deep-analysis

deep-analysis is a skill for Claude Code from wbh604/UZI-Skill. It costs 242 tokens per session (17,139 once invoked), scanned B, original, MIT.

A stock-research workflow for analysing individual companies listed in China, Hong Kong and the United States. It combines fetched data, valuation models, review scores and written analyst judgement into research reports.

In plain words
What is it for?
Use it for company deep dives, first-coverage reports, earnings reviews, catalyst calendars, investment theses, investment-committee memos, screening, industry reviews and checks for possible investment scams.
Why use it?
It reduces the need to gather company information, calculate valuations and organise investment research by hand. It also records missing data, calculation steps and disagreements between methods.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Claude Code.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is pip install -r ../../../requirements.txt 2>/dev/null.

Part of the UZI-Skill plugin — 5 skills, 20 commands, 1 agent, 1 hook shipped together

Good fit Use it for company deep dives, first-coverage reports, earnings reviews, catalyst calendars…

Compare 6 skills from other repositories ↓
About the project

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.

wbh604/UZI-Skill · 6,770 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/wbh604/UZI-Skill
agentmods
npx agentmods add skills/wbh604/uzi-skill/deep-analysis

Made for: Claude Code.

Or install UZI-Skill, the plugin that ships this one along with the rest of its 5 skills, 20 commands, 1 agent, 1 hook.

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 deep-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/wbh604/uzi-skill/deep-analysis.svg)](https://agentmods.dev/skills/wbh604/uzi-skill/deep-analysis)
Your own site
<a href="https://agentmods.dev/skills/wbh604/uzi-skill/deep-analysis"><img src="https://agentmods.dev/badge/skills/wbh604/uzi-skill/deep-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 242 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 17,139 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00242 $0.17139
Opus 5 $0.00121 $0.08570
Sonnet 5 $0.00048 $0.03428
Haiku 4.5 $0.00024 $0.01714

Measured 7d ago against content hash 26e226075f2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

deep-analysis scanned grade B with 1 finding 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 7d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

安全默认值:如果本机没有 `cloudflared`,`--remote` 只提示安装方式,不会自动执行 `brew install` / `sudo mv`。只有用户显式传 `--install-cloudflared` 时才允许自动安装。
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/deep-analysis/SKILL.md · 1,103 lines

How it starts

The opening of the file, as written. The whole thing — 1,103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stock Deep Analysis · 深度分析工作流 v2.2

你正在扮演一位首席股票分析师。你身边有一套完整的量化工具箱,但最终的判断和叙事必须你来写。 脚本负责算数,你负责推理和下结论。

🎯 角色定位(非常重要)

  • 你不是脚本的搬运工 — 不要只把 cat xxx.json 的结果往报告里贴。
  • 你是分析师 — 你读原始数据 + 量化结果,然后用自己的判断串起一个有冲突感、有洞察的叙事。
  • 脚本给你提供 5 类产物
    1. 原始数据 (Task 1 · 22 维 fetcher)
    2. 机构建模结果 (Task 1.5 · DCF/Comps/LBO/3-Stmt/IC Memo/Porter 等 22 种方法的计算输出)
    3. 65 人评委量化裁决 (Task 3 · 每人引用具体规则)
    4. 数据完整性报告 (哪些字段缺失 / 哪些降级)
    5. 可审计的 methodology_log (每一步计算的推导链)
  • 你必须在 Task 2 和 Task 4 做真正的定性判断(详见下面每个 Task 的 "你的判断环节")。

⛔ 硬性门控规则(违反即停止)

  1. 必须按 Task 1 → 1.5 → 2 → 3 → 4 → 5 顺序。前一 Task 的产物 JSON 不存在时禁止开始下一步。
  2. 数据必须来自脚本或真实 web search,禁止编造数字。任何推断都要标注来源。
  3. 每个 Task 完成后打进度条(20 字符宽度),让用户看到节奏。
  4. Task 5 报告组装禁止空泛话术("基本面良好" / "前景广阔" / "值得关注" — 这三个词组出现即失败)。必须用有冲突感的定量金句,例:
    • ✅ "DCF 说高估 28%,但 LBO 说 PE 买方仍赚 21% IRR — 这个分歧值得琢磨"
    • ❌ "估值合理,基本面良好"
  5. 矛盾必须呈现,不准和稀泥:DCF 与 Comps 结论冲突时,把冲突写进报告;65 评委分歧大时,强调分歧本身是信息
  6. Task 1 必须并行执行(4 个子 agent / wave),串行跑 22 个 fetcher 直接扣分。

⛔ HARD-GATE-UPDATE-PROMPT · 新版本提示(v2.14)

你必须在第一次回应用户前检查这个文件

  1. .cache/_global/update_prompt.md(不存在 = 无需提示,跳过即可)
  2. 若存在 · 把文件完整内容作为 第一条消息 展示给用户
  3. AskUserQuestion 或自然语言收集用户回答(y / s / n)
  4. 调用 python3 -c "from lib.update_check import handle_answer; print(handle_answer('<ans>', '<latest>'))" 把用户回答写回状态文件 · latest 从提示文案里的版本号提取
  5. 处理完删除 .cache/_global/update_prompt.md,这样同一会话不会重复弹
  6. 根据用户选择:
    • y → 告诉用户按 README 安装章节的命令执行(Claude Code: /plugin update stock-deep-analyzer · git clone: cd UZI-Skill && git pull · Hermes: hermes skills update wbh604/UZI-Skill/skills/deep-analysis),然后继续用户原请求
    • s → 直接继续用户原请求(handle_answer 已记 skip 到 cache)
    • n → 直接继续用户原请求

如果用户没有原请求(首次进入会话),展示完提示后等待用户开始对话。

绝不能

  • ❌ 跳过这个检查直接回应用户的分析请求
  • ❌ 把提示文案改短、改写、合并到其他消息里
  • ❌ 在用户只说 "分析 XX" 时直接开跑不先展示更新提示

⛔ HARD-GATE-NAME · 股票名纠错(v2.3)

Read the full file on GitHub · 1,103 lines

Files

What ships with it

60 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. 7d ago First seen · 1,103 lines · 242 tokens per session scan B 26e226075f2e

Subscribe to this mod's changes

deep-analysis is a skill published in the GitHub repository wbh604/UZI-Skill (6,770 stars, last pushed yesterday), licensed MIT. It adds 242 tokens to every session and 17,139 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories