원클릭으로
vs-verify
Use when asked to verify, prove it works, check completion, or before claiming done. Produces evidence-backed PASS/WARN/FAIL status.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when asked to verify, prove it works, check completion, or before claiming done. Produces evidence-backed PASS/WARN/FAIL status.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Analyze Codex, Claude Code, or Cursor threads, transcripts, and transcriptions. Use for thread analysis, transcript review, conversation audits, agent-performance diagnosis, comparing sessions, finding loops or corrections, and extracting decisions, outcomes, evidence, and actionable improvements.
Internal reference for vs shared conventions: artifact paths, project ID resolution, storage preference, and skill taxonomy.
Use when asked to scan a named external repo for ideas worth porting. Produces a cited, ranked steals report.
Use when asked to QA, test this site or app, find bugs, or test and fix a user-facing interface. Runs harness-aware browser or computer-use QA, fixes issues, and re-verifies.
Use when the user wants to create/open a pull request, submit changes for review, send changes to dev, or otherwise ship local Git changes. Also use for explicit commit and push or push to main/master or the current branch requests. Requires affirmative publish intent; do not use for review/readiness-only requests. Creates and verifies a GitHub PR by default; honors explicit direct pushes and babysits only when requested.
Use when asked to watch a PR, fix CI, address review comments, or keep a branch merge-ready in a loop.
| name | vs-verify |
| description | Use when asked to verify, prove it works, check completion, or before claiming done. Produces evidence-backed PASS/WARN/FAIL status. |
Prove that a change actually works before anyone claims completion.
Use this as a standalone check or as the verification building block inside delivery flows. It is intentionally smaller than QA: QA explores user-visible behavior; verify proves the specific promised outcome with the cheapest sufficient evidence.
## Verification Result with status, evidence, gaps, and next actionPASS, WARN, FAIL, or BLOCKEDvs:build-it, vs:bugfix, vs:fix-pr, vs:ship-it, standalone pre-handoff checksSKIPPED_TRIVIAL with the reason.Use the cheapest check that proves the behavior. Stop when the proof is strong enough; do not run the entire suite by reflex.
WARN.PASS without naming the command, check, or observation that
proved the claim.FAIL and the smallest useful failure excerpt.BLOCKED and name exactly what
is missing.WARN,
not PASS.WARN until artifact
identity is confirmed.Consumers repeat the verify status; they do not soften it:
WARN, FAIL, or BLOCKED, the
summary must not say "fixed", "working", or "complete" — say what was proven
and what was not, e.g. "Deployed; fix not verified against the reported
crash."## Verification Result
- Status: PASS | WARN | FAIL | BLOCKED
- Claim: <what was being proven>
- Evidence:
- `<command or observation>` - <result>
- Gaps:
- <anything not proven, or "none">
- Next action:
- <ship / fix / run QA / ask user / unblock environment>
Direct: emit Next only. Composed: return to caller.
Prev: /vs-build-it | /vs-bugfix | /vs-fix-pr | /vs-qa
Next: /vs-ship-it
Relevant: /vs-perf | /vs-tdd