一键导入
source-audit
Verify public-web findings with source quality, dates, and second-source checks before turning them into advice or claims.
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
Verify public-web findings with source quality, dates, and second-source checks before turning them into advice or claims.
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
| name | source-audit |
| description | Verify public-web findings with source quality, dates, and second-source checks before turning them into advice or claims. |
| origin | repo-local web research workflow |
Use this skill before giving a final answer based on web research, especially when facts are recent, contested, expensive to act on, or easy to misread.
docs/reference/ai-agent-web-research-stack.mdcompliance-and-rate-limit for repeated or large-scope collectionUse a deterministic browser workflow only when direct fetch or extraction is insufficient for a public-web task.
Run the smallest correct verification lane and report it precisely.
Keep public-web research compliant, bounded, and efficient through rule checks, caching, and backoff instead of evasive scraping.
Optimize a parity-proven ome-zarr native C++ surface for measurable speedups by improving data layout, copies, cache behavior, and boundary design without changing behavior.
Benchmark converted code against the frozen upstream implementation before making performance claims.
Port one upstream ome-zarr-py surface to standalone native C++ without touching the frozen snapshot.