lyndonkl/design-evaluation-audit
skills/design-evaluation-audit/SKILL.md
Systematically evaluates existing designs against cognitive science principles using repeatable checklists, scoring rubrics, and severity-classified fix recommendations. Use when conducting design reviews or critiques, evaluating designs for cognitive alignment, performing quality assurance before launch, diagnosing usability issues, or choosing between design alternatives with objective criteria.
$ install --global
skillsauthnpx skillsauth add lyndonkl/claude design-evaluation-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 6:27 AM9.2s4 files scanned
SKILL.md
- name:
- design-evaluation-audit
- description:
- Systematically evaluates existing designs against cognitive science principles using repeatable checklists, scoring rubrics, and severity-classified fix recommendations. Use when conducting design reviews or critiques, evaluating designs for cognitive alignment, performing quality assurance before launch, diagnosing usability issues, or choosing between design alternatives with objective criteria.
Design Evaluation & Audit
Table of Contents
- Skill Boundaries
- Design Review Workflow
- Path Selection Menu
- Path 1: Run Cognitive Design Checklist
- Path 2: Run Visualization Audit
- Path 3: Combined Review
- Quick Reference
- Guardrails
Skill Boundaries
Use instead of this skill for:
- Creating new designs from scratch: use
cognitive-design - Learning cognitive theory: use
cognitive-designPath 1 - Detecting misleading visualizations: use
cognitive-fallacies-guard
Design Review Workflow
Time: 30-90 minutes depending on scope
Copy this checklist and track your progress:
Design Evaluation Progress:
- [ ] Step 1: Systematic Assessment
- [ ] Step 2: Visualization Quality Audit (if applicable)
- [ ] Step 3: Severity Classification & Prioritization
- [ ] Step 4: Fix Recommendations
Step 1: Systematic Assessment
Apply the Cognitive Design Checklist across all 8 dimensions: Visibility, Visual Hierarchy, Chunking, Simplicity, Memory Support, Feedback, Consistency, Scanning Patterns. Check every item. Record pass/fail for each dimension with specific evidence.
Resource: Cognitive Design Checklist
Step 2: Visualization Quality Audit (if applicable)
If the design includes data visualizations, apply the 4-Criteria Visualization Audit. Score each criterion 1-5: Clarity, Efficiency, Integrity, Aesthetics. Calculate average and identify weakest dimension.
Resource: Visualization Audit Framework
Step 3: Severity Classification & Prioritization
Classify every finding by severity:
- CRITICAL: Integrity violations, accessibility failures, users cannot complete core tasks. Fix immediately.
- HIGH: Clarity/efficiency issues preventing use, missing feedback for critical actions, working memory overload (>10 ungrouped items). Fix before launch.
- MEDIUM: Suboptimal patterns, aesthetic issues, minor inconsistencies. Fix in next iteration.
- LOW: Minor optimizations, polish items. Fix when convenient.
Priority rule: Fix foundation-first — perception before coherence, integrity before aesthetics, critical before high.
Step 4: Fix Recommendations
For each finding, document:
- What is wrong — specific description with evidence
- Why it matters — which cognitive principle is violated
- How to fix — concrete, actionable recommendation
- Expected outcome — what improves after the fix
- Effort estimate — quick fix (minutes), moderate (hours), significant (days)
Verify fixes don't harm other dimensions.
Path Selection Menu
Path 1: Run Cognitive Design Checklist
Choose this when: Evaluating any interface, layout, content page, form, or general design.
What you'll get: Pass/fail across 8 cognitive dimensions, test methods, common failures, severity-classified findings.
Time: 20-40 minutes
→ Go to Cognitive Design Checklist
Path 2: Run Visualization Audit
Choose this when: Evaluating data visualizations — charts, graphs, dashboards, infographics.
What you'll get: 1-5 scores on Clarity, Efficiency, Integrity, Aesthetics with pass/fail threshold.
Time: 15-30 minutes per visualization
→ Go to Visualization Audit Framework
Path 3: Combined Review
Choose this when: Comprehensive review covering both interface elements and data visualizations.
Process: Run Cognitive Checklist first, then Visualization Audit on each data component, merge findings, produce unified fix list.
Time: 45-90 minutes
→ Start with Cognitive Checklist, then Visualization Audit
Quick Reference
3-Question Rapid Check
1. Attention — "Is it obvious what to look at first?"
- If NO: hierarchy and visibility issues
2. Memory — "Is the user required to remember anything that could be shown?"
- If NO: memory support and chunking issues
3. Clarity — "Can someone unfamiliar understand in 5 seconds?"
- If NO: simplicity and comprehension issues
All YES = likely cognitively sound. Any NO = run full checklist on the failing area.
Guardrails
Out of scope: Creating designs, teaching theory, providing domain guidance, replacing user testing, or covering full accessibility compliance.
In scope: Systematic evaluation against cognitive principles, severity-classified findings, prioritized fix recommendations, and visualization quality scoring.
Related Skills
lyndonkl/conf-theme-clustering
testing
VerifiedTrustedCommunity
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-schedule-optimization
development
VerifiedTrustedCommunity
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-program-extraction
development
VerifiedTrustedCommunity
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
127SKILL.mdUpdated Jun 28, 2026
lyndonkl/conf-preference-elicitation
development
VerifiedTrustedCommunity
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.
127SKILL.mdUpdated Jun 28, 2026