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
.claude/commands/prioritize-hypotheses.mdWhat 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.mdCall it with /prioritize-hypotheses. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/prioritize-hypotheses.mdCall it with /prompts:prioritize-hypotheses. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/prioritize-hypotheses.prompt.mdManually: put the files in place
.gemini/commands/prioritize-hypotheses.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
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