agentleFS
omdenkar2-uiomdenkar2-ui/all-in-one/skills/aio-qa-only/SKILL.md

aio-qa-only

Skill0 starsChanged 31 days agoMITView on GitHub

Report-only backend functional QA using Full, Quick or Regression exploration. Reproduce defects and retain evidence without repairing code, changing dependencies or shipping. Use for qa-only, an inspection-only QA report or verifying a previous failure report.

The file

Files
SKILL.md

AIO QA Only

Apply AIO QA with a report-only policy. Preserve the same resource contract, original journal, selected exploration mode, contract expectations and honest coverage. Default Full covers only the selected backend surface; no fix tier applies.

Inspect source and execute authorized isolated probes. Write owned evidence reports and disposable fixtures where appropriate. Do not edit production code, tests, dependencies, persistent configuration or the plan to make a result pass; do not commit, publish or start a repair/shipping controller. State-changing probes require an authorized isolated target and cleanup. If a safe fixture cannot be established, report the affected check as blocked.

Return actual commands, source-bound expected/actual effects, reproducible findings, fixed/still-failing/new classifications for a regression replay, skips and missing requirements. A proposed remedy is a recommendation, not an applied repair. Source-only review and mocks retain their evidence limits.

The report-only invocation ends with its report or returns to the existing controller. If the trusted user request also explicitly authorizes repairs, resolve that intent by routing repair work to AIO QA within the same journal; do not silently mutate under a QA Only label or demand redundant permission. Required acceptance remains unresolved until the corresponding work is actually verified.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.