sales-cdp

What this skill does

# CDP Comparison & Selection Strategy

## Step 1 — Gather context

If `references/learnings.md` exists, read it first for accumulated knowledge.

1. **What's your primary goal?**
   - A) Choosing between CDPs (evaluation/comparison)
   - B) Deciding if I even need a CDP
   - C) Planning a CDP implementation
   - D) Unifying customer data across channels
   - E) Activating audiences to ad platforms, email, CRM
   - F) Setting up real-time personalization
   - G) Warehouse-first / composable CDP approach
   - H) Other — describe it

2. **What's your technical maturity?**
   - A) No data infrastructure — starting from scratch
   - B) Basic analytics (GA, Mixpanel) but no unified profiles
   - C) Data warehouse exists (Snowflake, BigQuery) but not activated
   - D) Current CDP that we want to replace
   - E) Homegrown system we've outgrown

3. **Who will own the CDP?**
   - A) Marketing team (need no-code/low-code)
   - B) Engineering team (API-first, developer tools)
   - C) Data team (SQL, warehouse, dbt)
   - D) Cross-functional (marketing + engineering + data)

4. **What's your scale?**
   - A) Under 100K monthly active users
   - B) 100K-1M MAU
   - C) 1M-10M MAU
   - D) 10M+ MAU

Skip-ahead rule: if the user's prompt already contains enough context, skip to Step 2.

## Step 2 — Route or answer directly

| Problem domain | Route to |
|---|---|
| Tealium-specific setup or config | `/sales-tealium {user's question}` |
| BlueConic-specific setup or config | `/sales-blueconic {user's question}` |
| Treasure Data-specific setup or config | `/sales-treasuredata {user's question}` |
| RudderStack-specific setup or config | `/sales-rudderstack {user's question}` |
| mParticle-specific setup or config | `/sales-mparticle {user's question}` |
| CRM data dedup without a CDP | `/sales-data-hygiene {user's question}` |
| Email marketing strategy | `/sales-email-marketing {user's question}` |
| Retargeting ad strategy | `/sales-retargeting {user's question}` |
| Contact enrichment | `/sales-enrich {user's question}` |

When routing, provide the exact command.

## Step 3 — CDP comparison reference

**Read `references/platform-guide.md`** for the full CDP comparison — positioning, feature matrices, pricing guidance, decision frameworks, implementation timelines.

Answer the user's question using only the relevant section. Don't dump the full reference.

## Step 4 — Actionable guidance

You no longer need the comparison reference — focus on the user's specific situation.

**Decision framework (quick version):**
- **Marketer-first, no-code segmentation, mid-market**: BlueConic
- **Enterprise, 1000+ integrations, tag management heritage**: Tealium
- **Enterprise, AI/ML-native, 400+ connectors, heavy SQL**: Treasure Data
- **Developer-first, quick implementation, warehouse-centric**: Segment
- **Mobile-first, SDK-focused, gaming/media apps**: mParticle
- **Open-source, self-hosted, full control**: RudderStack
- **Warehouse-native activation (reverse ETL)**: Hightouch
- **Identity-focused, retail/hospitality**: Amperity

If you discover a gotcha, workaround, or tip not covered in `references/learnings.md`, append it there.

## Gotchas

> *Best-effort from research — review these, especially items about plan-gated features and pricing that may be outdated.*

1. **CDPs don't fix bad data** — if your source systems have duplicates, missing fields, or inconsistent formats, the CDP will unify garbage. Clean data at the source first (use `/sales-data-hygiene`).

2. **Identity resolution quality varies wildly** — duplication rates of 10-30% are common across CDPs. Test identity resolution with your actual data in a POC, not just vendor demos.

3. **"Real-time" means different things** — event ingestion may be fast but profile updates or downstream activation may lag by minutes or hours. Test end-to-end latency, not just ingestion speed.

