ワンクリックで
brat-review
Review phase skill. Input: completed implementation artifact. Output: merge decision or human approval request.
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
Review phase skill. Input: completed implementation artifact. Output: merge decision or human approval request.
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。
Architecture phase skill. Input: product requirements + current arch KB. Output: architecture design as zkb notes.
Auto-bootstrap skill. Input: codebase scan. Output: product/architecture notes + consistency score + inconsistencies.
Implementation phase skill. Input: architecture design. Output: working code with tests, written in swimlanes.
Memory phase skill. Input: session findings. Output: structured memory notes in KB.
Product phase skill. Input: user intent + current product KB. Output: structured product requirements as zkb notes.
SOC 職業分類に基づく
| name | brat-review |
| description | Review phase skill. Input: completed implementation artifact. Output: merge decision or human approval request. |
Review completed implementation against architecture design and product requirements. Request human approval before merge.
{
"implementation": {
"component": "string",
"files_changed": ["string"],
"diff_summary": "string",
"tests": {
"unit": {"passing": "number", "failing": "number"},
"integration": {"passing": "number", "failing": "number"}
}
},
"architecture": {
"component": "string",
"expected_interfaces": ["string"],
"expected_file_paths": ["string"]
},
"product": {
"requirement_title": "string",
"acceptance_criteria": ["string"]
},
"policy": {
"require_human_approval": "boolean",
"required_checks": ["string"]
}
}
{
"decision": "approve|request_changes|reject|escalate",
"assessment": {
"architecture_compliance": "compliant|partial|non_compliant",
"test_coverage": "adequate|partial|inadequate",
"acceptance_criteria_met": "all|partial|none"
},
"approval_request": {
"rationale": "string (why this needs human eyes)",
"artifact_summary": "string (what changed)",
"risk_level": "low|medium|high",
"suggested_reviewers": ["string"]
},
"required_changes": ["string (if decision=request_changes)"],
"reason": "string"
}
require_human_approval is true, ALWAYS request approval before merge