide. 3. Read the file and tell me in plain words: what the skill does when used, whether it connects to a service, whether it reads or sends any personal information or keys, and anything that seems unusual. 4. When I say yes, copy SKILL.md into my skills folder, in a folder named "evaluate". 5. Check the copy opens correctly (valid frontmatter, files in place) and tell me what was installed, where, and what is left for me to do (for example, hand the agent the experience to evaluate and its scope — which flows, which device, what was not assessed; the specialist Intent skills that own the fixes are separate skills, not included here). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Rules: only touch the temporary folder and the install target. If something seems off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
Files that changed since our review
- SKILL.md · changed on 2026-11-18 · SHA-256 78dea649f550 → 7ebd3b2e97d1
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- b89a519 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.