بنقرة واحدة
qa-evidence
Use when behavior needs concrete proof before review, merge, or shipment.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Use when behavior needs concrete proof before review, merge, or shipment.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | qa-evidence |
| description | Use when behavior needs concrete proof before review, merge, or shipment. |
Lifecycle stage: VERIFY
Use after build or before review/ship.
Do not use when this trigger is absent; choose the command or skill that owns the requested state, artifact, and verification gate.
| Shortcut | Rebuttal |
|---|---|
| "This is obvious." | Write the assumption and evidence. If you cannot, it is not obvious. |
| "We can do this later." | If the missing step changes the decision, do it now or state the risk. |
| "The user wants speed." | Reduce scope; do not skip the quality bar. |
| "This does not need verification." | Every important claim or behavior needs proof. |
QA Evidence
Use templates/qa-evidence.md. The artifact should be concise, auditable, and include evidence, blockers, and next action so another agent can resume.
Trigger: a build claims a route or behavior works. Action: tie the claim to exact commands, checked artifacts, schema validation, diff checks, scrub results, and blocked runtime commands. Output artifact: templates/qa-evidence.md with blockers and next action. Verification: cite command output, artifact path, expected result, and unresolved gaps.
A build claims, "The command router works." QA evidence should name the exact command, fixture or runtime checked, expected artifact, schema validation, git diff check, public-copy scrub, and any blocked runtime commands before accepting the claim.
Agent Brain /brain-brief: after intake, research, and grill have enough signal.
Agent Brain /brain-build: an implementation plan has a selected task and validation method.
Agent Brain /brain-design: a product brief needs ux or interaction design before planning.
Agent Brain /brain-eval: changing Agent Brain behavior or checking quality.
Agent Brain /brain-grill: the idea, brief, design, or plan has unresolved assumptions.
Agent Brain /brain-learn: after repeated success/failure, a tricky fix, or a shipped workflow.