Cn Ib Memo Builder logo

Cn Ib Memo Builder

Community
QiushenZou
cn-ib-memo-builder

Turn source materials into concise, source-backed Chinese investment-banking memos with clear facts, analysis, decisions, risks, and actions. Use for project updates, diligence findings, issue memos, transaction-path analyses, internal briefing notes, meeting follow-ups, 上会材料摘要、事项备忘录、项目进展、风险事项、核查结论、交易方案 or management-ready summaries in Markdown or Word. Preserve the requested template and distinguish evidence from inference; do not use for investment recommendations.

Overview

PublisherQiushenZou
Repositorycn-investment-banking-skills
Skill namecn-ib-memo-builder
Stars
97
Forks
0
Bundled files
6
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by QiushenZou on GitHub. Read the source before you install it.

Installation

Install the Cn Ib Memo Builder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/QiushenZou/cn-investment-banking-skills/tree/main/skills/cn-ib-memo-builder
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/QiushenZou/cn-investment-banking-skills.git /tmp/cn-investment-banking-skills
mkdir -p .claude/skills
cp -r /tmp/cn-investment-banking-skills/skills/cn-ib-memo-builder .claude/skills/cn-ib-memo-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cn Ib Memo Builder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cn Ib Memo Builder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cn Ib Memo Builder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

CN IB Memo Builder

Produce a memo that lets a senior banker understand the decision, evidence, risk, and next action quickly.

Principles

  1. Start with the decision or conclusion, not a chronology of work performed.
  2. Distinguish confirmed fact, source statement, analysis, assumption, and open question.
  3. Support material facts with stable source identifiers and precise locators.
  4. Keep unresolved issues visible with owner, deadline, dependency, and consequence.
  5. Preserve the user's template, defined terms, and requested sections.
  6. Never manufacture a conclusion when the evidence is incomplete.

Workflow

1. Define the memo's job

Read references/memo-types.md. Confirm:

  • reader and decision required;
  • memo type and required length;
  • reporting cut-off and transaction stage;
  • approved sources and confidentiality level;
  • required template, headings, and sign-offs.

If no template is supplied, start from assets/memo-template.md and remove irrelevant sections rather than filling them with generic prose.

2. Build an evidence ledger

Before drafting, assign each material source a stable ID such as [S1]. Record:

text
source_id, title, date, file_or_url, page_or_cell, owner, status

Extract facts with original wording, period, unit, scope, and caveat. Use cn-ib-source-verifier for calculation lineage or cn-ib-cross-document-check when sources disagree.

3. Create the issue structure

For each material issue, state:

  • Conclusion: what the evidence currently supports;
  • Facts: source-backed observations only;
  • Analysis: why the facts matter to the transaction;
  • Gap or risk: what remains uncertain and the consequence;
  • Action: next step, owner, deadline, and closure evidence.

Do not hide a qualification in a footnote when it changes the conclusion.

4. Draft conclusion-first

Read references/drafting-style.md. Write the executive summary after the issue analysis, then move it to the front. Use tables for decisions, open items, and comparisons; use prose for reasoning that needs context.

Keep source tags close to supported statements:

text
公司截至2026年6月30日的在手订单为人民币10亿元。[S2]

Label management representations, estimates, and adviser analyses explicitly.

5. Validate the draft

Read references/source-and-review.md, then scan a Markdown draft:

bash
python3 scripts/check_memo_markdown.py memo.md --output memo-issues.csv

The script detects unresolved placeholders, missing core headings, empty sections, uncited quantitative claims, unsupported superlatives, duplicate punctuation, and broken source tags. Adjust required headings with repeated --required-heading options when the user's template differs.

6. Reviewer-ready close

Verify:

  • the executive summary agrees with the detailed sections;
  • dates, units, names, and transaction terms are consistent;
  • every material conclusion states its evidence and limitations;
  • every open item has an owner and next step;
  • source definitions resolve all citations;
  • the final Word/PDF rendering has been visually inspected if delivered in that format.

When revising an existing Word memo, preserve the original and use native Word tracked changes by default. Keep edits granular, retain existing revisions and comments unless instructed otherwise, and do not simulate redlines with color or strikethrough. Use a transparent revision author such as Codex when none is specified. Verify the revision markup and render all changed pages; provide a clean accepted copy only when explicitly requested.

Output contract

Deliver:

  1. memo with conclusion-first executive summary;
  2. issue-by-issue fact, analysis, risk, and action;
  3. decision and open-item table;
  4. source register with exact locators;
  5. explicit assumptions, limitations, and unresolved disagreements.

Do not turn a management statement or professional inference into an unqualified fact.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cn Ib Memo Builder AI skill do?

Turn source materials into concise, source-backed Chinese investment-banking memos with clear facts, analysis, decisions, risks, and actions. Use for project updates, diligence findings, issue memos, transaction-path analyses, internal briefing notes, meeting follow-ups, 上会材料摘要、事项备忘录、项目进展、风险事项、核查结论、交易方案 or management-ready summaries in Markdown or Word. Preserve the requested template and distinguish evidence from inference; do not use for investment recommendations.

Why use Cn Ib Memo Builder on TypingMind?

Because you install it once and use it with any model. Cn Ib Memo Builder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cn Ib Memo Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/QiushenZou/cn-investment-banking-skills/tree/main/skills/cn-ib-memo-builder. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cn Ib Memo Builder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cn Ib Memo Builder?

As many as you like. As long as a model supports skills, you can use Cn Ib Memo Builder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cn Ib Memo Builder AI skill free?

Yes. It is published on GitHub by QiushenZou under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