メニュー
Serialized UX audit using 20 deep framework subskills. Each framework runs in its own agent context with expert-level depth. Smart interview pre-fills from conversation context.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Keep a live interactive chat session coming back to itself, visibly, after a usage/session cap interrupts it, never a silent background process. Invoke with /qq-cap-resume, or say “keep this session alive,” “resume yourself after the cap,” “don’t go dark on me,” any time a long interactive burn needs to survive a 5-hour session cap or ride out to a weekly reset without leaving you staring at a dead thread.
The unbounded end of the AFK spectrum: spend whatever it takes for quality, budget isn’t the constraint. Stand up a self-healing, fully-autonomous “kitchen-sink max-effort” campaign for a big multi-day initiative: resilience first, creative meta strategy, workflows spawning workflows, audit-gated quality, a phone-glanceable status surface with a proud wins list, and a long living tasklist. Invoke when you say “go HAM”, “go-ham”, “go afk ham”, “qq-go-afk-ham”, “kitchen sink”, “blow me away”, “use all the quota”, or hand it a large ambitious build to run autonomously for hours or days. For the frugal end, use `qq-go-afk-lean`; for the adaptive middle, use `qq-go-afk-smart`.
The adaptive middle of the AFK spectrum: picks the right model task by task, moment by moment, instead of committing to either extreme. Stand up a calm, self-healing, fully-autonomous overnight worker for a well-scoped punch list: the top-tier model writes strict specs and does quality control, cheap and free models do the grunt work, one bounded task per cycle, each one deployed and live-verified, a phone-glanceable status surface, and a durable done log. Invoke when you say “go afk smart”, “go-afk-smart”, “qq-go-afk-smart”, “go smart”, “bounded overnight”, “delegate and verify overnight”, or hand it a finite, well-specified backlog (a punch list, a rollout, a sweep) to grind down autonomously while you sleep, without the kitchen-sink fan-out of go HAM. For the unbounded end, use `qq-go-afk-ham`; for the frugal end, use `qq-go-afk-lean`.
The moment a real, avoidable mistake happens, name it plainly, root-cause the general class of it rather than just this one instance, and fix it at a level that prevents a repeat, not a note that gets written and forgotten. Then, before starting work that looks like it could repeat that shape, check the log first. A second occurrence of the same mistake means the note wasn’t enough, and it needs to become a real check instead of a reminder. Invoke with /ww-mistake-ledger, or say “log this mistake,” “close the loop on this,” “add this to the mistake log,” “check the mistake log first,” right after a preventable error, or right before starting work that resembles one already logged.
Ask what would make this fail before you build it, not after. A one-question design-time gate, imagine it’s already broken three months from now, work backward to the most likely cause, and let the answer change the plan instead of just getting noted and ignored. Works on code, an automation, a process, or a decision. Invoke with /ww-premortem, or say “what breaks this in three months,” “pre-mortem this,” “why would this fail,” “before I build this,” at the moment you’re about to commit to an approach, not after you’ve already started.
Before filling a gap in what you know with a guess, check whether the guess is load-bearing. If getting it wrong would mean redoing real work, or building on a false premise, ask a real question with concrete options instead of assuming silently. If it’s genuinely low-stakes, state the assumption out loud and keep moving rather than stalling on it. Works on any ambiguous request, with or without an AI agent involved. Invoke with /ww-questioning, or say “wait, let me ask first,” “is this load-bearing,” “check before I guess,” “clarify before building,” whenever a request has more than one reasonable reading and you’re about to just pick one.
| name | qq-audit-ux |
| description | Serialized UX audit using 20 deep framework subskills. Each framework runs in its own agent context with expert-level depth. Smart interview pre-fills from conversation context. |
| version | 3.0.0 |
| triggers | ["ux audit","usability audit","heuristic evaluation","ux framework review","sus score","run all frameworks","run ux audit"] |
Part of Claude Code operator skills: a collection of skills for running a real Claude Code setup.
Run a full serial UX audit using 20 deep expert persona frameworks, fixing critical issues and verifying each framework before proceeding to the next.
20 usability frameworks, each loaded as a deep expert persona into its own agent context. Serial execution: one framework → fix critical issues → verify → next. Each agent thinks like a 20-year specialist in that specific framework.
Supersedes: ux-framework-audit v2, deep-product-sweep v1, product-qa suite.
This skill responds to three modes based on the args passed. Interpret intent loosely: fuzzy matching, not exact phrasing.
Triggers: /qq-audit-ux, "run all", "full audit", "everything", no args at all.
Triggers: /qq-audit-ux Fitts's Law, "just run gestalt on the sidebar", "nielsen's on the settings page", etc.
Match the framework name fuzzily: "fitts", "fitt's law", "target sizes" should all match Fitts's Law. "nielsen", "heuristics", "10 heuristics" should all match Nielsen's. If ambiguous, show the 2-3 closest matches and ask.
