define-profiles — Claude Code command for audience profiles
The define-profiles command maps audience profile schemas, data sources, and activation needs. Use it to plan personalization across selected channels.
Apache-2.0 ★ 450 updated 2026-04-03
.claude/commands/define-profiles.mdWhat define-profiles does
The command takes an initiative from its goals and target personas through attribute inventory and segment logic to channel activation. Its outputs include a profile schema with attribute types, sources, and privacy notes, eligibility and suppression documentation, and an activation checklist.
It also records a plan in .claude/plans, covering dependencies, error handling, and success metrics. The workflow can involve personalization-architect, customer-data-engineer, and the decision-trees skill. Consent or compliance blockers trigger escalation, so those issues need attention before profiles are activated.
Provide an initiative and the channels to activate. Metrics, constraints, and a timeline are optional inputs; the workflow also captures data sources, consent rules, and attribute refresh cadence.
What it helps with
- map profile attributes to their data sources
- define eligibility and suppression rules for audience segments
- connect audience profiles to activation channels
- record dependencies and success metrics in a plan
Example prompts for the agent
- Define audience profiles for the PLG onboarding initiative across web, in-app, and email.
- Draft an attribute schema with its source systems and consent rules.
- Map profile activation to web and email, including privacy constraints.
How to install define-profiles
Manually: put the files in place
.claude/commands/define-profiles.mdCall it with /define-profiles. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/define-profiles.mdCall it with /prompts:define-profiles. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/define-profiles.prompt.mdManually: put the files in place
.gemini/commands/define-profiles.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about define-profiles
How do I install define-profiles in Claude Code?
Save the command file in your project at .claude/commands/define-profiles.md. Then invoke it with /personalization-engine:define-profiles.
What does define-profiles do?
It describes audience profiles, including attributes, data sources, segment rules, and channel activation needs. The workflow produces profile documentation and a plan stored in .claude/plans.
What inputs does define-profiles need?
Provide an initiative and the channels for activation. Metrics, constraints, and a timeline can be supplied as optional inputs.
Source text
define-profiles.md · Apache-2.0
--- name: define-profiles description: Produces audience profile schemas, data sources, and activation requirements for personalization programs. usage: /personalization-engine:define-profiles --initiative "PLG Onboarding" --channels "web,in-app,email" --- # Command: define-profiles ## Inputs - **initiative** – program or campaign name anchoring the personalization effort. - **channels** – comma-separated channels to activate (web, in-app, email, ads, sales). - **metrics** – optional KPIs (activation rate, pipeline $, retention). - **constraints** – optional compliance, consent, or tooling notes. - **timeline** – optional delivery window. ### GTM Agents Pattern & Plan Checklist > Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325. - **Pattern selection**: Profile definition typically runs **diamond** (objective intake ↔ attribute inventory in parallel, reconverging into activation/governance) or **pipeline** when sequential; document pattern choice in plan header. - **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing initiative, data sources, dependency graph (data eng, legal, privacy), error handling, and success metrics (attribute coverage %, consent integrity, activation lift). - **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for schema diffs, Context7 for privacy/compliance docs, Sequential Thinking for governance reviews, Playwright for consent/opt-in flow QA if needed. - **Guardrails**: Default retry limit = 2 for data pulls or consent checks; escalation ladder = Personalization Architect → Data Privacy Lead → Exec sponsor. - **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before finalizing to confirm dependencies + approvals. ## Workflow 1. **Objective Intake** – clarify business goals, target personas, lifecycle stages. 2. **Attribute Inventory** – list required fields, source systems, refresh cadence, and consent rules. 3. **Profile Definition** – outline segments, eligibility logic, scoring, decay windows. 4. **Activation Mapping** – document downstream systems, API/webhook needs, fallback states. 5. **Governance Plan** – assign owners, QA cadences, and change management checkpoints. ## Outputs - Profile schema deck/table (attributes, types, source, SLA, privacy notes). - Eligibility + suppression logic doc for each profile. - Activation checklist linking profiles to channels and tooling. - Plan JSON entry stored/updated in `.claude/plans` for audit trail. ## Agent/Skill Invocations - `personalization-architect` – leads objectives + profile design. - `customer-data-engineer` – validates data feasibility. - `decision-trees` skill – ensures logic structures align with downstream rules. ## GTM Agents Safeguards - **Fallback agents**: document substitutes (e.g., Customer Data Engineer covering Architect) when leads unavailable. - **Escalation triggers**: escalate if consent/compliance blockers occur twice or attribute coverage misses SLA; log remediation in plan JSON. - **Plan maintenance**: update plan JSON/change log when attributes, data sources, or governance cadences change. ---
© gtmagents · Apache-2.0 · gtmagents/gtm-agents