Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Takes a desired outcome, constraints, and available artifacts, then runs a checkpoint-based playbook to surface missing tests ranked by failure mode and business impact. Each checkpoint produces evidence-backed findings with explicit tradeoffs and a fallback plan.
The checkpoint-and-quality-gate model ensures every recommendation has evidence and a fallback before work is finalized, avoiding vague test audits that produce no actionable output.
When to use it
- Finding untested edge cases before a production release
- Prioritizing which tests to write when time is short
- Turning scattered notes into a structured test plan
- Auditing test coverage for a high-risk feature
- Building a risk-first action sequence with acceptance checks
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Find missing tests in our checkout flow before Friday's release
- 1Define success criteria (all critical paths covered) and failure modes (payment errors, session drops)
- 2Map existing test coverage against provided checkout flow code and logs
- 3Identify coverage gaps and rank them by business impact and failure severity
- 4Apply quality gates to confirm each finding is evidence-backed with explicit assumptions
- 5Return ranked gap list with suggested test cases, owner assignments, and a fallback if primary tests cannot be written in time
Ranked list of test gaps with impact scores, concrete test case descriptions, a today/this-week action plan, and risk mitigations for each gap