From rp1-dev
Validates pending design hypotheses in features/hypotheses.md via rp1-dev:hypothesis-tester agent using code experiments, codebase analysis, and research. Handles rejections with user overrides.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rp1-dev:validate-hypothesisThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Invokes **hypothesis-tester** agent to validate design assumptions.
Invokes hypothesis-tester agent to validate design assumptions.
Extract these parameters from the user's input:
| Parameter | Required | Default | Description |
|---|---|---|---|
FEATURE_ID | Yes | - | Feature identifier whose hypotheses to validate (kebab-case) |
Environment values (resolve via shell):
RP1_ROOT: !rp1 agent-tools rp1-root-dir (extract data.root from JSON response){{$RP1_ROOT}}/work/features/{FEATURE_ID}/hypotheses.md MUST exist{% dispatch_agent "rp1-dev:hypothesis-tester" %} FEATURE_ID: {FEATURE_ID} RP1_ROOT: {{$RP1_ROOT}} Validate all PENDING hypotheses for this feature. {% enddispatch_agent %}
Agent actions: load hypotheses.md -> parse PENDING -> validate via experiment/analysis/research -> document findings w/ evidence -> update status CONFIRMED|REJECTED -> cleanup temp artifacts -> report summary
Parse agent output. If JSON block w/ type: "rejected_hypotheses":
{
"type": "rejected_hypotheses",
"hypotheses": [...],
"hypotheses_path": "..."
}
For each rejected:
{% ask_user "{id} REJECTED: {statement}. Evidence: {evidence_summary}. Domain knowledge confirms valid?", options: "Accept rejection", "Override - I confirm valid" %}
If "Override":
REJECTED -> CONFIRMED_BY_USER**User Override**: User confirmed validity based on domain knowledge.If "Accept rejection": No change (status remains REJECTED)
Display validation summary. Note any user overrides.
npx claudepluginhub rp1-run/rp1Produces structured probe plans to minimally validate blocking or high-risk assumptions in product discovery or spec phases before advancing.
Surfaces, refines, and manages testable hypotheses about a project. Tracks status (untested, confirmed, invalidated, archived), adds evidence from web research, and generates next validation actions.
Validates development rules using scientific method: register hypotheses, design experiments, execute, score confidence, and graduate or kill rules based on evidence.