client-validation-document

What this skill does

# /digital-marketing-pro:client-validation-document — Part 5: The One True Stop

This skill produces the Part 5 deliverable: the Client Validation Document. It is the only point in the engagement where unbiased v1 findings are formally presented to the client for accept/reject/edit decisions.

## Context efficiency

Heavy skill. **Grep before Read** any referenced file, then `Read` only matched ranges with `offset` + `limit`. List `${CLAUDE_PLUGIN_DATA}/<brand>/` before opening files. On re-invocation mid-session, skip files already in context.

This is the **one true stop** in the 12-Part flow. Nothing in Parts 6+ proceeds until this is signed off.

## What this document is

The Client Validation Document compiles the most strategically consequential findings from Parts 2, 3, and 4 (the unbiased research and the four core documents) into a structured review document. For each finding:

- The finding itself
- Evidence / sources
- Proposed implication if accepted
- Three response options for the client: ACCEPT / REJECT / EDIT / DEFER
- (For REJECT or EDIT) — the client provides their corrected version and the rationale

The client's responses then feed the Decision Matrix in Part 6 to determine which v2 re-runs are needed.

## What this document is NOT

- **Not a Growth Plan.** This is research findings, not strategic recommendations dressed up. The Growth Plan is Part 8.
- **Not exhaustive.** It includes only findings that have material strategic implications. Detail belongs in the source documents.
- **Not a slide deck.** It is a written document the client reads carefully and responds to. Slides do not capture the rigor required.
- **Not optional.** Every engagement runs Part 5. No shortcut to Part 6 without it.

## Pre-conditions

Before running this skill:

1. Parts 2, 3, 4 must be completed (or substantially complete with explicit acknowledgment that some research continues)
2. The engagement state file `_engagement.json` must show Parts 3 and 4 as `completed`
3. The Living Project Instruction File should be up to date with the v1 strategic facts

If pre-conditions fail, do NOT produce output. Instruct the user on what is missing.

## Document Structure

The Client Validation Document is organised by category of finding. Each category has 3–8 findings; total document is typically 12–25 findings across categories.

### Section 1: Executive Briefing

**Length:** 1 page.

**Content:**

- Purpose of this document
- How to read it (the ACCEPT / REJECT / EDIT / DEFER framework)
- What happens after the client responds (Part 6 v2 re-runs governed by the Decision Matrix)
- Decision deadline (typically 7–14 days)

### Section 2: Findings — by category

Each category contains its findings as structured blocks. Categories:

#### A. Business & SBU Findings (from 3.1)

Findings about the business reality — SBU separation, unit economics, value chain, growth levers, constraints, risks. Typically 3–5 findings.

#### B. Audience & Segmentation Findings (from 3.2 + 4.3)

Findings about target groups, persona priority, decision-making units, MQL/SQL definitions. Typically 3–5 findings.

#### C. Positioning & Communications Findings (from 3.3)

The chosen positioning, messaging pillars, tone-of-voice, don't-say rules, sensitive-topic handling. Typically 3–5 findings.

#### D. Channel & Budget Findings (from 3.4)

Channel selections, in-market vs out-market split, budget allocation, channel sequencing. Typically 2–4 findings.

#### E. Competitive Findings (from 4.1 + 4.2)

Competitor list, competitive positioning, Three-Question outputs (do well / do poorly / not doing). Typically 2–4 findings.

#### F. Market & Customer Findings (from 4.3 + 4.4)

Market sizing, customer behaviour patterns, demand signals. Typically 2–4 findings.

### Section 3: Open Questions

Questions that the unbiased research could not resolve and need client input. The client provides answers here.

### Section 4: Response Mechanism

How the client returns their responses (typically a structured response file or a meeting walkthrough).

## Finding Block Format

Each finding follows this exact structure:

```markdown
### Finding {ID}: {Short title}

**Category:** {A/B/C/D/E/F}
**Source:** {Document and step references — e.g., "3.1 Step 4, 4.1 Three-Question Output"}
**Materiality:** {High / Medium / Low}

**Finding:**
{2–4 sentences stating the finding from the unbiased research}

**Evidence:**
- {Cited source 1 with specific data point}
- {Cited source 2}
- {Cited source 3}

**Proposed implication if accepted:**
{1–3 sentences on what this means for the strategy if the client accepts}

**Client response:**

- [ ] ACCEPT — finding is correct as stated
- [ ] REJECT — finding is wrong; correction below
- [ ] EDIT — finding is partially correct; amended version below
- [ ] DEFER — needs further investigation; reason below

**If REJECT or EDIT, client correction:**
{Client fills in: what the correct finding is, with their evidence}

**If DEFER, reason and follow-up plan:**
{Client fills in: what additional research / data is needed, who is accountable, deadline}
```

## Materiality Classification

Each finding gets a Materiality rating that indicates how consequential the response is:

- **High** — accepting vs rejecting would meaningfully change the channel mix, budget, positioning, or audience priority. Triggers v2 re-runs per Decision Matrix.
- **Medium** — accepting vs rejecting would change tactical execution but not strategic direction. May or may not trigger re-runs.
- **Low** — accepting vs rejecting changes phrasing or examples but not substance. No re-run triggered.

The client should focus most attention on High materiality findings; Medium and Low are still presented for completeness.

## Response Categorisation for the Decision Matrix

After the client provides responses, the responses are categorised into Decision Matrix triggers:

| Client decision pattern | Decision Matrix trigger |
|---|---|
| Any competitor finding REJECTED or EDITED with new competitors | `competitors_changed` |
| Any market sizing finding REJECTED or EDITED | `target_market_changed` |
| Any segmentation finding REJECTED or EDITED with persona changes | `audiences_changed` |
| Any positioning finding REJECTED or EDITED | `positioning_changed` |
| Any budget / scope finding REJECTED or EDITED | `budget_or_scope_changed` |
| Any pricing or offering finding REJECTED or EDITED | `pricing_or_offering_changed` |
| Any unit economics finding REJECTED or EDITED | `unit_economics_changed` |
| Only Low-materiality EDITs / minor wording corrections | `minor_corrections_only` |

The skill compiles the trigger list and runs:

```bash
python ${CLAUDE_PLUGIN_ROOT}/scripts/engagement-state.py decision-matrix \
  --brand {slug} --id {id} \
  --triggers "{comma-separated-trigger-list}"
```

The output then feeds the Part 6 v2 re-run plan.

## Production Steps

1. **Verify pre-conditions** — Parts 2, 3, 4 completed.

2. **Read the v1 source documents:**
   - `part-03-four-core-documents/v1/3.1-business-and-sbu-analysis.md`
   - `part-03-four-core-documents/v1/3.2-segmentation-framework.md`
   - `part-03-four-core-documents/v1/3.3-brand-positioning-and-communications.md`
   - `part-03-four-core-documents/v1/3.4-dmflow.md`
   - `part-04-competitive-customer-market/v1/4.1-competitor-ad-analysis.md`
   - `part-04-competitive-customer-market/v1/4.2-competitor-positioning.md`
   - `part-04-competitive-customer-market/v1/4.3-customer-analysis.md`
   - `part-04-competitive-customer-market/v1/4.4-market-analysis.md`

3. **Extract material findings.** For each source document, identify the 2–5 most strategically consequential findings. Materiality rating: prefer High and Medium; include Low only if the client specifically benefits from confirming.

4. **Synthesise findings into the structured format.** Use plain client-facing language, not internal jargon. Each finding stands alone — do not require the client to read the source documents