monitor-personalization — Claude Code command: setup and use
monitor-personalization audits personalization campaigns, tracks experiment outcomes, and flags consent violations across user segments.
Apache-2.0 ★ 450 updated 2026-04-03
.claude/commands/monitor-personalization.mdWhat monitor-personalization does
The command runs an end-to-end review of personalization initiatives. It pulls engagement and revenue metrics, inspects consent flags and fallback rates, and summarizes running experiments with statistical confidence scores. Audit records land directly in .claude/plans/plan-<timestamp>.json.
Execution follows a five-step pipeline covering data aggregation, governance scanning, experiment readouts, anomaly detection, and report generation. The workflow calls the testing-lead and personalization-architect roles alongside the governance skill.
Failed data collection jobs stop after two retries before escalating up the lead chain.
What it helps with
- Track statistical confidence across active personalization experiments
- Audit consent flags, rule change logs, and fallback triggers
- Detect metric drops and variant suppression anomalies
- Generate audit plan snapshots in .claude/plans
Example prompts for the agent
- /personalization-engine:monitor-personalization --initiative "PLG Onboarding" --window 14d --detail full
- /personalization-engine:monitor-personalization --initiative "Enterprise Checkout" --window 30d --alert_threshold 0.05
- /personalization-engine:monitor-personalization --initiative "Mobile Activation" --window 7d --dimension channel
How to install monitor-personalization
Manually: put the files in place
.claude/commands/monitor-personalization.mdCall it with /monitor-personalization. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/monitor-personalization.mdCall it with /prompts:monitor-personalization. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/monitor-personalization.prompt.mdManually: put the files in place
.gemini/commands/monitor-personalization.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about monitor-personalization
How to install monitor-personalization in Claude Code?
Place the command definition file at .claude/commands/monitor-personalization.md in your project root. Claude Code registers the command immediately.
What does monitor-personalization do?
It audits campaign performance, verifies consent governance, and inspects A/B test confidence. Findings and next steps are logged into an audit plan JSON file.
How does error handling work during metric collection?
The command allows up to 2 retries on failed data pulls. If alerts repeat or thresholds are breached twice, it routes the incident to testing and privacy leads.
Source text
monitor-personalization.md · Apache-2.0
--- name: monitor-personalization description: Audits personalization performance, governance compliance, and experiment results. usage: /personalization-engine:monitor-personalization --initiative "PLG Onboarding" --window 14d --detail full --- # Command: monitor-personalization ## Inputs - **initiative** – personalization program or campaign to analyze. - **window** – time frame (7d, 14d, 30d) for pulling metrics. - **detail** – summary | full to control report depth. - **dimension** – optional breakdown (profile, channel, cohort). - **alert_threshold** – optional KPI threshold to trigger incident items. ### GTM Agents Pattern & Plan Checklist > Mirrors GTM Agents orchestrator blueprint @puerto/plugins/orchestrator/README.md#112-325. - **Pattern selection**: Monitoring usually runs **pipeline** (data aggregation → governance scan → experiment readout → issue detection → action plan). If governance + experiments review can run concurrently, capture a **diamond** block with merge gate in the plan header. - **Plan schema**: Save `.claude/plans/plan-<timestamp>.json` capturing initiative, data feeds, dependency graph (data eng, privacy, experimentation), error handling, and success metrics (lift %, incident response time, consent adherence). - **Tool hooks**: Reference `docs/gtm-essentials.md` stack—Serena for schema diffs, Context7 for governance/experiment SOPs, Sequential Thinking for retro cadence, Playwright for experience QA evidence. - **Guardrails**: Default retry limit = 2 for failed data pulls or anomaly jobs; escalation ladder = Testing Lead → Personalization Architect → Data Privacy Lead. - **Review**: Run `docs/usage-guide.md#orchestration-best-practices-puerto-parity` before distribution to ensure dependencies + approvals are logged. ## Workflow 1. **Data Aggregation** – pull engagement, conversion, and revenue impact by profile/channel plus decision tree health signals. 2. **Governance Scan** – verify consent flags, fallback rates, and rule change logs for compliance. 3. **Experiment Readout** – summarize live/completed tests with statistical confidence and recommended actions. 4. **Issue Detection** – flag anomalies (data freshness, variant suppression, performance dips) and suggest playbooks. 5. **Report Distribution** – publish recap with dashboards, backlog items, and owners. ## Outputs - Performance dashboard snapshot segmented by profile/channel/variant. - Governance checklist status with any violations or pending approvals. - Experiment memo with next steps + rollout guidance. - Plan JSON entry stored/updated in `.claude/plans` for audit trail. ## Agent/Skill Invocations - `testing-lead` – interprets experiments and recommends rollouts. - `personalization-architect` – validates experience integrity. - `governance` skill – enforces policy checks and approvals. ## GTM Agents Safeguards - **Fallback agents**: document substitutes (e.g., Governance covering Testing Lead) when leads unavailable. - **Escalation triggers**: escalate if alert_threshold breached twice, consent violations appear, or anomaly alerts repeat; log remediation steps in plan JSON. - **Plan maintenance**: update plan JSON/change log when metrics, thresholds, or monitoring cadences change to keep audits accurate. ---
© gtmagents · Apache-2.0 · gtmagents/gtm-agents