ProductFREEACCESS AVAILABLEFC-PROD-012
Discovery Claw
discovery-claw
v0.2.0May 22, 2026Product discovery — research plans, validation gates, and decision frameworks that separate signals from noise
Building the wrong thing faster just means you'll have more features to sunset when nobody uses them. I run continuous discovery with customer interviews shaped by Teresa Torres' opportunity solution trees, catalog your riskiest assumptions before you write a line of code, and make sure every solution traces back to a validated problem—not a HiPPO's pet idea from last quarter's offsite.
OpenClaw
Hermes
Claude Code
Codex
Cursor
Windsurf
Aider
OllamaPRIMARY ACTION
COMPATIBLE 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
- Problem defined before solution
- Answerable research questions
- Gates with clear pass/fail criteria
- Non-leading interview guide
- Structured synthesis framework
5 GATES DEFINED
Expected Outputs
Opportunity Solution Tree (Current State)JTBD Interview Synthesis DocumentAssumption Test Plan with Kill CriteriaDiscovery Sprint Summary with Key DecisionsCustomer Interview Repository Index
Native exports per tool
OpenClaw10 files
openclaw/AGENTS.mdopenclaw/SOUL.mdopenclaw/TOOLS.md+7 moreHermes5 files
hermes/skills/flickclaw/discovery-claw/SKILL.mdhermes/skills/flickclaw/discovery-claw/references/workflow.mdhermes/skills/flickclaw/discovery-claw/references/quality-gates.md+2 moreClaude Code6 files
claude-code/CLAUDE.mdclaude-code/.claude/skills/discovery-claw/SKILL.mdclaude-code/.claude/skills/discovery-claw/references/workflow.md+3 moreCodex5 files
codex/AGENTS.mdcodex/.flickclaw/agents/discovery-claw/codex.mdcodex/.flickclaw/agents/discovery-claw/workflow.md+2 moreCursor3 files
cursor/.cursor/rules/flickclaw-discovery-claw.mdccursor/.cursor/rules/flickclaw-discovery-claw-workflow.mdccursor/.cursor/rules/flickclaw-discovery-claw-quality-gates.mdcWindsurf3 files
windsurf/.windsurf/rules/flickclaw-discovery-claw.mdwindsurf/.windsurf/rules/flickclaw-discovery-claw-workflow.mdwindsurf/.windsurf/rules/flickclaw-discovery-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 discovery-claw --target openclawDownload as ZIP
Example Prompt
Try this prompt with Discovery Claw to see what it can do:
Analyze the current feature set and prioritize the next 3 features by user impact and effort. Create Opportunity Solution Tree (Current State), JTBD Interview Synthesis Document, Assumption Test Plan with Kill Criteria with clear rationale.Example Output
IllustrativeWhat a typical Discovery Claw report looks like:
# Discovery 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 Discovery 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 - [✓] Customer interviews conducted within current sprint - [✓] Assumptions cataloged and prioritized by risk (not confidence) - [✓] Opportunity sized with TAM/SAM/SOM estimates before solution design ## Outputs Generated - **Opportunity Solution Tree (Current State)**: Included in the report above. - **JTBD Interview Synthesis Document**: Included in the report above. - **Assumption Test Plan with Kill Criteria**: Included in the report above. - **Discovery Sprint Summary with Key Decisions**: Included in the report above. - **Customer Interview Repository Index**: 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