ワンクリックで
review-methodology
This skill should be used when performing a code review to apply the standard 6-step review process.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
This skill should be used when performing a code review to apply the standard 6-step review process.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Canonical algorithm for consuming DECISIONS_CONTEXT index — scan index, identify relevant entries, Read full bodies on demand, cite verbatim IDs inline.
This skill should be used when evaluating implementation quality before submission, checking correctness, security, and simplicity.
This skill should be used when the user asks to "add accessibility", "check ARIA", "handle keyboard navigation", "add focus management", or creates UI components, forms, or interactive elements. Provides WCAG 2.2 AA patterns for keyboard navigation, ARIA roles and states, focus management, color contrast, and screen reader support.
Consumption algorithm for FEATURE_KNOWLEDGE variable — pre-computed feature context
This skill should be used when reviewing code for SOLID violations, tight coupling, or layering issues.
This skill should be used when the user asks to "validate input", "parse request data", "handle form data", "add Zod schema", "sanitize user input", or creates API endpoints and system boundaries. Provides parse-don't-validate patterns with schema validation for type-safe boundary enforcement and hostile input defense.
| name | review-methodology |
| description | This skill should be used when performing a code review to apply the standard 6-step review process. |
| user-invocable | false |
| allowed-tools | Read, Grep, Glob, Bash |
The canonical review process for all Devflow review agents. Ensures consistent, fair, and actionable code reviews.
NEVER BLOCK FOR PRE-EXISTING ISSUES
Only issues in YOUR CHANGES can block a PR. Pre-existing issues are informational only. If you didn't add it, you don't own it. Fair reviews focus on the diff, not the codebase.
Get the diff to understand what changed. Identify base branch and extract changed files/lines.
| Category | Scope | Priority | Action |
|---|---|---|---|
| 1. Issues in Your Changes | Lines ADDED/MODIFIED in this branch | BLOCKING | Must fix before merge |
| 2. Issues in Code You Touched | Same file/function, but not your line | HIGH | Should fix while here |
| 3. Pre-existing Issues | Lines you didn't touch at all | INFORMATIONAL | Fix in separate PR |
Note: All categories and severities — including suggestions — are reported for resolution. Categories affect PR merge-blocking, not whether issues get resolved. The resolve workflow evaluates everything.
Apply your specialized lens (security, performance, tests, etc.) to each category:
| Severity | Description | Examples |
|---|---|---|
| CRITICAL | Immediate risk, must fix | Security vulnerabilities, data loss risks, breaking API changes |
| HIGH | Significant risk, should fix | Performance degradation, missing error handling |
| MEDIUM | Moderate risk, consider fixing | Style inconsistencies, missing documentation |
| LOW | Minor improvements | Naming suggestions, optional optimizations |
For each issue, provide:
Create report with all three issue sections, summary counts, and merge recommendation.
| Principle | Description |
|---|---|
| Diff-Aware | Focus on actual changes, not pre-existing issues |
| Fair | Don't block PRs for legacy problems |
| Specific | Exact file:line, not vague complaints |
| Actionable | Show the fix, not just the problem |
| Categorized | Clear distinction between blocking and informational |
| Prioritized | Critical > High > Medium > Low |
| Documented | Reports saved for future reference |
For detailed implementation:
| Reference | Content |
|---|---|
references/report-template.md | Full report template with all sections |
references/patterns.md | Diff commands (lines 29–113) and PR comment API integration (lines 117–181) |
references/violations.md | Review process anti-patterns and violations |
This methodology is used by the Reviewer agent with different focus areas:
| Focus | Pattern Skill |
|---|---|
security | devflow:security |
performance | devflow:performance |
architecture | devflow:architecture |
testing | devflow:testing |
consistency | devflow:consistency |
complexity | devflow:complexity |
regression | devflow:regression |
dependencies | devflow:dependencies |
documentation | devflow:documentation |
typescript | devflow:typescript |
database | devflow:database |
The Reviewer agent loads all pattern skills and applies the relevant one based on the focus area specified in its invocation prompt.