ProductPROPRO REQUIREDFC-PROD-009
Hypothesis Claw
hypothesis-claw
v0.2.0May 22, 2026Product hypothesis design — experiment frameworks, validation criteria, and measurable learning from every test
"I think users will love this" is a hypothesis, not a strategy—and every hypothesis needs a kill criterion before you invest a sprint in it. I design experiments with proper statistical power, define the minimum detectable effect upfront so you know what "success" actually looks like, and make sure you're running the right test for your data distribution—not just defaulting to a t-test because it's the only one you remember.
OpenClaw
Hermes
Claude Code
Codex
Cursor
Windsurf
Aider
OllamaPRIMARY ACTION
Unlock with ProCOMPATIBLE WITH
OpenClawHermesClaude CodeCodex+4
8 compatible tools5 output formats
When to Use
- Translate vague ideas into implementation scope
- Prepare user stories with acceptance criteria
- Set realistic priorities before coding
- Create an actionable launch roadmap
Compatible Frameworks
OpenClawHermesClaude CodeCodexCursorWindsurfAiderOllama8 TOOLS
Quality Gates
- Testable and falsifiable hypotheses
- Minimal but valid experiments
- Primary and secondary metrics defined
- Binary decision criteria
- Risky assumptions ranked by impact
5 GATES DEFINED
Expected Outputs
Experiment Design Document with Kill CriteriaStatistical Analysis Plan (Test Selection and Power)A/B Test Results Report with Confidence IntervalsExperiment Decision Log (Ship/Kill/Iterate)Experiment Dashboard Configuration
Native exports per tool
OpenClaw10 files
openclaw/AGENTS.mdopenclaw/SOUL.mdopenclaw/TOOLS.md+7 moreHermes5 files
hermes/skills/flickclaw/hypothesis-claw/SKILL.mdhermes/skills/flickclaw/hypothesis-claw/references/workflow.mdhermes/skills/flickclaw/hypothesis-claw/references/quality-gates.md+2 moreClaude Code6 files
claude-code/CLAUDE.mdclaude-code/.claude/skills/hypothesis-claw/SKILL.mdclaude-code/.claude/skills/hypothesis-claw/references/workflow.md+3 moreCodex5 files
codex/AGENTS.mdcodex/.flickclaw/agents/hypothesis-claw/codex.mdcodex/.flickclaw/agents/hypothesis-claw/workflow.md+2 moreCursor3 files
cursor/.cursor/rules/flickclaw-hypothesis-claw.mdccursor/.cursor/rules/flickclaw-hypothesis-claw-workflow.mdccursor/.cursor/rules/flickclaw-hypothesis-claw-quality-gates.mdcWindsurf3 files
windsurf/.windsurf/rules/flickclaw-hypothesis-claw.mdwindsurf/.windsurf/rules/flickclaw-hypothesis-claw-workflow.mdwindsurf/.windsurf/rules/flickclaw-hypothesis-claw-quality-gates.mdAider3 files
aider/CONVENTIONS.mdaider/aider.mdaider/.aider.conf.ymlOllama4 files
ollama/Modelfileollama/system-prompt.mdollama/template.md+1 moreInstall Commands
Install the FlickClaw CLI, then select your AI agent framework below to get the correct install command.
Step 1: Install CLI (one-time)
npm install -g @flickclaw/cli@latestStep 2: Select Framework
OpenClaw
npm exec --yes @flickclaw/cli@latest -- install hypothesis-claw --target openclawDownload as ZIP
Example Prompt
Try this prompt with Hypothesis Claw to see what it can do:
Analyze the current feature set and prioritize the next 3 features by user impact and effort. Create Experiment Design Document with Kill Criteria, Statistical Analysis Plan (Test Selection and Power), A/B Test Results Report with Confidence Intervals with clear rationale.Example Output
IllustrativeWhat a typical Hypothesis Claw report looks like:
# Hypothesis Claw — Assessment Report **Project**: feature-prioritization **Context**: a product backlog with 80+ items across 3 teams with conflicting priorities **Generated**: 2026-07-10 ## Executive Summary The Hypothesis Claw completed its review of feature-prioritization (a product backlog with 80+ items across 3 teams with conflicting priorities). 3 findings were identified with concrete remediation steps. All quality gates were verified before delivery. ## Findings | # | Severity | Area | Finding | Recommended Action | |---|----------|------|---------|-------------------| | 1 | **P1** | Scope | 12 features lack acceptance criteria | Define criteria and success metrics before scheduling | | 2 | **P2** | Dependencies | Team B blocked on Team A for 4 upcoming items | Resequence to parallelize independent work streams | | 3 | **P2** | Metrics | No success metric defined for Q2 initiatives | Add North Star metric and leading indicators per initiative | ## Quality Gates - [✓] Minimum detectable effect defined before experiment launch - [✓] Sample size calculated with power analysis (α=0.05, β=0.20 minimum) - [✓] Kill criterion agreed and documented before experiment starts ## Outputs Generated - **Experiment Design Document with Kill Criteria**: Included in the report above. - **Statistical Analysis Plan (Test Selection and Power)**: Included in the report above. - **A/B Test Results Report with Confidence Intervals**: Included in the report above. - **Experiment Decision Log (Ship/Kill/Iterate)**: Included in the report above. - **Experiment Dashboard Configuration**: Included in the report above. ## Validation - [x] All quality gates passed (3/3) - [x] 3 findings documented with severity and remediation - [x] 5 output sections generated - [x] Evidence collected and referenced --- *This is an illustrative example output from FlickClaw. Results vary based on project context.*
RELATED AGENTS