Token导航 LogoToken导航

Agent Skill · 研究检索

corporate-credit-memo(公司贷项凭证)

corporate-credit-memo 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

corporate-credit-memo 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,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 13,749。

总安装 9,126周安装 388GitHub Stars 1下载 3,197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
MIT-0
版本
1.0.0

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:corporate-credit-memo(公司贷项凭证)
来源仓库:https://github.com/henrijoe20/corporate-credit-memo
安装命令:
openclaw skills install corporate-credit-memo
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install corporate-credit-memo

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。

根据上传的年度报告、财务报表或用户项目生成英文的机构级企业信用申请备忘录(信用备忘录)

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 OpenClaw;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 openclaw skills install corporate-credit-memo;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

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

corporate-credit-memo 怎么安装?

在终端执行 openclaw skills install corporate-credit-memo。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

corporate-credit-memo 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。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。

corporate-credit-memo 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

corporate-credit-memo 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

corporate-credit-memo 用的人多吗?

公开数据是累计安装 9,126 次,近一周安装 388 次,下载 3,197 次,GitHub 1 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。

corporate-credit-memo 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

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 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 OpenClaw,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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 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
corporate-credit-memo

公司贷项凭证 · 本页

9,1261接触敏感数据MIT-0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

name
corporate-credit-memo
version
1.0.0
description
>
homepage
https://github.com/henrijoe20/corporate-credit-memo
tags
metadata
clawdbot
emoji
🏦
requires
env
[]
files
["references/*", "assets/*"]

Corporate Credit Memo Skill

Produces full institutional-grade Credit Application Memoranda (20–30+ pages) from uploaded financial documents and user-provided deal parameters. Output follows the 8-section structure used by major international banks, with all financial ratios calculated and flagged where data is insufficient.


Step 1 — Intake & Clarification

When triggered, immediately check what the user has provided. Do NOT ask multiple questions at once. Follow this sequence:

1a. Check for uploaded files

If annual reports / financial statements are attached → proceed to Step 2. If nothing is attached, ask:

"Please upload the company's annual reports (last 2–3 years, PDF or Word). If you don't have them, paste the key financials and I'll work with those."

1b. Collect deal parameters (ask once, in a single message)

Once files are confirmed, ask the user to confirm or provide:

1. Borrower legal name
2. Facility type & amount (e.g. GBP 50m term loan / USD 120m revolving credit)
3. Tenor (e.g. 3 years, 5 years)
4. Purpose of loan (working capital / capex / refinancing / acquisition)
5. Security / guarantee structure (if known)
6. Repayment profile (bullet / amortising / quarterly)
7. Pricing (if known — e.g. SONIA + 250bps)
8. Lending bank / branch name
9. Any internal policy or industry classification to reference?
   (If unsure, leave blank — I will note it as [TO BE CONFIRMED])

Tell the user:

"Items marked [TO BE CONFIRMED] will be flagged in the report for your team to complete — including RAROC, internal limits, and any policy-specific thresholds."

Step 2 — Document Extraction

Read all uploaded files carefully. Extract and organise:

From financial statements (P&L, Balance Sheet, Cash Flow):

  • 3 years of annual data + latest interim period if available
  • All line items needed for ratio calculation (see references/financial-ratios.md)
  • Auditor name and opinion type (unqualified / qualified / emphasis of matter)
  • Reporting currency and any FX translation notes

From the annual report narrative:

  • Business description, segment breakdown, revenue mix
  • Key customers and suppliers (concentration risk)
  • Management team and ownership structure
  • Geographic footprint
  • Material litigation, contingent liabilities, off-balance-sheet items
  • ESG disclosures if present

Flag clearly any data that is:

  • Missing → label [DATA NOT AVAILABLE — please provide]
  • Restated vs prior year → note the restatement
  • Unaudited → label [UNAUDITED]

Step 3 — Research (Web Search)

Use web search to supplement document data for:

  • Industry overview: market size, growth rate, cycle positioning
  • Regulatory / policy environment relevant to the borrower's sector
  • Competitive landscape: 2–3 named peers with approximate market share
  • Recent news on the company (last 12 months): M&A, rating actions, management changes
  • Macroeconomic context relevant to the jurisdiction and sector

Do NOT fabricate specific figures. If web search returns insufficient data, note:

"[Industry data limited — recommend analyst review / Bloomberg supplement]"

Step 4 — Calculate Financial Ratios

Read references/financial-ratios.md for all formulas and flag logic.

