Token导航 LogoToken导航

Agent Skill · 研究检索

data-room(资料室)

用于辅助数据整理、表格处理、CSV/Excel 分析、指标计算和图表准备。它适合让 Agent 清洗字段、汇总数据、发现异常、生成统计口径或把分析结果转成可读说明。使用时需要确认数据来源、字段含义和时间范围,避免把样本数据当全量事实;涉及敏感数据、导出文件或批量写回时,应先确认权限和脱敏边界。

data-room 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 48,042。

总安装 706周安装 30GitHub Stars 115下载 247核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:data-room(资料室)
来源仓库:https://github.com/shawnpang/startup-founder-skills
仓库路径:skills/data-room
安装命令:
npx skills add https://github.com/shawnpang/startup-founder-skills --skill data-room
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/shawnpang/startup-founder-skills --skill data-room

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

专为创业公司融资阶段设计,协助准备投资者尽职调查所需的资料室材料。适用于种子轮到 B 轮融资期间,应对投资机构正式尽调或 term sheet 后的补充审查。自动整合企业基本信息、财务数据、团队结构和法律文件等核心尽调要素。需用户提供当前融资阶段、目标投资方及具体材料类型等上下文信息。

安装依赖 GitHub 仓库结构,通过 npx 命令添加并使用 startup-context 提供基础数据。

来源仓库内路径:skills/data-room

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/shawnpang/startup-founder-skills --skill data-…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

data-room 怎么安装?

在终端执行 npx skills add https://github.com/shawnpang/startup-founder-skills --skill data-room。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

data-room 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

data-room 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

data-room 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

data-room 用的人多吗?

公开数据是累计安装 706 次,近一周安装 30 次,下载 247 次,GitHub 115 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

data-room 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
data-room

资料室 · 本页

706115只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Data Room

When to Use

  • The founder is mid-fundraise and investors are requesting due diligence materials.
  • The founder wants to proactively prepare a data room before starting outreach.
  • The founder received a term sheet and needs to prepare for confirmatory due diligence.

Context Required

From startup-context: stage, legal entity type, founding date, team composition, fundraising history, cap table basics, revenue/metrics, and any existing legal or financial documents.

From the user: current round stage (pre-term sheet vs. post-term sheet), which investor is requesting materials, and any specific document requests received.

Workflow

  1. Read startup context — Pull company details from .agents/startup-context.md to understand stage, entity type, and what documents should already exist.
  2. Assess the DD stage — Determine if this is proactive prep (pre-pitch), initial DD (post-first meeting), or confirmatory DD (post-term sheet). The scope differs significantly.
  3. Generate the checklist — Produce a stage-appropriate checklist using the master framework below. Mark each item as: Exists, Needs Update, Needs Creation, or Not Applicable.
  4. Audit existing materials — Review documents for completeness, staleness (financials older than 1 month), and red flags (missing signatures, inconsistent cap table).
  5. Draft missing items — Provide templates or drafts for documents the founder needs to create (financial summary, KPI dashboard, org chart).
  6. Organize the room — Recommend a folder structure and set access controls for what to share pre- vs. post-term sheet.

Output Format

A structured checklist in markdown, organized by category:

## Data Room Checklist — [Company Name] — [Round]

### Section 1: Corporate Documents
- [x] Certificate of Incorporation — exists, current
- [ ] Board consent for fundraise — needs creation
- [ ] 409A valuation — needs update (last done 14 months ago)

Followed by a recommended folder structure and access-level guidance.

Frameworks & Best Practices

Master Due Diligence Checklist

1. Corporate Documents: Certificate of Incorporation (and amendments), bylaws, board minutes (last 12 months), board consent for fundraise, stockholder agreements, QSBS eligibility docs, state registrations, any pending litigation.

