UZI-Skill is a collection of coding-agent skills for analyzing individual stocks across Chinese, Hong Kong, and United States markets using public data, investor viewpoints, quantitative rules, and institutional analysis methods. It is for users who want an agent to produce detailed stock-analysis reports. The catalogue entries are the commands, skills, instructions, plugin, agent, and hook that provide this workflow in supported coding agents.
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.
npx agentmods add commands/wbh604/uzi-skill/segmental-modelgit clone --depth 1 https://github.com/wbh604/UZI-SkillWrote 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.
[](https://agentmods.dev/commands/wbh604/uzi-skill/segmental-model)<a href="https://agentmods.dev/commands/wbh604/uzi-skill/segmental-model"><img src="https://agentmods.dev/badge/commands/wbh604/uzi-skill/segmental-model.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.01357 |
| Opus 5 | $0.00022 | $0.00678 |
| Sonnet 5 | $0.00009 | $0.00271 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
segmental-model 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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- segmental-model — 92% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/segmental-model <股票代码或名称>
对目标股票做 bottom-up 分业务收入模型,跟自上而下的 DCF 互补校验。
为什么需要这个方法
现有 22 种机构方法里,DCF/3-statement/IC Memo 都是 top-down——从整体营收 × 单一增速假设推未来。遇到业务结构在转型的公司就失真:
- 贵州茅台 直销比例 17% → 目标 50%+
- 宁德时代 动力电池 vs 储能 vs 海外 三条曲线增速完全不同
- Credo 收购 SiPh 后,Optics 线增速和 AEC 线差两倍
单一营收增速掩盖了这些分化。本方法把公司拆 3-5 条业务线,每条独立给 driver,三情景 3 年 projection,总量必须对账回当前营收。
工作流(agent 必须走完 5 步)
Step 1 · 生成骨架(脚本)
python skills/deep-analysis/scripts/compute_segmental.py discover <ticker>
读 5_chain.breakdown_top + 1_financials.revenue_history + 15_events,产出 .cache/<ticker>/segmental_skeleton.json:
{
"ticker": "600519.SH",
"name": "贵州茅台",
"currency": "CNY",
"total_revenue_latest_yi": 1721.4,
"segments": [
{"name": "茅台酒", "latest_revenue_yi": 1460.3, "latest_share_pct": 84.83, ...},
{"name": "系列酒", "latest_revenue_yi": 246.0, "latest_share_pct": 14.29, ...}
],
"inflection_candidates": [
"直销渠道占比持续提升",
"1935 新品上市拓展年轻客群"
]
}
Step 2 · 读骨架 + 识别核心 thesis(agent)
Agent 必做:
- 打开
.cache/<ticker>/segmental_skeleton.json - 结合
6_research.reports(卖方研报对业务分段的看法)+14_moat+13_policy - 识别 核心 inflection(1-2 条)——例如:
- 茅台 = "直销占比 17% → 50%+"
- 宁德 = "海外储能 0 → 30%+"
- Credo = "copper → SiPh optics"
- 围绕 inflection 组织 segment 叙事
Step 3 · 填 driver(agent)
对每个 segment 写:
- drivers: 价 × 量 × 市占 × 渗透 —— 至少列 2 个
- ✓ 好例子:
["ASP +5%/年", "shipment +20%/年"] - ✗ 坏例子:
["行业景气"]
- ✓ 好例子:
- thesis_tag:
growth_engine/cash_cow/declining/cyclical/turnaround - bull_growth_3y_cagr / base_growth_3y_cagr / bear_growth_3y_cagr 必须满足 bull ≥ base ≥ bear
Step 4 · 写回 + 校验(脚本)
写 .cache/<ticker>/segmental_model.json,然后:
python skills/deep-analysis/scripts/compute_segmental.py validate <ticker>
校验规则:
- 🔴 sum(segment.latest_revenue) 必须对账回 total_revenue ±10%
- 🔴 每个 segment bull ≥ base ≥ bear 单调
- 🟡 Base 情景 3 年总增速 > 100% 需要明确收购/新业务 note
- 🟡 每个 segment 必须有 ≥ 1 个 driver
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.
- 5d ago First seen · 112 lines · 44 tokens per session scan A c9007fbc8831
segmental-model is a command published in the GitHub repository wbh604/UZI-Skill (6,756 stars, last pushed 8d ago), licensed MIT. It adds 44 tokens to every session and 1,357 once invoked, about $0.0002 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.
Other commands, from other repositories
merit-reconcile
Preview or check the status of Stripe → Merit payout reconciliation (read-only).
audit-checklist
Perform an internal audit, review controls, or prepare for an external financial audit.
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
scan
Scan AWS account for cost optimization.
finops-status
Orientation — say where an opportunity or assignment sits in the five-step FinOps lifecycle and what unlocks next. Useful when a record has no active stage: an opportunity while its assignments do the work, an assignment whose plan has not been approved yet, or a rejected or archived assignment. Read-only; mutates…
archive-ledger
../../../shared/commands/archive-ledger.md.