fincomp-deck

fincomp-deck is a skill for Claude Code, Codex from phanghonghao/THU-Awesome-Skills. It costs 216 tokens per session (2,981 once invoked), scanned A, original, MIT.

A Chinese-language workflow for creating or reviewing a 12-page pitch deck for a financing or business competition. A pitch deck is a short presentation explaining a project, its market, solution, evidence, business model, and plans.

In plain words
What is it for?
Generating a new competition pitch deck from project materials, or inspecting an existing deck page by page for missing evidence, unclear positioning, weak validation, and other structural gaps.
Why use it?
It gives a project presentation a fixed structure and checks whether an existing deck has important gaps. It also keeps claims tied to sources and focuses on innovation, feasibility, and industry value.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Generating a new competition pitch deck from project materials, or inspecting an existing deck page by page for missing evidence, unclear positioning, weak validation, and other structural gaps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/phanghonghao/thu-awesome-skills/fincomp-deck
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 phanghonghao/THU-Awesome-Skills --skill fincomp-deck
Clone the repo
git clone --depth 1 https://github.com/phanghonghao/THU-Awesome-Skills

Made for: Claude Code, 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 fincomp-deck

README.md
[![agentmods](https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/fincomp-deck/github.svg)](https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/fincomp-deck)
Your own site
<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/fincomp-deck"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/fincomp-deck/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 fincomp-deck

Your own site · 80×15
<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/fincomp-deck"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/fincomp-deck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 216 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,981 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.
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 $0.00216 $0.02981
Opus 5 $0.00108 $0.01491
Sonnet 5 $0.00043 $0.00596
Haiku 4.5 $0.00022 $0.00298

Measured 10d ago against content hash 32bb0455ed0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fincomp-deck 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 10d ago.

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/fincomp-deck/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fincomp-deck — 融资比赛 12 页路演 deck(生成 + 体检)

一套从真实大赛项目沉淀出的 12 页路演结构,可复用到任何融资/商业大赛场景。 自带"标准范例"(见 references/),生成时对照范例的笔法和密度,体检时用它做基准。

设计哲学(务必内化):

  • 大赛 deck ≠ 纯融资 deck。大赛评委额外重:技术创新性/壁垒、落地可行性、社会与产业价值;弱化估值与融资金额。
  • 每页只回答一个问题。标题是一句论断,不是主题词("马来西亚 SME 工厂卡在最难受的中间地带",不是"市场分析")。
  • 金句承担记忆点。每页留一句评委能复述给同事的话。
  • 脚注/来源=可信度。所有数字、政策、案例必须可溯源;正式版每页带脚注。

0. 模式路由(先判断,再动手)

用户给了什么 / 说了什么 模式 入口
描述新项目 / 给原始素材 / "做一版""写一份""生成" 生成模式 → §3
指向一个已存在的 deck 文件 / "体检""检查""审""对照""找缺口" 体检模式 → §4
不确定 先问:是要从零生成一份,还是审一份已有的?

判断不清时优先问一句,不要默认。


1. 12 页结构总表(核心资产)

每页固定 4 列:序号 / 页名 / 这一页必须回答的唯一问题 / 对应 SixArm 投资人框架页。

# 页名 唯一要回答的问题 ↔ SixArm
1 封面 Cover 我们是谁、为谁解决什么(一句话,不讲技术) (标题页,SixArm 无)
2 问题 Problem 谁在痛、痛在哪、为什么现有方案不合适 Problem ✓
3 为什么是现在 Why Now 为什么是现在做,而不是太早或太晚 Problem·Bonus + Market
4 市场洞察 Market 真正的空白带在哪、多窄多明确 Market ✓
5 定位 / 边界 Positioning 我们是什么、不是什么(缩边界) Solution + Competition
6 解决方案结构 Solution 我们交付的产品到底由什么组成 Solution ✓
7 Demo / MVP 现场只证明哪 3 件事 Validation(大赛特有,SixArm 无 Demo 页)
8 全球验证 Global Proof 这条路全球是否已被证明成立 Validation + Competition
9 壁垒 / 微笑曲线 Moat 凭什么是我们、护城河怎么长出来 Competition(可持续优势)
10 盈利模式 Business Model 钱怎么赚、怎么一步步长出高毛利层 Financial + Sales
11 上下游 / GTM 上游借谁、下游先打谁、怎么卖出第一单 Partner + Sales + Marketing
12 愿景 / Ask / Closing 接下来做什么、现在要什么 Investment + Roadmap

附 2 页备用页(Q&A 兜底,不在主 12 页内):

  • 备用页 A:公开案例数字(4 个可量化 case)
  • 备用页 B:核心来源总览(数据/政策/案例/客户)

2. 每页字段 schema(输出必须遵守)

每一页用以下结构,缺字段体检会扣分:

## 第 N 页|<页名>

### 标题
<一句论断,≤20 汉字,是结论不是主题词>

### 页面内容
- <3-5 条要点,可扫读;数字用反引号包住如 `21.2%`>

### 页面金句              ← 可选但强烈建议(承担记忆点)
> <1-2 行,评委能复述的话>

### 演讲提示              ← 生成版/路演版用此字段名
<这页讲什么、刻意不讲什么、停在哪个瞬间>

(正式版把"演讲提示"替换为 ↓)
### 脚注
`[1]` <证据说明,对应一个来源>

### 来源
[1] <机构/标题>  <URL>

### 建议配图
- 主图:`source/<文件名>`  或  <视觉概念描述>
- 小辅助图(可选):...

生成两版(沿用范例的交付习惯):

  • XX_12页路演版.md:用 ### 演讲提示,不带来源,适合直接进 PPT。
  • XX_12页路演版_带脚注正式版.md:把"演讲提示"换成 ### 脚注 + ### 来源,适合备注页/答辩备份。

Read the full file on GitHub · 209 lines

Files

What ships with it

3 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. 10d ago First seen · 209 lines · 216 tokens per session scan A 32bb0455ed0c

Subscribe to this mod's changes

fincomp-deck is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 216 tokens to every session and 2,981 once invoked, about $0.0011 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 2026-08-31.