Qq Audit Copy

Part of Claude Code operator skills: a collection of skills for running a real Claude Code setup.

Audit copy with expert personas

Audit copy by running 22 expert personas in serial, fixing critical issues per framework before verifying.

22 content and copy 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.

The expert lens: Is the writing good? Would an editor approve? Every framework asks whether the copy is doing its job: informing, guiding, persuading, or reassuring, without wasting the reader's time or trust.

Modes

This skill responds to three modes based on the args passed. Interpret intent loosely: fuzzy matching, not exact phrasing.

Mode 1: Full serial audit (no args or "run all")

Triggers: /qq-audit-copy, "run all", "full audit", "everything", no args at all.

Mode 2: Single framework (framework name + optional scope)

Triggers: /qq-audit-copy voice tone, "just run microcopy on the settings page", "error messages on the form", etc.

Match the framework name fuzzily: "voice", "tone", "voice consistency" should all match Voice and Tone Consistency. "errors", "error msgs", "error messages" should all match Error Message Helpfulness. If ambiguous, show the 2-3 closest matches and ask.

Mode 3: List frameworks (help/list/discovery)

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.

Smart interview (runs before any audit)

DO NOT ask dumb questions. Before asking anything, gather what you already know:

1. Check conversation context: What product are we working on? What files have been discussed? What has the user been complaining about?
2. Check project CLAUDE.md: Product description, tech stack, target audience.
3. Check recent session state: What was just built or changed?

Pre-fill and present assumptions:

"Here's what I know going in:

• Product: [name] ([description from context])
• Audience: [who reads this copy, inferred from product type]
• Voice/brand docs: [existing style guide, voice bank, or none detected]
• Known copy pain points: [what the user has mentioned or what recent changes suggest]
• Scope: [full app / specific pages / specific component / marketing site]

Anything wrong or missing?"

Use AskUserQuestion with multiple choice ONLY for genuine gaps. For example, if you truly can't tell whether this is a consumer app or B2B enterprise tool, 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.

Execution flow (full audit)

Phase 1: Context gathering

1. Run smart interview (above)
2. Read the product's key pages/components to understand scope
3. Identify any existing voice/style documentation

Phase 2: Serial framework execution

For each framework (in order 1-22):

1. Spawn one agent with these instructions:

   • "Read the framework subskill file at ~/.agents/skills/qq-audit-copy/frameworks/[NN-name].md"
   • "You ARE the expert described in that document. Think like them, not like a generalist."
   • "Audit [product name] focusing on [scope]. Context: [interview output]"
   • "Previous frameworks found these issues: [cumulative findings list]. Do NOT re-report duplicates."
   • "Score 1-10, list findings with file:line references, fix critical issues (score < 7), write report."

2. Collect the agent's output:

   • Score for this framework
   • Findings (new, not duplicates)
   • Fixes applied
   • Items flagged for downstream frameworks

3. Verify build if fixes were applied (npx next build or equivalent)

4. Update cumulative state:

   • Add findings to the dedup list
   • Update the running score card
   • Note cross-framework flags for upcoming frameworks

5. Move to next framework

Phase 3: Synthesis

1. Run framework #22 (Localization Readiness) as the final forward-looking evaluation
2. Compile consolidated report:
   • Overall copy quality score (average across frameworks)
   • Per-framework scores
   • All findings grouped by severity
   • Fixes applied (with file:line)
   • Remaining items for future rounds
3. Compare to previous audit rounds if they exist

Phase 4: Report

Save to project's data directory:

• data/audit-copy-[date].md: full report
• data/audit-copy-[date]-summary.md: scores + critical findings only

Framework inventory

Key principles

• Serial, not parallel: 70% of findings duplicate across frameworks. Serial means each round finds genuinely new issues after fixes.
• Fix before moving on: don't accumulate a findings list. Fix each framework's criticals before the next audit.
• Expert persona, not checklist: each agent IS the specialist. They reason from editorial principles, not rules.
• Voice consistency across screens: the most common copy failure is not bad writing on any one screen, it's different writing on every screen. Voice/tone should feel like one author.
• Microcopy over macrocopy: button labels, error messages, tooltips, empty states, and placeholders do more work than any paragraph of body copy. Audit the small text hardest.
• The reader never reads: 79% scan. Copy must work for scanners first and readers second. Headings, labels, and first sentences carry the entire load.
• Hold every fix to a real quality bar: is this real data? Does it prevent errors? Is the complexity earned?
• Code + rendered output: code audits miss how copy actually reads in context. Always audit rendered output when possible.
• Multi-round: after all 22 frameworks, run the full cycle again. Scores increase each round until plateau.
• Dedup across frameworks: each agent receives cumulative findings so they don't re-report known issues.
• Would an editor approve? The ultimate test for every piece of copy: not "is it technically correct" but "is it good writing that serves the reader."