cn-ib-deck-qc

cn-ib-deck-qc is a skill for Codex from Qiushen-first/cn-investment-banking-skills. It costs 111 tokens per session (892 once invoked), scanned A, original, Apache-2.0.

A quality-control workflow for Chinese investment-banking PowerPoint decks. It checks the editable presentation and its rendered slides for factual, consistency, source, formatting, and visual problems.

In plain words
What is it for?
Use it before circulating pitchbooks, transaction proposals, project updates, roadshow decks, or committee presentations. It helps report each problem with its slide location, evidence, severity, and correction.
Why use it?
A deck can look polished while containing stale numbers, the wrong company, missing sources, or leftovers from another project. The workflow separates confirmed defects from issues needing professional judgment.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it before circulating pitchbooks, transaction proposals, project updates, roadshow decks, or committee presentations. It helps report each problem with its slide location, evidence, severity, and correction.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qiushen-first/cn-investment-banking-skills/cn-ib-deck-qc
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Qiushen-first/cn-investment-banking-skills --skill cn-ib-deck-qc
Clone the repo
git clone --depth 1 https://github.com/Qiushen-first/cn-investment-banking-skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cn-ib-deck-qc

README.md
[![agentmods](https://agentmods.dev/badge/skills/qiushen-first/cn-investment-banking-skills/cn-ib-deck-qc/github.svg)](https://agentmods.dev/skills/qiushen-first/cn-investment-banking-skills/cn-ib-deck-qc)
Your own site
<a href="https://agentmods.dev/skills/qiushen-first/cn-investment-banking-skills/cn-ib-deck-qc"><img src="https://agentmods.dev/badge/skills/qiushen-first/cn-investment-banking-skills/cn-ib-deck-qc/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cn-ib-deck-qc

Your own site · 80×15
<a href="https://agentmods.dev/skills/qiushen-first/cn-investment-banking-skills/cn-ib-deck-qc"><img src="https://agentmods.dev/badge/skills/qiushen-first/cn-investment-banking-skills/cn-ib-deck-qc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 892 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.00892
Opus 5 $0.00056 $0.00446
Sonnet 5 $0.00022 $0.00178
Haiku 4.5 $0.00011 $0.00089

Measured 13d ago against content hash 36c426297ed8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cn-ib-deck-qc scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/scan_pptx.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/cn-ib-deck-qc/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CN IB Deck QC

Review a deck as a banker preparing it for circulation. Treat automated hits as leads, not final conclusions.

Principles

  1. Protect the client first: wrong entity, stale transaction terms, unsupported claims, and other-project residue are release blockers.
  2. Reconcile facts before polishing layout.
  3. Inspect both the editable file and rendered slides; XML or text extraction cannot prove visual correctness.
  4. Preserve the user's template, slide geometry, and house style unless asked to redesign.
  5. Report each issue with slide number, exact location, evidence, severity, and a concrete correction.
  6. Separate confirmed defects from items that require professional judgment.

Workflow

1. Establish the review baseline

Confirm:

  • intended audience and circulation status;
  • client, transaction, valuation date, and reporting period;
  • approved source documents and data cut-off date;
  • governing template and any required disclaimers;
  • whether the task is a full review or a delta review after refresh.

Do not assume that an old deck is the source of truth.

2. Scan the editable deck

Read references/deck-qc-checklist.md, then run:

python3 scripts/scan_pptx.py input.pptx --output deck-issues.csv

To detect names or terms from another project, create a temporary text file with one forbidden term per line and run:

python3 scripts/scan_pptx.py input.pptx --forbidden-terms forbidden.txt --output deck-issues.csv

The script checks text-accessible placeholders, unit case, duplicate punctuation, superlatives, small font settings, and supplied forbidden terms. It does not validate numbers against sources and does not replace rendering.

3. Reconcile high-risk content

Check every slide containing:

  • transaction structure, timetable, valuation, fundraising, share capital, or ownership;
  • historical or forecast financials;
  • market share, ranking, growth, capacity, customers, or order backlog;
  • legal, regulatory, tax, accounting, or eligibility conclusions;
  • credentials, tombstones, league tables, or comparable transactions.

Read the full file on GitHub · 97 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 97 lines · 111 tokens per session scan A 36c426297ed8

Subscribe to this mod's changes

cn-ib-deck-qc is a skill published in the GitHub repository Qiushen-first/cn-investment-banking-skills (101 stars, last pushed 26d ago), licensed Apache-2.0. It adds 111 tokens to every session and 892 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.