一键导入
findings-contract
Defines the compact JSONL finding schema used by all PR specialist agents and the review auditor.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Defines the compact JSONL finding schema used by all PR specialist agents and the review auditor.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Resolve GitHub PR review comments safely, read unresolved comments, validate each issue, make minimal fixes, test, commit, and resolve.
Use zero-install context minimization first, with optional local optimization tooling when available.
Accessibility review for semantic HTML, ARIA, keyboard support, focus, screen readers, contrast, and WCAG-oriented issues.
API and contract review for OpenAPI/AsyncAPI/protobuf changes, backwards compatibility, schemas, status codes, and examples.
Architecture review for SOLID, layering, boundaries, coupling, cohesion, extensibility, and maintainability.
Backend review for handlers, services, validation, errors, transactions, dependency boundaries, and service contracts.
| name | findings-contract |
| description | Defines the compact JSONL finding schema used by all PR specialist agents and the review auditor. |
| license | MIT |
All reviewer agents must return compact JSONL findings. One finding per line.
{
"id": "SEC-001",
"agent": "security-reviewer",
"severity": "blocking",
"category": "security",
"file": "src/auth/token.ts",
"line": 42,
"title": "Access token is logged",
"evidence": "The changed code writes accessToken to structured logs.",
"recommendation": "Remove the token from logs or mask it before logging.",
"confidence": "high"
}
| Field | Values |
|---|---|
id | Stable per agent run, prefix by category, e.g. SEC-001 |
agent | Agent name |
severity | blocking, non_blocking, note |
category | Review category |
file | Relative path, or empty string for repo-level finding |
line | Integer line number or null |
title | Short finding title |
evidence | Concrete evidence from diff/file/tool output |
recommendation | Minimal actionable recommendation |
confidence | high, medium, low |