Cn Ib Inquiry Response Review logo

Cn Ib Inquiry Response Review

Community
QiushenZou
cn-ib-inquiry-response-review

Decompose and review Chinese IPO and refinancing regulatory inquiry responses for complete issue coverage, evidence, intermediary procedures, explicit opinions, filing synchronization, and follow-up risk. Use for 上交所、深交所、北交所或证监会问询回复、审核问询、反馈意见、落实函、子问题拆解、逐项回复检查、中介核查程序、明确意见、招股书同步更新 or multi-round response review. This skill reviews answer quality and traceability; it does not replace legal or accounting judgment.

Overview

PublisherQiushenZou
Repositorycn-investment-banking-skills
Skill namecn-ib-inquiry-response-review
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 Inquiry Response Review 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-inquiry-response-review
  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-inquiry-response-review .claude/skills/cn-ib-inquiry-response-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cn Ib Inquiry Response Review 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 Inquiry Response Review 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 Inquiry Response Review 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 Inquiry Response Review

Turn each regulatory question into an auditable set of answer obligations, then test whether the response and intermediary work actually satisfy them.

Principles

  1. Review against the regulator's verbs and subquestions, not only the response headings.
  2. Separate the issuer's explanation from sponsor, counsel, and accountant procedures and opinions.
  3. A conclusion without evidence is incomplete; a procedure without procedure evidence is not demonstrated.
  4. Track whether material response content is synchronized into the prospectus or other filing.
  5. Compare rounds so that a new explanation does not silently contradict an earlier response.
  6. Mark judgment calls and likely follow-up questions explicitly.

Workflow

1. Establish scope

Confirm the inquiry round, regulator, board, filing version, response cut-off, responsible intermediaries, and documents in scope. Preserve the original question numbering and wording.

2. Decompose every question

Read references/question-decomposition.md. Split the question by:

  • each operative verb such as 说明, 披露, 量化分析, 核查, or 发表明确意见;
  • each period, entity, product, transaction, and exception;
  • each addressed party;
  • each requested comparison, explanation, evidence item, and filing update.

Use one row per atomic obligation and addressee in assets/inquiry-review-template.csv. Do not combine issuer disclosure and intermediary opinion in one untestable row.

3. Test the issuer response

For each issuer item, determine whether it is answered, partial, unanswered, or genuinely not_applicable. Check:

  • direct answer to the requested point;
  • relevant facts, periods, units, definitions, and denominators;
  • quantitative support where the question requests it;
  • explanation of exceptions and adverse evidence;
  • exact source or filing locator;
  • consistency with prior rounds and other filing documents.

Read references/response-quality.md before classifying completeness.

4. Test intermediary work

For sponsor, counsel, or accountant rows, require:

  • procedures responsive to the specific risk;
  • procedure evidence, sample scope, period, counterparties, or records reviewed;
  • treatment of exceptions and limitations;
  • an explicit opinion where requested;
  • a logical connection between procedures, evidence, and opinion.

Do not accept 已核查相关资料 as a sufficient procedure description.

5. Test filing synchronization

When the response adds or changes material information, record whether the prospectus or other filing must be updated and the exact updated locator. Use cn-ib-cross-document-check for conflicting figures and cn-ib-filing-refresh-control for a broader refresh.

6. Validate the review matrix

Run:

bash
python3 scripts/review_inquiry_matrix.py inquiry-review.csv --output inquiry-issues.csv

The script detects structural and closure defects. It cannot decide whether prose is substantively persuasive; review that manually using references/follow-up-risk.md.

7. Produce the reviewer view

Group findings into:

  • unanswered or partially answered obligations;
  • missing evidence and weak quantitative support;
  • insufficient intermediary procedures or missing opinions;
  • prospectus synchronization gaps;
  • inconsistencies with prior rounds;
  • likely follow-up questions and recommended remediation.

8. Apply accepted response edits

If the user asks to revise an existing Word response:

  • keep the original file unchanged;
  • use native Word tracked changes by default for every insertion and deletion;
  • edit only the accepted issue rows and keep revisions as local as possible;
  • preserve existing revisions and comments unless specifically asked to resolve them;
  • do not replace entire paragraphs when a sentence-level amendment is sufficient;
  • do not fake revisions with colored text, highlighting, or manual strikethrough;
  • use a transparent revision author such as Codex when none is specified;
  • verify the revision markup structurally, re-render every changed page, and rerun the obligation review.

Return a clean accepted copy only if the user requests it separately.

Output contract

Deliver:

  1. overall status: BLOCK, MATERIAL GAPS, MINOR GAPS, or READY FOR REVIEW;
  2. question-to-obligation matrix preserving original numbering;
  3. prioritized defect log with exact response locators;
  4. intermediary procedure and opinion gaps;
  5. filing synchronization list;
  6. predicted follow-up questions, with reasons;
  7. scope limitations and unresolved professional judgments.

When direct edits are requested, deliver the tracked-changes DOCX as the default corrected document.

Never state that a response is complete solely because every heading contains text.

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 Inquiry Response Review AI skill do?

Decompose and review Chinese IPO and refinancing regulatory inquiry responses for complete issue coverage, evidence, intermediary procedures, explicit opinions, filing synchronization, and follow-up risk. Use for 上交所、深交所、北交所或证监会问询回复、审核问询、反馈意见、落实函、子问题拆解、逐项回复检查、中介核查程序、明确意见、招股书同步更新 or multi-round response review. This skill reviews answer quality and traceability; it does not replace legal or accounting judgment.

Why use Cn Ib Inquiry Response Review on TypingMind?

Because you install it once and use it with any model. Cn Ib Inquiry Response Review 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 Inquiry Response Review 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-inquiry-response-review. 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 Inquiry Response Review?

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 Inquiry Response Review?

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

Is the Cn Ib Inquiry Response Review 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 👇