Pricing Audit

Pricing Audit — sub-skill

The deeper audit. Where pricing-diagnostic runs 3 surfaces fast, pricing-audit runs 30 checks across 4 dimensions and produces a prioritized 90-day remediation plan.

Activation

The main pricing skill routes here when the operator says:

• "Audit my pricing program"
• "Grade my pricing 0-100"
• "What's my biggest pricing lever?"
• "Full pricing review"
• "What would Hermann Simon say about my pricing?"

The 30 checks

Dimension 1 — Diagnostic Data (8 checks)

Dimension 2 — Reference Frames + Copy (8 checks)

Dimension 3 — Tier Architecture (8 checks)

Dimension 4 — Operating Practice (6 checks)

Workflow

1. Load inputs

From brand-config.json:

• pricing.* section (all subfields)
• customer.psps[]

From the operator's pricing page URL (if provided):

• Use WebFetch to grab the live page
• Parse tier structure, copy, value metric

2. Run each of 30 checks

For each check, output one of:

• ✅ PASS
• ⚠️ PARTIAL (with what's missing)
• ❌ FAIL (with the specific gap)
• 🔘 NOT APPLICABLE (with the reason)

3. Calculate score

Score per dimension:

• Dim 1: PASS count × 12.5 (max 100)
• Dim 2: PASS count × 12.5 (max 100)
• Dim 3: PASS count × 12.5 (max 100)
• Dim 4: PASS count × 16.7 (max 100)

Overall = weighted mean: Dim 1 × 0.25 + Dim 2 × 0.25 + Dim 3 × 0.25 + Dim 4 × 0.25.

4. Identify the top 3 levers

Rank failed/partial checks by:

1. Magnitude — what's the expected revenue/margin impact?
2. Reversibility — how easy to undo if it doesn't work?
3. Diagnostic depth — do we know enough to act, or do we need more data first?

Top 3 = highest magnitude × reversibility × diagnostic-depth.

5. 90-day remediation order

For each of the top 3 levers, output:

Lever 1: {description}
  Why: {magnitude + impact framing}
  Action: {specific sub-skill route — e.g., "Run pricing-pocket-waterfall"}
  Owner: {who}
  Timeline: {week 1-3 / week 4-6 / week 7-12}
  Success metric: {how we'll know it worked}

6. Output format

Pricing Audit — {company}
─────────────────────────────────────────────────────────────────

OVERALL: {score}/100

Dimension 1 — Diagnostic Data: {score}/100
  ✅ {n} pass / ⚠️ {n} partial / ❌ {n} fail
Dimension 2 — Reference Frames + Copy: {score}/100
  ✅ {n} pass / ⚠️ {n} partial / ❌ {n} fail
Dimension 3 — Tier Architecture: {score}/100
  ✅ {n} pass / ⚠️ {n} partial / ❌ {n} fail
Dimension 4 — Operating Practice: {score}/100
  ✅ {n} pass / ⚠️ {n} partial / ❌ {n} fail

─────────────────────────────────────────────────────────────────
TOP 3 LEVERS (90-day remediation):

1. {lever 1}
2. {lever 2}
3. {lever 3}

DETAILED CHECK RESULTS:
[full 30-row table]

Self-check

• All 30 checks evaluated with rationale (not just scores)
• Score per dimension + overall calculated
• Top 3 levers identified with magnitude + reversibility + diagnostic-depth reasoning
• 90-day order respects sequencing (e.g., WTP discovery before tier rebuild)
• No fabrication — uncertain checks flagged, not guessed

References

• ../../pricing/references/pricing-framework.md — framework underlying each check
• ../pricing-diagnostic/SKILL.md — the lighter 3-surface diagnostic
• ../pricing-tribunal/SKILL.md — for material decisions surfaced by the audit