---
name: personalization-plan
description: Entry-point slash command for the Personalization & Experimentation Planner. Reads available context (analytics exports, journey maps, research briefs, stakeholder docs) and routes to the appropriate skill or to the full-pipeline agent for a complete experiment brief.
argument-hint: "[full | hypothesis <brief> | audience <persona> | test-plan <HYP-NNN> | measure <HYP-NNN> | review <client>]"
allowed-tools:
  - Read
  - Glob
---

Route the request based on the argument provided:

## Routing logic

**No argument or `full`:**
Run the full pipeline via `personalization-planner-agent`. Collect intake interactively, then produce hypothesis backlog + audience definition + test plan + measurement spec + assembled experiment brief.

**`hypothesis <brief-or-file>`:**
Run `hypothesis-generator` only. Produce a signal inventory, problem map, and prioritized hypothesis backlog. Output: `hypothesis-backlog-<slug>-<YYYY-MM>.md`.

**`audience <persona-or-segment-description>`:**
Run `audience-segment-builder` only. Define behavioral/firmographic/lifecycle segments for the named audience and produce platform-specific configuration. Output: `audience-segments-<slug>-<YYYY-MM>.md`.

**`test-plan <HYP-NNN-or-hypothesis-brief>`:**
Run `experiment-test-plan` only. Calculate sample size, define traffic split, write variant specs, produce QA checklist and stopping rules. Output: `test-plan-<hypothesis-id>-<YYYY-MM>.md`.

**`measure <HYP-NNN-or-test-plan-path>`:**
Run `personalization-measurement-spec` only. Author primary metric, secondary metrics, guardrail metrics, counter-metric analysis, data readiness checklist, and reporting spec. Output: `measurement-spec-<hypothesis-id>-<YYYY-MM>.md`.

**`review <client-context-or-'interview'>`:**
Run `experimentation-program-review`. Assess the client's experimentation program maturity and produce a scored assessment + improvement roadmap. Output: `experimentation-program-review-<client>-<YYYY-MM>.md`.

## Context reading

Before routing, check for any of these files in the current directory and read them automatically if found:

```
Glob: *.analytics.json, *-brief.md, *-research.md, *journey*.md, *persona*.md, hypothesis-backlog-*.md, test-plan-*.md
```

If context files are found, pass their contents to the routed skill as input so it does not start from scratch.

## Output

After routing and execution, always summarize:
1. Which skill(s) were run
2. Which files were created (with full paths)
3. Any assumptions made that the user should review
4. Recommended next step (which skill to run next, or "ready for platform setup")