本文へ移動
cccskills
無料GitHub で公開

architecture-review-lens

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.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md4.8 KB
  • evals/triggers.json933 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

architecture-review-lens

Fifth judge in the /review-changes family. 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 of judge-bug-hunter et al. — never overlaps.

When to use

  • /review-changes dispatches its "architecture" slice to this skill.
  • A reviewer asks "does this belong here?", "should this be in the domain layer?", or "is this leaking storage details?".
  • A diff adds a cross-service call, event, or contract.

Do NOT use when:

Procedure

1. Anchor on the system shape

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.

2. Inspect each changed file for fit

For every changed file, answer:

QuestionSmell 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.

3. Check the seams

Pay special attention to:

  • New public methods on existing classes.
  • New imports that cross module boundaries.
  • New events, queue messages, or HTTP calls.
  • Removed deprecation warnings or feature flags.

Cross-module / cross-service additions are the highest-leverage findings — surface them even at low individual severity.

4. Issue a verdict per the judge contract

VerdictWhen
applyNo architectural concerns; diff fits the stated shape
reviseFindings exist; diff lands after the listed fixes
rejectArchitectural shape itself must be reconsidered (rare)

reject requires citing which ADR or stated shape would need to change — never reject for taste.

5. Validate the verdict

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.

Output format

The verdict block carries these ordered fields:

  1. Judge: — fixed value architecture-review-lens
  2. Model: and Target: — model id from .agent-settings.yml and diff range
  3. Verdict: — exactly one of apply / revise / reject
  4. Issues: — numbered list, each with file:line, smell label, suggested fix
Judge:  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. 🟢 ...

Gotcha

  • The stated shape may be wrong. If the diff has a sound reason to break it, do NOT raise a finding — recommend an ADR via decision-record and approve the diff.
  • "Could be split into more files" is style, not architecture; route to judge-code-quality.
  • A finding with no file:line citation is a vibe; reject your own finding before issuing it.

Do NOT

  • Do NOT review correctness, security, tests, or style — those are other judges.
  • Do NOT issue reject without naming the ADR or stated shape that would need to change.
  • Do NOT raise findings against the current architecture if the diff did not introduce them; this is a diff-judge, not a codebase-audit.
  • Do NOT merge findings with another judge's output — the user needs to see which lens raised each one.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

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'.

日本語の概要は準備中です。原文の説明を表示しています。

event4u-app/agent-config112026年10月13日 更新

Use when defining or auditing the activation event — aha-moment selection, retention correlation, falsifiable definition. Triggers on 'what is our aha moment', 'redefine activation'.

日本語の概要は準備中です。原文の説明を表示しています。

event4u-app/agent-config112026年10月13日 更新

Use when capturing an architectural decision — file naming, next ADR number, Status / Context / Decision / Consequences, index regen; fires even without saying 'ADR'.

日本語の概要は準備中です。原文の説明を表示しています。

event4u-app/agent-config112026年10月13日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

event4u-app/agent-config112026年10月13日 更新

Use when reading, creating, or updating agent documentation, module docs, roadmaps, or AGENTS.md. Understands the full .augment/, agents/, and copilot-instructions structure.

日本語の概要は準備中です。原文の説明を表示しています。

event4u-app/agent-config112026年10月13日 更新

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.

日本語の概要は準備中です。原文の説明を表示しています。

event4u-app/agent-config112026年10月13日 更新

event4u-app のスキルをすべて見る

このスキルの問題を報告する