Triggers: "list", "what do you have", "what frameworks", "help", "which ones", "show me", etc.
Show the framework table from §Framework inventory below, then ask which one(s) to run.
DO NOT ask dumb questions. Before asking anything, gather what you already know:
Pre-fill and present assumptions:
"Here's what I know going in:
- Product: [name] ([description from context])
- Platform: [desktop/mobile/both, inferred from tech stack]
- Quality bar: [SUS target, from previous audits or conversation]
- Known pain points: [what the user has mentioned or what recent changes suggest]
- Scope: [full app / specific pages / specific component]
Anything wrong or missing?"
Always ask the target score using AskUserQuestion:
Use AskUserQuestion with multiple choice ONLY for genuine gaps. For example, if you truly can't tell whether it's desktop-only or responsive, ask. If you can infer it, state the inference.
Interview output becomes the audit context: passed to every framework agent so they audit with purpose, not generically.
For each framework (in order 1-20):
Spawn one agent with these instructions:
~/.agents/skills/qq-audit-ux/frameworks/[NN-name].md"Collect the agent's output:
Verify build if fixes were applied (npx next build or equivalent)
Update cumulative state:
Move to next framework
Exec summary is MANDATORY: every report starts with a 3-5 sentence executive summary at the very top. No jargon, no framework names. Just: what was audited, what the score is, what the biggest problem is, and whether it improved from last time.
Per-framework exec summaries too: after each framework completes, present a 1-2 sentence summary before the detailed findings. Lead with the score change and the single most important finding.
Save to project's data directory:
data/audit-ux-[date].md: full report (exec summary at top)data/audit-ux-[date]-summary.md: scores + critical findings only| # | Framework | Expert lens | Subskill file |
|---|---|---|---|
| 1 | Nielsen's 10 Heuristics | Broad usability sweep: visibility, consistency, error prevention, recognition, flexibility, minimalism | 01-nielsens-heuristics.md |
| 2 | Gestalt Principles | Visual grouping: proximity, similarity, continuity, closure, figure-ground | 02-gestalt-principles.md |
| 3 | Fitts's Law | Motor control: target sizes, distances, touch targets, click area geometry | 03-fitts-law.md |
| 4 | Hick's Law | Decision complexity: option counts, defaults, progressive narrowing | 04-hicks-law.md |
| 5 | Miller's Law | Working memory: chunking, information density, cross-screen recall | 05-millers-law.md |
| 6 | Jakob's Law | Convention compliance: does this match patterns users already know? | 06-jakobs-law.md |
| 7 | Aesthetic-Usability Effect | Polish and trust: beauty creates perceived usability (and can mask real problems) | 07-aesthetic-usability.md |
| 8 | Von Restorff Effect | Visual salience: does the most important thing actually stand out? | 08-von-restorff.md |
| 9 | Zeigarnik Effect | Progress and completion: open loops, progress indicators, completion feedback | 09-zeigarnik-effect.md |
| 10 | Progressive Disclosure | Complexity management: what's visible vs. what's behind interaction | 10-progressive-disclosure.md |
| 11 | Error Tolerance | Recovery and forgiveness: undo, confirmation, form data persistence | 11-error-tolerance.md |
| 12 | Emotional Design | Feeling: visceral, behavioral, reflective (Don Norman's three levels) | 12-emotional-design.md |
| 13 | WCAG 2.1 AA | Accessibility: perceivable, operable, understandable, robust | 13-wcag-accessibility.md |
| 14 | Doherty Threshold | Response time: <400ms for flow, <100ms for instantaneous feel | 14-doherty-threshold.md |
| 15 | Peak-End Rule | Memory: users judge by the peak moment and the ending | 15-peak-end-rule.md |
| 16 | Tesler's Law | Complexity budget: who bears the irreducible complexity, user or system? | 16-teslers-law.md |
| 17 | Cognitive Load Theory | Mental bandwidth: intrinsic, extraneous, germane load management | 17-cognitive-load-theory.md |
| 18 | Serial Position Effect | Placement: primacy and recency, the forgotten middle | 18-serial-position-effect.md |
| 19 | Goal-Gradient Effect | Momentum: progress visibility, acceleration near completion | 19-goal-gradient-effect.md |
| 20 | SUS Scoring | Synthesis: 10-item usability scale, maps score to framework-specific diagnosis | 20-sus-scoring.md |
| Product | Round | SUS | Fixes | Key improvement |
|---|---|---|---|---|
| Internal dashboard (example run) | 1 | 57.5 → 77.5 | 100+ | Basic interactivity, real data, help |
| Internal dashboard (example run) | 2 | 77.5 → 85+ | 45+ | Convergence UX, WCAG, mobile |
| Internal dashboard (example run) | 3 | 85+ → 92.5 | 30+ | Polish, emotional design, peak moments |