Skip to main content
command CX Codex

prioritize-hypotheses — Claude Code command: setup and guide

prioritize-hypotheses scores product experiment backlogs with ICE or RICE while factoring in sprint capacity and guardrail readiness.

Apache-2.0 ★ 450 updated 2026-04-03

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/prioritize-hypotheses.md
Open on GitHub

What prioritize-hypotheses does

The command imports hypotheses from a CSV file, experiment tracker, or Notion database, standardizing input fields before running the scoring engine. It supports ICE, RICE, or custom weighting schemes while evaluating guardrail readiness across each candidate test.

The pipeline covers data ingestion, score calculation, funnel stage distribution, capacity planning, and decision pack generation. The final output includes a ranked backlog with dependencies, a capacity allocation plan with a waitlist, and a decision memo detailing trade-offs.

The workflow requires an existing backlog source file or database ID to evaluate metrics and allocate sprint slots.

What it helps with

  • rank experiment ideas using standard ICE or RICE formulas
  • fit top-scoring tests into defined sprint capacity slots
  • verify test distribution across conversion funnel stages
  • generate a decision memo outlining test trade-offs

Example prompts for the agent

  • /growth-experiments:prioritize-hypotheses --source backlog.csv --capacity 6 --framework rice
  • /growth-experiments:prioritize-hypotheses --source notion_db_id --capacity 4 --framework ice --filters activation
  • /growth-experiments:prioritize-hypotheses --source experiments.csv --capacity 5 --framework custom --guardrails guardrails.json

How to install prioritize-hypotheses

Manually: put the files in place

.claude/commands/prioritize-hypotheses.md

Call it with /prioritize-hypotheses. For all projects use ~/.claude/commands/

Questions about prioritize-hypotheses

How to install prioritize-hypotheses in Claude Code?

Place the command file at .claude/commands/prioritize-hypotheses.md within your project repository.

What does prioritize-hypotheses do?

It scores candidate growth tests, checks guardrail constraints, and allocates highest-priority items to available sprint slots.

Which prioritization frameworks can be selected?

The --framework parameter accepts ICE, RICE, or custom scoring modes.

Source text

prioritize-hypotheses.md · Apache-2.0
---
name: prioritize-hypotheses
description: Scores experiment backlog using impact, confidence, effort, and guardrail readiness.
usage: /growth-experiments:prioritize-hypotheses --source backlog.csv --capacity 6 --framework rice
---

# Command: prioritize-hypotheses

## Inputs
- **source** – backlog file, experiment tracker, or Notion database ID.
- **capacity** – number of experiments that can run in the next sprint/cycle.
- **framework** – ice | rice | custom; determines scoring weights.
- **guardrails** – optional JSON/CSV for mandatory guardrail requirements.
- **filters** – tags or OKRs to focus on (acquisition, activation, retention, monetization).

## Workflow
1. **Data Ingestion** – load backlog, normalize fields, and enrich with latest metrics.
2. **Scoring Engine** – calculate ICE/RICE/custom scores, factoring guardrail readiness.
3. **Portfolio Mix** – ensure balance across funnel stages and surfaces; flag conflicts.
4. **Capacity Planning** – fit highest-value tests into available slots, accounting for owners + effort.
5. **Decision Pack** – generate prioritized list, rationale, and trade-off notes for approval.

## Outputs
- Ranked backlog with scores, dependencies, and guardrail status.
- Capacity plan showing selected tests plus waitlist.
- Decision memo summarizing trade-offs and next actions.

## Agent/Skill Invocations
- `experimentation-strategist` – orchestrates prioritization + governance alignment.
- `insight-analyst` – validates data quality and metric assumptions.
- `hypothesis-library` skill – links past learnings to current ideas.
- `guardrail-scorecard` skill – enforces readiness requirements.

---

© gtmagents · Apache-2.0 · gtmagents/gtm-agents

Similar slash commands

All slash commands for Marketing and content →

From the same set224

The whole set →
plan-merchandising-campaign plan-merchandising-campaign builds an omni-channel merchandising campaign plan with offers, creative, and a QA checklist. CX Codex +1 ★ 450repo stars monitor-retention monitor-retention generates cohort retention dashboards, risk signal summaries, and customer save plays directly in Claude Code. CX Codex +1 ★ 450repo stars simulate-pricing-impact simulate-pricing-impact is a Claude Code command that models how price changes affect ARR, margin, churn, and expansion by segment, for comparing scenarios before repricing. CX Codex +1 ★ 450repo stars design-packaging design-packaging is a command that builds pricing packages with features, limits, and usage metrics for customer segments. CX Codex +1 ★ 450repo stars trend-research The trend-research skill helps spot cultural moments, audio trends, memes, and creators for social content. Use it when planning timely posts or refreshing a campaign’s creative direction. CX Codex +1 ★ 450repo stars design-curriculum-partnership design-curriculum-partnership turns an education partner conversation into a curriculum alignment plan, a pilot outline and a co-marketing roadmap. CX Codex +1 ★ 450repo stars analyze-competitive-landscape analyze-competitive-landscape — a Claude Code command that produces a competitive brief with threat levels, a differentiator map, and a stakeholder-specific action plan. CX Codex +1 ★ 450repo stars route-approvals route-approvals is a Claude Code command that assigns reviewers to scheduled social posts, gathers edits, and tracks sign-off before publication. CX Codex +1 ★ 450repo stars

Project sponsors

Companies that keep this analytics open