Menu
Post-edit verification workflow for lint, typecheck, tests, and spot checks.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Shared protocol for review-shaped actions, authorization scope, defect routing, L2 audit handling, and local-only capture.
Use when the user asks to "test TPC-H", "check compliance", "review architecture", "run quality checks", "check binaries", "test dialect translation", "compare implementations", "run live platform tests", or "plan and execute" a benchmark feature.
Use for "commit code", "review code", "fix lint/type error", "improve performance", "compare code", "shrink code", "generate spec from code", "investigate code", "debug an error", "triage a bug", "iterate to green", or "create handoff prompt".
Use when the user asks to "create documentation", "build docs", "review docs", "compare documents", "compress docs", "adversarial review docs", or "commit docs".
Use when the user asks to "sync skills", "set up skill-sync", "check skill status", "validate skills", "preview skill changes", "diagnose skills", "pin a skill", "unpin a skill", "prune skills", or "promote skill changes".
Use when the user asks to "run tests", "create tests", "fix failing test", "add test coverage", "fix slow tests", or "commit test changes".
| name | verify-framework |
| description | Post-edit verification workflow for lint, typecheck, tests, and spot checks. |
Run before return/stage/commit.
Never silently skip verification; if unavailable, report why.
Fix failures before committing or clearly report blocker.
Report command, result, and residual risk.
Narrowest check that proves the change first; full fast/preflight are final gates, not exploration. Long output → log file, report summary.
When a low-effort subagent is available, the main agent may delegate boilerplate deterministic gate runs — full/default test suite, project preflight, CI status check, push, PR-open equivalent, PR-followup runner, or any long run-and-report gate. The main agent chooses the command, cwd, log path, max runtime, and stop condition, and keeps all failure analysis, fixes, scope decisions, retries, and final reporting. The subagent only runs that command and reports status, log tail, PR URL, and check state — no edits, scope/command changes, unrequested retries, review-thread resolution, or policy calls. Gates still run unchanged; only who waits on them shifts. With no subagent or reasoning-effort control available, run the gate inline as before.