2. Cap Table & Equity: Fully diluted cap table (Carta/Pulley export, not a manual spreadsheet), option plan and grant ledger, SAFEs/convertible notes with terms, pro forma post-round cap table, current 409A valuation (<12 months old), secondary sale history.

3. Financials: P&L, balance sheet, cash flow — actual, last 12 months (monthly). Bank balance and burn rate. 18-36 month projections with stated assumptions. Revenue breakdown by customer/cohort. Unit economics (CAC, LTV, gross margin, payback). AR/AP aging. Outstanding debt.

4. Metrics & KPIs: Monthly KPI dashboard (MRR/ARR, growth, churn, NRR, DAU/MAU). Cohort retention. Sales pipeline (B2B) or funnel conversion (B2C/PLG).

5. Product & Technology: Product roadmap (6-12 months), architecture overview, IP ownership confirmation, patent filings, open source license audit, SOC 2 or security summary.

6. Contracts & Customers: Top 10 customer contracts, customer concentration analysis (<20% per customer is ideal), key vendor/partner agreements, exclusivity or non-compete clauses, churn log.

7. Team & HR: Org chart, founder/key employee bios, employment agreements (confirm IP assignment), contractor agreements, option grant summary, HR disputes, benefits summary.

8. Legal & Compliance: Privacy policy and GDPR/CCPA status, regulatory licenses, trademarks, terms of service, insurance (D&O, E&O, cyber).

Stage-Specific Scoping

  • Pre-seed / Seed: Focus on sections 1, 2, 3 (lighter — 3-6 months of financials), and 7 (team). Product and legal can be thinner. No 409A yet is fine.
  • Series A: All sections expected. Monthly financials for 12+ months. Solid metrics dashboard. Airtight IP assignment. Current 409A required.
  • Post-term sheet DD: Everything above, plus items the lead investor's counsel specifically requests. Corporate governance gets scrutinized here.

Folder Structure

/01-Corporate           /05-Product-and-Technology
/02-Cap-Table-Equity    /06-Contracts-Customers
/03-Financials          /07-Team-HR
/04-Metrics-KPIs        /08-Legal-Compliance
                        /09-Pitch-Materials

Access Control

  • Pre-term sheet: Share pitch materials, metrics dashboard, financial summary, team bios. Hold back contracts, full cap table, legal docs.
  • Post-term sheet: Open the full room. Require an NDA before sharing customer contracts or detailed financials.
  • Watermark PDFs with the investor's name. Use link-level analytics (DocSend) to track what gets opened.

Red Flags That Kill Deals

  • Cap table inconsistencies between the table and signed documents.
  • Missing IP assignment agreements for contractors who built core product.
  • Stale or missing 409A when options have been granted.
  • Financial statements that don't reconcile with bank statements.
  • Non-standard founder vesting without board approval documentation.

Related Skills

  • pitch-deck — the deck is the top-of-funnel; the data room is the supporting evidence
  • investor-research — knowing which investors are in the pipeline helps prioritize what to prepare first

Examples

Example prompt: "We just got a term sheet for our Series A. What do I need in my data room?"

Good output approach: Generate the full 8-section checklist scoped for confirmatory DD. Cross-reference against startup context to pre-fill what likely exists. Flag highest-risk items (cap table accuracy, IP assignments, 409A currency). Recommend a folder structure and 2-4 week timeline.

Example prompt: "I'm about to start fundraising for our seed round. Should I set up a data room now?"

Good output snippet:

Yes — a proactive data room signals operational maturity. For seed, focus on: - Clean cap table export (Carta or Pulley, not a spreadsheet) - Certificate of Incorporation and amendments - 6-month financial summary (revenue, burn, bank balance) - IP assignment agreements for all founders and contractors - Monthly KPI dashboard (MRR, user count, growth rate)

平台分布

Codex

34.93%
按下载量换算86

Claude

30.98%
按下载量换算77

Cursor

16.64%
按下载量换算41

Gemini CLI

8.36%
按下载量换算21

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills