Menü
Trigger only to inspect an existing diff, commit, branch, or PR for correctness, regression, security, performance, and maintainability issues; do not use to implement changes or run acceptance verification.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | review-diff |
| description | Trigger only to inspect an existing diff, commit, branch, or PR for correctness, regression, security, performance, and maintainability issues; do not use to implement changes or run acceptance verification. |
| requires | [] |
Use this skill only when there is an existing change set to review:
execute-plan.Do not use this skill to implement requested changes, debug an observed failure, create a plan, or verify acceptance criteria after implementation.
critical or high only for correctness, security, data loss, regression, build breakage, or severe maintainability risk.approved: true is allowed only when no critical or high issues remain.Resolve the review target and changed files. If no diff target exists, return blocked.
Review changed logic for:
Use severity definitions:
critical: likely data loss, security compromise, production outage, or unrecoverable broken build.high: likely user-visible regression, failing core path, serious correctness issue, or unsafe behavior.medium: plausible bug or maintainability problem with limited blast radius.low: cleanup, readability, minor consistency, or non-blocking improvement.Approve only if blocking severities are empty. Include a short rationale either way.
approved: true when critical or high findings exist.status: reviewed | blocked
approved: boolean
target: string
targetType: pr | branch | commit | diff-file | worktree | unknown
summary: string
issues:
critical:
- file: string
line: number | null
title: string
impact: string
recommendation: string
high: []
medium: []
low: []
blockedReason: string | null
Trigger only when an already-approved PLAN.md or equivalent structured plan must be executed through wave-ordered tasks, isolated git worktrees, wave-level verification, final integration, and controlled merge handling; never create the plan or execute unapproved work.
Trigger only when an observed failure, reproducible bug, regression, stack trace, failing test, or merge conflict requires evidence-based root-cause diagnosis before applying or recommending a fix.
Trigger only when the user explicitly requests test-driven implementation or when an assigned task requires adding behavior by first writing a failing test, then minimal code, then refactoring without behavior change.
Trigger only when a coding task requires a written implementation plan before execution, especially multi-file or multi-step work needing dependency analysis, wave classification, and file-isolation-safe task partitioning; dispatches Planner to write a timestamped plan under ~/.yi-workflow/docs/plans/ and performs no implementation.
Trigger only after an implementation exists and must be validated against an explicit plan, acceptance criteria, or expected behavior by running relevant checks and reporting evidence-backed pass/fail results.