Menu
Use when reviewing VibePro PR preparation artifacts, deciding whether to proceed, split, add evidence, waive with reason, or block.
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
Use when recording VibePro verification or review evidence, writing Architecture/Spec artifacts, or resolving blocked gates when pr prepare reports needs_verification, needs_review, or unresolved gate ids.
Use when the user asks VibePro to check UI, security, performance, architecture, PR readiness, launch readiness, or performance improvement evidence.
Use when working with VibePro CLI, Graphify, Story diagnosis, task planning, PR preparation, Gate evidence, or VibePro review artifacts.
Use when refactoring with VibePro so the agent follows Story -> Architecture -> Spec -> Task -> Code -> Gate -> PR instead of editing code first.
Use when generating, reviewing, or repairing Japanese business meeting minutes from transcripts, Slack attachments, recordings, or Meeting Pack inputs.
Use when VibePro work needs codebase-memory-mcp impact context for changed files, call paths, routes, symbols, or risk hints without treating topology as correctness evidence.
| name | vibepro-human-review |
| description | Use when reviewing VibePro PR preparation artifacts, deciding whether to proceed, split, add evidence, waive with reason, or block. |
Use this Skill when a human or AI reviewer needs to interpret VibePro PR artifacts. pr-prepare.json is the readiness source of truth; the review cockpit is the human control plane.
Use this Skill when deciding whether a VibePro-prepared change should proceed, split, add evidence, waive with reason, or block. It applies to PR readiness reviews, merge readiness checks, waiver decisions, and cases where the user asks whether VibePro evidence is enough.
.vibepro/pr/<story-id>/pr-prepare.json gate_status.gate_status.overall_status, ready_for_pr_create, unresolved Gates, and critical unresolved Gates.gate_status.agent_review_instruction is present, block human approval until the coordinator has authorization to use subagents and then has:
vibepro review prepare commands,parallel-dispatch.md requests to parallel subagents,vibepro review record including Codex/Claude Code subagent provenance and --agent-closed,vibepro pr prepare and cleared gate:agent_review.
If the coordinator runtime cannot spawn subagents, treat that as a blocker or require a human waiver decision. Do not accept manual review records as a substitute for required Codex/Claude Code subagent provenance..vibepro/pr/<story-id>/decision-index.json and .vibepro/pr/<story-id>/evidence-plan.json when present, especially generated/skipped artifacts and review path references..vibepro/pr/<story-id>/review-cockpit.html when it was generated for the selected evidence depth.split-plan.json / split-plan.html when present..vibepro/design-modernize/<story-id>/derived-design-system.json, design-modernize.json, and ds-gate.json. Confirm that current routes, information architecture, CTA priority, state behavior, and data dependencies are preserved unless the Story/Spec explicitly changes them.Performance Evidence summary in pr-body.md if present, then verify the JSON runs under .vibepro/pr/<story-id>/performance-runs/.vibepro pr create before PR creation and vibepro execute merge before merge.human-review.json, fill the review record, and keep it as the human decision artifact.proceed: Use only when gate_status.ready_for_pr_create=true, gate_status.overall_status=ready_for_review, and the split-plan does not require separation.split_pr: Use when scope is broad, repo-control files are mixed in, or split-plan recommends lanes.add_evidence: Use when required Gates need test, typecheck, integration, E2E, or requirement evidence.waive_with_reason: Use only with a specific reason for non-critical unresolved Gates. Critical unresolved Gates cannot be approved by reason alone.block: Use when Story, Architecture, Spec, security, or Gate evidence is contradictory or insufficient.Fill these fields in human-review.json:
review_record.selected_decisionreview_record.reviewerreview_record.reasonreview_record.reviewed_atreview_record.comments when neededreview-cockpit.html as machine-readable truth; use the JSON sidecars.scope.status=reviewable as completion approval. It is PR size/scope guidance only.pr-prepare.json, decision/evidence indexes, Gate DAG evidence, and verification artifacts are the review control plane.gh pr create; it bypasses VibePro Gate enforcement and waiver recording.pass review result that lacks Codex/Claude Code parallel subagent provenance and closed lifecycle evidence (--agent-closed) when gate:agent_review is required. It is a coordinator note, not verified subagent review evidence.vibepro pr create --allow-needs-verification --verification-waiver <reason>.改善率不明 / not_comparable.browser_e2e, client_marker, or manual_observation.ds-gate.json is missing, has implicit fallback, or omits DS drift / component role / composition / anti-pattern checks.pr-prepare.json, decision/evidence indexes, Gate DAG evidence, and verification artifacts are the machine-readable truth.ready_for_pr_create is false, missing, or contradicted by unresolved gates.--agent-closed.not_comparable or 改善率不明 while the PR claims improvement.Record the final decision from current pr-prepare.json, decision-index.json, evidence-plan.json, Gate DAG evidence, generated review surfaces, and human-review.json. If the decision is proceed, confirm gate_status.ready_for_pr_create=true, overall_status=ready_for_review, no critical unresolved gates, and no split requirement. If the decision is waive, record the exact waiver reason and affected gates.
For a PR that claims speed improvement, require:
performanceMetrics[]..vibepro/pr/<story-id>/performance-runs/*.json.metricId and completionCondition.blocked, needs_review, timeout, auth_required, resource_unavailable, or unknown runs are retained instead of silently dropped.