Cn Ib Filing Refresh Control logo

Cn Ib Filing Refresh Control

Community
QiushenZou
cn-ib-filing-refresh-control

Plan, execute, and review Chinese IPO or refinancing filing refreshes across reporting periods, transaction changes, inquiry responses, and document versions. Use for 加期审计、财务数据更新、申报材料换期、新旧版本对比、漏改检查、招股书更新、问询回复同步、数据截止日更新、全套材料刷新 or stale-content review. This skill controls refresh scope and closure across documents; use source and cross-document skills for substantive verification.

Overview

PublisherQiushenZou
Repositorycn-investment-banking-skills
Skill namecn-ib-filing-refresh-control
Stars
97
Forks
0
Bundled files
9
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.

  • 9 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 Filing Refresh Control 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-filing-refresh-control
  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-filing-refresh-control .claude/skills/cn-ib-filing-refresh-control
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cn Ib Filing Refresh Control 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 Filing Refresh Control 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 Filing Refresh Control 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 Filing Refresh Control

Treat a filing refresh as a controlled change program, not a search-and-replace exercise.

Principles

  1. Start from refresh drivers and dependencies before editing individual documents.
  2. Distinguish changed facts, changed periods, changed conclusions, and presentation-only edits.
  3. Propagate one source change to every downstream table, narrative, risk factor, opinion, and filing.
  4. Preserve old/new lineage and explain intentional non-updates.
  5. Require independent review and closure evidence for material changes.
  6. Scan for stale terms after editing, but treat search hits and non-hits as review leads only.
  7. Apply changes to existing Word filings as native tracked revisions by default.

Workflow

1. Define the refresh baseline

Record:

  • old and new reporting cut-offs;
  • documents and versions in scope;
  • refresh drivers: new audit period, transaction change, inquiry response, rule change, corporate event, or correction;
  • approved new source documents;
  • freeze date, owners, reviewers, and delivery deadline.

Read references/refresh-drivers.md and build a driver-to-document impact map.

2. Build the refresh register

Use assets/refresh-register-template.csv. Create one row for each affected disclosure unit, not one row per entire document. Record old/new source, period, value, unit, change type, downstream documents, update locator, consistency review, and closure evidence.

Read references/change-taxonomy.md before classifying changes.

3. Execute in dependency order

Recommended order:

  1. approve new source data and definitions;
  2. update core financial and operating tables;
  3. reperform totals, ratios, changes, and CAGR;
  4. update narrative analysis, trends, risk factors, and conclusions;
  5. propagate changes to sponsor, legal, accounting, inquiry, and summary documents;
  6. update dates, defined terms, cross-references, contents, appendices, and signatures;
  7. run stale-term and cross-document checks.

Do not update narrative percentages independently from their underlying tables.

For DOCX refreshes, preserve the original, use native Word insertions and deletions, keep each amendment granular, and retain existing comments and revisions unless instructed otherwise. Do not simulate redlines with color or strikethrough. Use a transparent revision author such as Codex when none is specified.

4. Validate the control register

Generate a first-pass text delta between two DOCX versions:

bash
python3 scripts/compare_docx_text.py old.docx new.docx --output text-delta.csv

The delta preserves ordered paragraph and table-row changes but does not prove that a required update occurred. Convert material change blocks into refresh-register rows and classify their drivers and downstream effects.

Then validate the register:

Run:

bash
python3 scripts/review_refresh_register.py refresh-register.csv --output refresh-issues.csv

The script identifies incomplete lineage, missed propagation, invalid closure, lack of consistency review, and self-review.

5. Scan for stale content

Create a UTF-8 CSV using assets/stale-terms-template.csv, then run:

bash
python3 scripts/scan_stale_terms.py refreshed-file.docx stale-terms.csv --output stale-hits.csv

The scanner supports UTF-8 text/Markdown, DOCX, and PPTX text-accessible content. PDF or rendered deliverables require separate text extraction and visual inspection. A zero-hit result does not prove that the refresh is complete.

6. Perform semantic delta review

Read references/closure-standard.md. Compare old and new versions for:

  • changed numbers without changed explanation;
  • changed conclusion without corresponding evidence;
  • inconsistent periods, units, definitions, and denominators;
  • stale superlatives, rankings, market data, ages, or elapsed periods;
  • inquiry-response facts not synchronized into the filing;
  • deleted qualifications or new contradictions;
  • cross-references and page references affected by pagination.

Use cn-ib-source-verifier to reperform sourced calculations, cn-ib-cross-document-check for propagated facts, and cn-ib-filing-proofreader for final production QC.

7. Close and release

Close an item only when the updated locator, downstream propagation, consistency check, reviewer, and closure evidence are recorded. Structurally verify that the tracked insertions and deletions exist in each revised DOCX, then re-render the final document and inspect every materially changed page.

Deliver the tracked-changes version by default. Create a clean accepted version only when explicitly requested, and never overwrite the original.

Output contract

Deliver:

  1. refresh scope and driver summary;
  2. document impact map;
  3. old/new change register;
  4. stale-content and missed-propagation issue log;
  5. open items by owner and severity;
  6. release status: BLOCK, CONDITIONAL, or READY;
  7. limitations, excluded documents, and unresolved judgments.

Never describe a filing set as fully refreshed based only on textual search or redline volume.

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 Filing Refresh Control AI skill do?

Plan, execute, and review Chinese IPO or refinancing filing refreshes across reporting periods, transaction changes, inquiry responses, and document versions. Use for 加期审计、财务数据更新、申报材料换期、新旧版本对比、漏改检查、招股书更新、问询回复同步、数据截止日更新、全套材料刷新 or stale-content review. This skill controls refresh scope and closure across documents; use source and cross-document skills for substantive verification.

Why use Cn Ib Filing Refresh Control on TypingMind?

Because you install it once and use it with any model. Cn Ib Filing Refresh Control 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 Filing Refresh Control 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-filing-refresh-control. 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 Filing Refresh Control?

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 Filing Refresh Control?

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

Is the Cn Ib Filing Refresh Control 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 👇