Use when reviewing UI for accessibility — WCAG 2.2 AA, keyboard nav, focus, ARIA, contrast, screen-reader semantics — even on 'is this a11y-OK?' or 'mach das barrierefrei'.
中文简介正在准备中。当前显示原文说明。
Use when a diff may break system boundaries, dependency direction, or cross-service contracts — fifth judge dispatched by /review-changes alongside the four standard judges.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Fifth judge in the
/review-changesfamily. Reviews a diff for architectural fit, not correctness, security, tests, or style. Catches what the other four miss: layer violations, wrong dependency direction, leaking abstractions, and broken cross-service contracts. Sibling ofjudge-bug-hunteret al. — never overlaps.
/review-changes dispatches its "architecture" slice to this skill.Do NOT use when:
judge-bug-hunter.judge-security-auditor.judge-code-quality.decision-record first.Read the codebase's stated architecture (ADRs, AGENTS.md, module docs). If no shape is documented, infer it from folder structure and surface the gap. You are judging the diff against the stated shape, not a fantasy ideal.
For every changed file, answer:
| Question | Smell when "no" |
|---|---|
| Does this file live in the right layer? | Layer violation |
| Are imports flowing in the allowed direction? | Inverted dependency |
| Does this leak a storage / framework detail? | Leaky abstraction |
| Is the public API of the module still the same? | Contract drift |
| Does a cross-service call respect its contract? | Contract break |
Each smell is a finding with a file:line citation.
Pay special attention to:
Cross-module / cross-service additions are the highest-leverage findings — surface them even at low individual severity.
| Verdict | When |
|---|---|
apply | No architectural concerns; diff fits the stated shape |
revise | Findings exist; diff lands after the listed fixes |
reject | Architectural shape itself must be reconsidered (rare) |
reject requires citing which ADR or stated shape would need to
change — never reject for taste.
Verify before emitting: every finding has a file:line citation and
a smell label from the taxonomy; the verdict matches the worst
finding (revise if any finding exists, apply only when none);
reject cites the ADR or stated shape that would need to change.
Ensure no finding restates a concern owned by another judge.
The verdict block carries these ordered fields:
Judge: — fixed value architecture-review-lensModel: and Target: — model id from .agent-settings.yml and diff rangeVerdict: — exactly one of apply / revise / rejectIssues: — numbered list, each with file:line, smell label, suggested fixJudge: architecture-review-lens
Model: <model id from .agent-settings.yml>
Target: <branch / diff range>
Verdict: apply | revise | reject
Issues:
1. 🔴 <finding> file:line
Smell: layer-violation | inverted-dep | leak | contract-drift | contract-break
Suggested fix: <one sentence>
2. 🟡 ...
3. 🟢 ...
decision-record and approve the diff.judge-code-quality.reject without naming the ADR or stated shape that
would need to change.还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when reviewing UI for accessibility — WCAG 2.2 AA, keyboard nav, focus, ARIA, contrast, screen-reader semantics — even on 'is this a11y-OK?' or 'mach das barrierefrei'.
中文简介正在准备中。当前显示原文说明。
Use when defining or auditing the activation event — aha-moment selection, retention correlation, falsifiable definition. Triggers on 'what is our aha moment', 'redefine activation'.
中文简介正在准备中。当前显示原文说明。
Use when capturing an architectural decision — file naming, next ADR number, Status / Context / Decision / Consequences, index regen; fires even without saying 'ADR'.
中文简介正在准备中。当前显示原文说明。
Adversarial critique — devil's advocate, stress-test, honest teardown ('poke holes', 'be brutal', 'was hältst du davon'); explicit request only. Routine code or design review → code-review.
中文简介正在准备中。当前显示原文说明。
Use when reading, creating, or updating agent documentation, module docs, roadmaps, or AGENTS.md. Understands the full .augment/, agents/, and copilot-instructions structure.
中文简介正在准备中。当前显示原文说明。
Use for an adversarial red-team / blue-team / auditor review of an AI agent's CONFIG + behaviour (rules, skills, MCP, hooks, permissions) — attack-chain → defensive-gap list, not a code audit.
中文简介正在准备中。当前显示原文说明。