Customer Research
Customer Research skill from Corey Haines’ Marketing Skills collection.
Overview
Customer Research is a growth/marketing skill from Corey Haines’ Marketing Skills collection (github.com/coreyhaines31/marketingskills). Customer Research skill from Corey Haines’ Marketing Skills collection. The skill is structured around practical workflows—covering Before Starting, Two Modes of Research, Mode 1: Analyzing Existing Research Assets, Mode 2: Digital Watering Hole Research, Top Themes (ranked by frequency × intensity), Persona Generation—so Claude can move from context gathering to concrete artifacts (briefs, copy, checklists, or audit reports) instead of generic advice. Pair it with related skills in the same collection: `competitor-profiling`, `marketing-psychology`, `product-marketing`.
Work with LimeDock
Using this skill? LimeDock can wire it into a durable automation you own.
Skills show what's possible. LimeDock builds and runs the owned marketing, sales, and ops automations around them.
We sell owned automations for SaaS teams — live workflows that plug into Slack, CRM, and your internal platform — not just a skill list.
Link
Installation guide
Option A — Install just this skill (recommended)
npx skills add coreyhaines31/marketingskills --skill customer-researchOption B — Install the full Marketing Skills collection
npx skills add coreyhaines31/marketingskillsThat unlocks related skills like `cro`, `copywriting`, `emails`, `ads`, and `seo-audit`.
Option C — Manual install (Claude Code)
git clone https://github.com/coreyhaines31/marketingskills.git /tmp/marketingskills
mkdir -p ~/.claude/skills
cp -R /tmp/marketingskills/skills/customer-research ~/.claude/skills/customer-researchClaude.ai
Customize → Skills → Upload the `customer-research` folder as a zip / `SKILL.md` → enable the skill.
Always skim `SKILL.md` before first use so you know its triggers and related skills.
How to use it
1. **Trigger it with customer research language** — mention the job by name or ask for the deliverable this skill owns. 2. **Share product context up front** — ICP, offer, URL, constraints, and any metrics. If `.agents/product-marketing.md` (or `.claude/product-marketing.md`) exists, the skill will read it first. 3. **Let it run the assessment** — answer clarifying questions before asking for final copy/strategy. 4. **Request a concrete artifact** — brief, audit, page outline, sequence, scorecard, or launch checklist. 5. **Close the loop** — feed performance data back so the next iteration compounds.
**Typical sections it covers:** Before Starting, Two Modes of Research, Mode 1: Analyzing Existing Research Assets, Mode 2: Digital Watering Hole Research, Top Themes (ranked by frequency × intensity), Persona Generation, [Persona Name] — [Role/Title], Deliverable Formats.
If Claude does not auto-select it, say: “Use the Customer Research skill (`customer-research`)…”.
Example prompts
- “Use the Customer Research skill to assess our current state and produce a prioritized action plan.”
- “Walk me through how Customer Research would approach this step by step, then execute on our product.”
- “Create a reusable checklist and prompt template for running Customer Research monthly.”
- “Review my draft plan and improve it with Customer Research. Call out assumptions and risks.”
Use cases and examples
- Run a full Customer Research workflow on a live product or campaign
- Produce a reusable Customer Research brief/checklist for the team
- Audit the current state and prioritize fixes for customer research
- Generate first-draft artifacts then refine with brand constraints
- Connect Customer Research output to measurement and next experiments
- Document a playbook entry so customer research learnings compound
- Apply the “Before Starting” guidance to a current initiative
- Apply the “Two Modes of Research” guidance to a current initiative
Prerequisites
- Claude Code, Claude.ai Skills, or another Agent Skills–compatible host
- Product/brand context (ICP, offer, URLs, constraints) for grounded outputs
- Optional: `.agents/product-marketing.md` or `.claude/product-marketing.md` in the repo
- Permission to install third-party skills — audit SKILL.md first
- Optional: analytics or ad-platform access when the task needs real performance data
Tips
- Keep triggers specific so Customer Research fires only when that job is requested (avoids context tax).
- Load product-marketing context (ICP, voice, offer) before asking for final copy or strategy.
- Prefer one sharp deliverable per turn—brief, audit, or draft—then iterate with data.
- Audit `SKILL.md` and any scripts before production use; treat community skills as code.
- Pair with `competitor-profiling` and `marketing-psychology` when the workflow spans channels.