Agent skill · software engineering · steipete
auto-qa
Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.
Why this skill is useful
Adds a comprehensive automated QA framework with specific commands and workflows for OpenClaw that are not publicly documented.
What it needs
Requires docker installed locally. About 10k tokens when loaded. Last updated 2026-08-07. 385,400 stars on the source repository.
What this skill does
OpenClaw Auto QA Run a continuous, current-main OpenClaw product campaign. Treat a reviewer finding as a hypothesis, a passing test as evidence only for its actual head, and a merge as complete only when the canonical repository confirms it. Always prefer a clean, appropriately scoped root-cause refactor over a quick fix or smaller diff. Repair the actual root cause in its canonical owner; a patch is not acceptable when it leaves sibling paths, lifecycle invariants, or the defective abstraction intact. Set the campaign goal Default to 100 distinct, independently verified, actually merged root-cause fixes unless the operator explicitly specifies a different target. Count broken invariants, not pull requests, symptoms, proposed patches, skill updates, or merely passing tests. When the operator changes the target during an active campaign, update the existing report, numbered ledger, progress denominator, and live status in place. Preserve every previously verified landing; never reset the investigation or claim that an unfinished target has been reached. Exclude security-sensitive, persistent-state, protocol, public-contract, or otherwise review-required work from the accepted count until the appropriate owner explicitly authorizes and verifies its landing. Prefer clean refactors over quick fixes Identify the broken ownership boundary, abstraction, state transition, or dependency contract before choosing an implementation. Compare the canonical owner, callers, callees, and sibling paths; prefer the design that makes their shared invariant obvious and reliable. Consolidate decisions and authoritative state in their actual owner. Propagate prepared facts through existing lifecycles, repair all affected siblings, and delete obsolete branches, duplicate policy, dead helpers, and stale abstractions when they are no longer needed. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills steipete/auto-qa