Calculate every ratio for each available year. Apply the following flag rules:

  • ✅ Calculated successfully → show figure
  • ⚠️ Calculated but at borderline threshold → show figure + note
  • 🔲 Data insufficient → show [N/A — data required]
  • 📋 Requires internal input → show [TO BE CONFIRMED — internal policy]

RAROC and internal capital allocation are always [TO BE CONFIRMED]. DSCR denominator must match the proposed repayment schedule — confirm with user if unclear.


Step 5 — Draft the Credit Memo

Read references/credit-memo-structure.md for the full 8-section structure and content requirements for each section.

Drafting principles:

  • Write in formal institutional English — consistent with major UK/international bank standards
  • Tone: analytical, direct, no marketing language
  • Every material statement should be traceable to either the uploaded documents or web search
  • Clearly distinguish facts from analytical judgements
  • Use tables for all financial data — never prose for numbers
  • Section headers must match the structure in references/credit-memo-structure.md exactly
  • Flag all [TO BE CONFIRMED] items inline — do not omit them or leave blank
  • Do not invent internal policy figures (hurdle rates, limits, RWA) — always flag these

Risk section (Section 6):

Read references/risk-framework.md before drafting. Assign a risk rating (Low / Medium / High) for each risk category with a one-line rationale. This section reflects the analytical approach expected of a senior risk function, consistent with PRA supervisory expectations for credit risk governance.

Disclaimer:

Append the standard disclaimer from assets/disclaimer.md at the end of every report.


Step 6 — Output as Word Document (.docx)

Generate the final report as a formatted .docx file using the docx skill conventions:

  • Font: Arial throughout
  • Colour scheme: dark navy headers (#1F4E79), mid-blue subheadings (#2E75B6)
  • All financial tables: dark navy header row, alternating white/light-blue rows
  • Info tables (deal terms, company details): two-column label/value format
  • Risk rating boxes: colour-coded text (green=Low, amber=Medium, red=High)
  • Page header: "Credit Application Memorandum | Confidential — Internal Use Only"
  • Page footer: document date + page number
  • Cover page: borrower name, facility type, amount, date, classification label

Present the .docx file to the user when complete. Also offer a brief verbal summary of the key credit highlights and top 3 risks.


Quality Checklist (run before presenting output)

Before finalising, verify:

  • [ ] All 3 years of financials extracted and populated in tables
  • [ ] Every ratio in references/financial-ratios.md either calculated or flagged
  • [ ] No internal policy figures invented (RAROC, RWA, limits)
  • [ ] Risk section has a rating for each of the 7 categories
  • [ ] All [TO BE CONFIRMED] items visible and not hidden
  • [ ] Disclaimer appended
  • [ ] Document is .docx format, not markdown

Handling Edge Cases

Listed company: Extract financials from uploaded annual report. Use web search for stock performance context and peer comparison. Note exchange and ticker.

Unlisted / private company: Flag absence of public ratings. Rely on audited accounts. Note that valuation of pledged equity (if any) requires independent appraisal.

Holding company borrower / SPV: Distinguish between holdco and opco financials. Analyse guarantor separately. Note structural subordination risk.

Insufficient financials (only 1 year available): Complete what is possible. Note that trend analysis is limited and recommend additional data before credit approval.

Chinese-language source documents: Extract data from tables regardless of language. For narrative sections, translate key disclosures as needed. Note source language.

M&A / acquisition finance: Produce pro-forma combined financials. Separate target and acquirer analysis. Reference references/credit-memo-structure.md Section 1 addendum for transaction analysis structure.

平台分布

OpenClaw

96.06%
按下载量换算3,071

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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