4. **Implementation takes 2-6 months for enterprise CDPs** — Tealium and Treasure Data require careful planning and often professional services. Segment and RudderStack can POC in days.

5. **Event-based pricing catches enterprises off guard** — high-volume sites can see costs spike unpredictably. Negotiate volume commitments and overage caps upfront.

## Before recommending a specific platform skill

This skill covers a strategy domain across many platforms. **Before pointing the user to any specific platform skill** (any `/sales-{platform}` listed in `## Related skills`, e.g., `/sales-mailshake`, `/sales-klaviyo`, `/sales-apollo`), read that platform skill's actual `SKILL.md` first. The 1-line description in `## Related skills` is enough to *identify* a candidate — it's not enough to *commit* to it or to write a prompt that invokes it well.

**How to read it:**
- If `~/.claude/skills/{skill-name}/SKILL.md` exists locally, `Read` it.
- For `sales-*` skills, `WebFetch` directly from this repo: `https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md` — e.g., for `sales-mailshake`: `https://raw.githubusercontent.com/sales-skills/sales/main/skills/sales-mailshake/SKILL.md`.
- For non-`sales-*` skills (third-party), look up `{org}/{repo}` in `~/.claude/skills/sales-do/references/skill-sources.md` if installed and fetch the same `skills/{skill-name}/SKILL.md` path under that repo.

**After reading,** ground your recommendation in something concrete from the SKILL.md (its scope, a sub-flow, its `argument-hint` shape, or a "Do NOT use for..." negative trigger). Align any generated invocation with the platform skill's `argument-hint`. If the platform skill turns out not to fit the user's situation, swap to another or handle the question here directly rather than recommending a poor fit.

## Related skills

- `/sales-tealium` — Tealium platform help — Real-Time CDP, iQ Tag Management, EventStream, 1300+ connectors
- `/sales-blueconic` — BlueConic CDP — profile unification, segmentation, audience activation, Jebbit Experiences
- `/sales-treasuredata` — Treasure Data enterprise CDP — AI Marketing Cloud, 400+ connectors, SQL-based
- `/sales-rudderstack` — RudderStack platform help — warehouse-native CDP, Event Streams, Reverse ETL, open-source
- `/sales-mparticle` — mParticle platform help — hybrid CDP, real-time event streaming, identity resolution, 300+ integrations
- `/sales-data-hygiene` — CRM data quality — clean your data before feeding it to a CDP
- `/sales-retargeting` — Retargeting strategy — activate CDP audiences to ad platforms
- `/sales-integration` — Tool integration — connecting CDP to CRM, email, ad platforms
- `/sales-enrich` — Contact enrichment — augment CDP profiles with third-party data
- `/sales-do` — Not sure which skill to use? The router matches any sales objective to the right skill. Install: `npx skills add sales-skills/sales --skill sales-do`

## Examples

### Example 1: CDP selection
**User says**: "We have 500K monthly users across web and mobile. Our marketing team needs to build audiences without engineering help. Budget is $50K-$100K/year."
**Skill does**: Compares BlueConic (marketer-first, mid-market pricing) vs Tealium (enterprise, more integrations but steeper learning curve) vs Segment (developer-first, may not suit a non-technical marketing team). Recommends BlueConic for the marketer-first UI, or Tealium if the 1,300+ integration catalog is critical.
**Result**: User has a shortlist of 2 CDPs to evaluate with clear pros/cons for their situation.

### Example 2: Do I need a CDP?
**User says**: "We use HubSpot for CRM, Mailchimp for email, and Google Ads. Our data feels messy. Do we need a CDP?"
**Skill does**: Asks about pain points — are profiles fragmented? Do you need real-time activation? How many data sources? For a 3-tool stack, suggests starting with native integrations and `/sales-data-hygiene` before investing in a CDP. A CDP makes sense when you have 10+ data sources or need real-time audience activation across channels.
**Result**: User understands the CDP readiness thres