Test Claw
test-claw
v0.2.0May 20, 2026Test automation — unit, integration, and E2E strategies with frameworks that catch real bugs, not just increase coverage numbers
Tests that pass today and fail tomorrow without a code change are worse than no tests — they erode trust in the suite. I write deterministic tests with explicit setup, hermetic environments, and assertions that fail with messages telling you exactly what broke, because a red build at 4 PM on a Friday should take minutes to diagnose, not hours.
PRIMARY ACTION
Unlock with ProWhen to Use
- Implement production-grade code and architecture
- Audit design decisions and tradeoffs
- Catch reliability issues before release
- Raise quality consistency across teams
Compatible Frameworks
8 TOOLS
Quality Gates
- Verify test covers happy and unhappy paths
- Check assertions are meaningful
- Validate tests are deterministic
- Ensure no test pollution between cases
3 GATES DEFINED
Expected Outputs
Native exports per tool
openclaw/AGENTS.mdopenclaw/SOUL.mdopenclaw/TOOLS.md+7 morehermes/skills/flickclaw/test-claw/SKILL.mdhermes/skills/flickclaw/test-claw/references/workflow.mdhermes/skills/flickclaw/test-claw/references/quality-gates.md+2 moreclaude-code/CLAUDE.mdclaude-code/.claude/skills/test-claw/SKILL.mdclaude-code/.claude/skills/test-claw/references/workflow.md+3 morecodex/AGENTS.mdcodex/.flickclaw/agents/test-claw/codex.mdcodex/.flickclaw/agents/test-claw/workflow.md+2 morecursor/.cursor/rules/flickclaw-test-claw.mdccursor/.cursor/rules/flickclaw-test-claw-workflow.mdccursor/.cursor/rules/flickclaw-test-claw-quality-gates.mdcwindsurf/.windsurf/rules/flickclaw-test-claw.mdwindsurf/.windsurf/rules/flickclaw-test-claw-workflow.mdwindsurf/.windsurf/rules/flickclaw-test-claw-quality-gates.mdaider/CONVENTIONS.mdaider/aider.mdaider/.aider.conf.ymlollama/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
npm exec --yes @flickclaw/cli@latest -- install test-claw --target openclawDownload as ZIP
Example Prompt
Try this prompt with Test Claw to see what it can do:
Review the codebase architecture and identify 3 areas for improvement. Focus on maintainability, test coverage, and performance. Produce Test Suite Implementation (Unit + Integration + E2E), Test Fixture Factory with Isolated State per Test, CI Test Configuration with Flakiness Detection and Quarantine.Example Output
IllustrativeWhat a typical Test Claw report looks like:
# Test Claw — Assessment Report **Project**: data-pipeline **Context**: an ETL pipeline processing 2M events/hour with PostgreSQL and Redis **Generated**: 2026-07-10 ## Executive Summary The Test Claw completed its review of data-pipeline (an ETL pipeline processing 2M events/hour with PostgreSQL and Redis). 3 findings were identified with concrete remediation steps. All quality gates were verified before delivery. ## Findings | # | Severity | Area | Finding | Recommended Action | |---|----------|------|---------|-------------------| | 1 | **P0** | Performance | N+1 queries in batch processing loop | Use eager loading with batch size 500 | | 2 | **P1** | Architecture | Tight coupling between extract and transform | Introduce event queue with dead letter handling | | 3 | **P2** | Testing | No integration tests for Redis failover | Add chaos test with Redis connection drop | ## Quality Gates - [✓] tests_are_deterministic_no_flaky_dependencies_on_time_network_or_order - [✓] every_assertion_has_a_descriptive_failure_message - [✓] test_fixtures_are_isolated_no_shared_mutable_state_between_tests ## Outputs Generated - **Test Suite Implementation (Unit + Integration + E2E)**: Included in the report above. - **Test Fixture Factory with Isolated State per Test**: Included in the report above. - **CI Test Configuration with Flakiness Detection and Quarantine**: Included in the report above. ## Validation - [x] All quality gates passed (3/3) - [x] 3 findings documented with severity and remediation - [x] 3 output sections generated - [x] Evidence collected and referenced --- *This is an illustrative example output from FlickClaw. Results vary based on project context.*