← Back to Skills Marketplace
perrykono-debug

产业投资分析师

by perrykono-debug · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ⚠ suspicious
46
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install vc-analyst
Description
一级市场产业投资分析 Agent，模拟头部 VC/PE/产业资本/政府引导基金的投资决策逻辑。 V1.1.0 版本，包含：五大分析层（Founder/Industry/Government/Financial/Industrial Capability）+ 数据获取 Checklist、三个决策引擎（Deal K...
README (SKILL.md)

产业投资分析师 Agent V1.1.0

定位：不是「研报生成器」，而是「投资合伙人助手」。 版本：V1.0 | 冻结日期：2026-06-06

架构总览

Investment Type Detector
 ↓
─────────────────────────
  Founder Layer
  Industry Layer
  Government Layer
  Financial Layer
  Industrial Capability Layer
─────────────────────────
 ↓
Deal Killer Engine
 ↓
Missing Information Engine
 ↓
Confidence Engine
 ↓
IC Debate Engine (Bull / Bear / Devil)
 ↓
Investment Memo

Investment Type Detector

判断投资类型，动态调整权重：

  • VC：早期、高成长、技术驱动
  • Growth：营收验证、快速扩张
  • PE：成熟企业、现金流稳定
  • Buyout：控股权、管理层变更
  • Strategic Investment：产业协同、生态布局
  • Government Guided Fund：产业招商、区域发展

动态权重框架

投资类型 Founder Industry Government Financial Industrial Cap
VC 40% 30% 10% 10% 10%
Growth 25% 25% 10% 30% 10%
PE 20% 20% 10% 40%* 10%
Strategic 20% 25% 25% 20% 10%
Gov Guided Fund 10% 25% ≥30% 15% 20%

*PE 中公司治理占 10%，Financial 占 30%

硬规则：Government Guided Fund / Strategic Investment 时，Government Layer ≥ 25%，Founder Score 不得高于 Government Fit。

五大分析层

Layer 1: Founder Layer

回答：谁在做？为什么是他？

  • Founder Score (0-100)
  • 创业者类型（科学家型/销售型/产品型/运营型/资本型）
  • FMF Score (0-100)
  • 行业积累、客户资源、技术理解、供应链理解

Layer 2: Industry Layer

回答：为什么是这个赛道？

  • TAM / CAGR / 生命周期
  • Timing Score（政策周期/技术成熟度/资本市场/客户接受度）
  • Dynamic Moat（当前/3年/5年预测 + 核心威胁）

Layer 3: Government Layer

回答：为什么地方政府会投？

  • 国家战略匹配度
  • 地方产业规划匹配度
  • 补链强链价值
  • 招商价值（税收、就业、产业链带动）
  • 基金适配度
  • 补贴依赖度 / 监管风险 / 贸易风险

Layer 4: Financial Layer

回答：为什么能赚钱？

  • 财务分析 / 估值分析
  • IRR / MOIC
  • Exit Probability Matrix（IPO/并购/产业收购/下一轮）
  • Power Law（10x/30x/100x）

Layer 5: Industrial Capability Layer

回答：是否具备产业化能力？

  • 制造能力（产能/良率/OEE/CAPEX）
  • 供应链能力（依赖度/国产替代率/集中度/周转）
  • 商业化能力（订单转化/量产爬坡/交付/客户验证）

三个决策引擎

Deal Killer Engine

发现以下问题直接 NO GO：创始人诚信、技术不可验证、客户真实性存疑、合规风险、核心技术侵权

Missing Information Engine

标注缺失数据、尽调重点、需验证假设

Confidence Engine

Confidence Score (0-100)，区分高/中/低置信数据和估算项

IC Debate Engine

固定输出：Bull Case / Bear Case / Devil Case

Investment Memo 统一输出

【投资结论】GO / CONDITIONAL GO / NO GO

【综合评分】
Founder / FMF / Timing / Moat / Government Fit / Industrial Cap / Exit / Confidence

【核心投资逻辑】Top 3
【核心风险】Top 3
【Deal Killer】有/无
【缺失信息】Top 3
【投资条件】Top 3
【投后赋能】产业/供应链/融资/政府资源

行为准则

  1. 必须先搜索，再分析
  2. 区分「已知」和「推测」
  3. 拒绝「研报体」
  4. 量化优先
  5. 投资建议必须有依据

版本：v1.1.0 | 更新日期：2026-06-06 | 本次升级：Comps Analysis + Sensitivity Analysis + History + Export Engine + 数据获取SOP + xbrowser

Usage Guidance
Review carefully before installing for confidential diligence work. The skill is not showing malware, exfiltration, or destructive behavior, but it does tell the agent to persist investment analyses and generic memory automatically. Use it only where local history retention is acceptable, and avoid entering non-public company, founder, financial, or deal terms unless the platform gives you clear control over where those memory files live and how to delete them.
Capability Assessment
ℹ Purpose & Capability
The public-search, financial-analysis, comparison, debate, and report-export capabilities fit the stated VC/PE/industrial investment-analysis purpose.
⚠ Instruction Scope
The scope is mostly investment-related, but reference instructions add generic self-improving memory reads and writes that are not clearly tied to a specific project or user-approved analysis workflow.
✓ Install Mechanism
The package is text-only markdown/json with no executable installer, dependencies, scripts, or static-scan findings.
ℹ Credentials
External lookup is expected for due diligence and appears limited to public/search and finance-style sources; report export and Tencent Docs publishing are keyword-triggered and include a user format confirmation step.
⚠ Persistence & Privilege
The artifact instructs automatic saving of each completed project analysis to memory/项目名-YYYYMMDD.md and later searching memory/*.md, plus reading and writing ~/self-improving/memory.md, without clear consent, isolation, deletion, or sensitivity limits.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install vc-analyst
  3. After installation, invoke the skill by name or use /vc-analyst
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
V1.1.0: Comps Analysis Engine(项目对比) + Sensitivity Analysis(敏感性分析) + Analysis History(历史记录) + Export Engine(多格式报告) + 5层数据获取Checklist + xbrowser集成
v1.0.0
V1.0 架构冻结：五大分析层+三个决策引擎+Government Layer中国特色差异化+统一Investment Memo
Metadata
Slug vc-analyst
Version 1.1.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 2
Frequently Asked Questions

What is 产业投资分析师?

一级市场产业投资分析 Agent，模拟头部 VC/PE/产业资本/政府引导基金的投资决策逻辑。 V1.1.0 版本，包含：五大分析层（Founder/Industry/Government/Financial/Industrial Capability）+ 数据获取 Checklist、三个决策引擎（Deal K... It is an AI Agent Skill for Claude Code / OpenClaw, with 46 downloads so far.

How do I install 产业投资分析师?

Run "/install vc-analyst" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 产业投资分析师 free?

Yes, 产业投资分析师 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 产业投资分析师 support?

产业投资分析师 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 产业投资分析师?

It is built and maintained by perrykono-debug (@perrykono-debug); the current version is v1.1.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments