deal-screening
Skill2 starsChanged 3 months agoApache-2.0View on GitHub
项目初步筛选——提取 BP 核心事实、对照投资标准(4+6 地图/阶段/地域/弹药)、三选项分类+死亡清单快过、输出一页纸筛选单。MUST BE USED 当收到新 BP/收项目资料/判断是否值得深调时。
3 other projects use a version of this.
Adopted by
Most recently taken up by
- edu6565/claude-skillstheir own version, first seen Oct 11, 2026
- anthropics/financial-services-pluginstheir own version, first seen Oct 8, 2026
- anthropics/financial-servicestheir own version, first seen Jul 22, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- anthropics/financial-services★ 41ksame name
- anthropics/financial-services-plugins★ 41ksame name
- edu6565/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- audit-xlsSkill
- damodaran-valuationSkill
- dd-checklistSkill
- growth-tech-stocksSkill
- hardtech-waveSkill
- ic-memoSkill
- my-pe-viewSkill
- next-windfallSkill
- patent-quality-assessmentSkill
- pe-dd-handbookSkill
- physics-feasibility-checkSkill
- poor-charlie-almanackSkill
- portfolio-monitoringSkill
- serenity-investingSkill
- shou-zhengSkill
- tech-transferSkill
- unit-economicsSkill
- value-creation-planSkill
- value-investing-3Skill
- venture-dealsSkill
- verifier-methodSkill
The file
Files
项目初筛(Deal Screening)
借鉴:Anthropic financial-services private-equity/deal-screening。适配中国早中期硬科技。 上游:poor-charlie-almanack(三选项分类/死亡清单)、sector-scanner(赛道评估结论)。 衔接:通过者进入 tech-dd 深度尽调;输出并入 pipeline/templates/02-初步评估.md。 边界:本技能是项目级初筛(单份 BP/项目卡);赛道级评估(行业/方向选择)归 sector-scanner——赛道先过三选项,项目再过三选项,两层不混。
核心流程
① 提取项目事实(60 秒初筛)
从 BP/项目卡提取:
- 公司:名称/地点/赛道/一句话业务描述
- 财务:收入(如已有)、毛利、增速、融资史与估值
- 团队:创始人背景(产业 vs 学术)、全职状态
- 关键技术:路线/代际/专利数/TRL 标定(如有)
- 融资需求:拟融金额、出让比例、估值口径
- 明显红旗:技术存疑/团队短板/合规风险/模式不清
② 对照投资标准(先问后筛)
| 标准 | 目标 | 实际 | 通过/不通过 |
| 赛道 | 4+6 候选地图 | ||
| 阶段 | 天使-A轮(早中期) | ||
| 地域 | 中国(重点四川/成都) | ||
| 技术范式 | 五大范式定位 | ||
| 弹药 | 拟投金额 vs 弹药纪律 | ||
| 认知可及性 | 能力圈边界内? |
③ 三选项分类(铁律 1)
- 归入:可以 / 不行 / 太难
- "太难":无论多热门不投(禁 FOMO 改判)
- "可以"必须能说出能力圈边界(说不出 = 实际"太难")
④ 死亡清单快过(铁律 2)
六大死法逐条 30 秒过:
- 现金流断裂(烧钱率 vs 融资节奏)→ 伪需求(真实付费验证?)→ 团队内讧(合伙人结构?)→ 技术被颠覆(替代路线?)→ 合规事故(资质/出口管制?)→ 道德风险(数据造假可能?)
- 任一死法无法排除 = 不出手;标记"待验证"进入深调
⑤ 快评三件套
- 结论:通过 / 条件深调 / 硬过(hard pass)
- Bull case(2-3 条):为什么可能成
- Bear case(2-3 条):关键风险与担忧
- 首电问题(3-5 个):首次接触要问清的关键点
⑥ 输出
一页纸筛选单(含上述全部)→ 与 pipeline/templates/02-初步评估.md 衔接 → 进入项目池/发给 tech-dd 深调
双池分流(2026-09-09——三选项后必做)
三选项判定后,按阶段分流:
| 阶段 | 归入 | 处置 |
| 种子-PreA(早中期) | 主攻池 | 走完整深调(首电→验证→投决) |
| B 轮后-PreIPO | 配置池 | 小额配置评估(算清结构成本,分账管理) |
| 基金份额/间接投资 | 配置池 | 按 venture-deals 审结构(嵌套/费率/分配) |
| 材料过期/缺失 | 待材料 | 先补材料再评估 |
纪律:不因"标的顶级/国资背景"把成长期项目塞进主攻池——弹药纪律(铁律5)优先。
重要纪律
- 速度优先:筛选以分钟计,不以小时计(场景矩阵场景 1:收 BP 60 秒初筛)
- 红旗直说,不埋雷;财务数据不一致/不完整要显式标注
- 第一次筛前确认基金标准;确认后存入记忆,后续直接复用
- BP 数字默认打五折(铁律 3);欢迎坏消息
使用提示
- 与 vault 概念页联动:[[概念:能力圈]]
- 项目池持续运转:接触≠出手(铁律 5)
验证纪律(verifier-method,2026-08-20 注入)
- 5 候选维度:三选项分类 / 死亡清单逐条 / 订单真实性——每个候选带概率分布(口头数据=平缓分布)
- 反向风险模式:死亡清单六死法先排最坏(先问最坏死法能否承受,再谈亮点)
- 数据造假候选必含:财务/订单/客户数字可能虚报什么(BP 数字打五折的结构化版本)
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
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.

