Mmm Reviewer — Development agent for Claude Code
Adversarial reviewer for a media mix model fit.
How to install Mmm Reviewer
Installs to ~/.claude/agents/mindswim-alpine-mmm-mmm-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/mindswim/alpine-mmm/HEAD/.claude/agents/mmm-reviewer.md -o ~/.claude/agents/mindswim-alpine-mmm-mmm-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Mmm Reviewer does
name: mmm-reviewer description: Adversarial reviewer for a media mix model fit. Use to challenge identification, priors, sensitivity and whether conclusions follow from the evidence, before results are shared. tools: Read, Grep, Glob, Bash
You review an MMM run as a skeptical measurement lead. You are read-only: never edit files.
Read the diagnosis verdict, the model config, `fit-outputs.yaml` and the gate tables for the run under review. Challenge:
- Identification: is each chann
Alternatives in Development
- Media Interpreter 1k ★
- Theorist — Theoretical econometrician / mathematical statistician 250 ★
- Evidence Harvester — Evidence Harvester — rapid code tracer for the Deep Probe phase 125 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Campaign Strategist
Plans cross-platform advertising strategy — channel mix, budget allocation, audience approach, and measurement
Apm
Personas are Opus-only. Angelique, APM — adversarial junior-PM plan reviewer. ELI5 the choice, then challenge
Challenge Assumptions
Probe lens 2 of 6. Surfaces the hidden premises an argument rests on and tests whether the conclusion survives
Appraiser
Use for deep-dive evaluation of one specific job posting — the "evaluate and then ask me" flow. Trigger when t
Decision Loop
Autonomous PIVOT/REFINE/PROCEED decision agent — evaluates iteration results and autonomously decides whether
Prior Elicitation Agent
Help users choose appropriate priors through interactive dialogue and prior predictive checking
Related Skills
Reviewer Verify
You are the adversarial verifier for the candidate pull-request findings raised against one file. Your only jo
Claude Short Answer Skill
Initiate with /short - A Claude Code skill that switches output to summary-only mode - cutting reasoning, walk
Fit Dose Response
Fit dose-response curves and compute IC50/AUC. Use when the user has viability data across drug concentrations