agentleFS
sakuruamayday-opssakuruamayday-ops/enterprise-project-application-assistant/skills/peer-benchmarking/SKILL.md

peer-benchmarking

Skill2 starsChanged 2 months agoApache-2.0View on GitHub

从政府公示名单和公开资料中建立同项目、同地区、同产品的可比企业对标。用户说“做某产品的专精特新企业帮我查”“查专精特新同行”“查小巨人同行”等口语时必须使用。先取得官方名单,再用合法企业数据能力核验主体和产品;不由入选结果推定未公开评分或全部条件。只核验政策效力时改用 policy-retrieval。

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

同行对标

用户只要求找几家同行、核对某家是否可比或查询获评企业时,只返回命中对象、必要可比依据和来源,不自动扩展为完整评分表、竞争分析或企业全景报告。完整对标结构只在用户明确要求同行对标分析或报告时执行。

职责

从公开名单和公开材料中寻找可比企业,为申报定位提供事实参照,不推断未公开的申请书内容或专家评分。

若只核验旧通知、政策版本、效力或完整文件链,本技能不适用,必须以policy-retrieval为主技能。

流程

  1. 明确目标项目、年度、地区、行业、产品和对标目的。
  2. 先从政府部门网站、公示附件或用户提供的官方原文取得认定和复核名单,记录项目、年度、地区、批次、分页状态和文件来源。
  3. 再按 企业数据源有限降级协议 使用宿主已合法配置的企业数据能力核验主体、曾用名、登记地区和状态;缺少企业数据能力时只使用用户材料和官方公开来源。第三方资料只能作为主体线索或官方来源定位,不能替代官方认定事实。
  4. 锚定企业完整名称,避免集团、子公司和同名主体混淆。
  5. 按同项目、同政策版本、同地区、同细分行业、同类产品和相近规模评估可比性。
  6. 分开记录公开事实、可计算指标、合理推断和未知项。
  7. 入选事实只证明企业在对应年度获得该结果,不自动证明每个评分项均满足或高分。
  8. 跨年度比较前核验管理办法、申报范围和评价指标;口径不一致时只作历史背景或趋势参考。

输出

输出来源清单、可比性评分、事实对比表、政策口径差异和不可比较项。详细规则见 references/peer-comparability-rules.md。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.