fund-guy-skill: Skill for Claude Code

.agents/skills/fund-manager-alpha/SKILL.md

fund-manager-alpha is a skill for Claude Code from wbh604/fund-guy-skill. It costs 166 tokens per session (666 once invoked), scanned A, original, MIT.

A detailed audit of how a public fund manager makes investment decisions, delivered as a self-contained interactive HTML report. It separates the current manager's record from previous managers and examines trades, comparisons, market events, and possible warning signs.

In plain words
What is it for?
Reviewing individual trades after twelve months, testing whether decisions appear independent, replaying market events, checking drawdowns and forced selling, investigating performance-chasing, comparing similar funds, and producing a shareable report.
Why use it?
It helps distinguish repeatable decision-making from market-wide gains, luck, copied positions, or incomplete evidence. It also records missing data instead of filling gaps with guesses.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents).

This is wbh604/fund-guy-skill's own configuration. It tells Claude Code how to work on fund-guy-skill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fund-guy-skill configures →

Part of the fund-manager-alpha plugin — 1 skill, 3 commands shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to wbh604/fund-guy-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wbh604/fund-guy-skill/main/.agents/skills/fund-manager-alpha/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/wbh604/fund-guy-skill

Made for: Claude Code.

Or install fund-manager-alpha, the plugin that ships this one along with the rest of its 1 skill, 3 commands.

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 fund-manager-alpha

README.md
[![agentmods](https://agentmods.dev/badge/skills/wbh604/fund-guy-skill/fund-manager-alpha/github.svg)](https://agentmods.dev/skills/wbh604/fund-guy-skill/fund-manager-alpha)
Your own site
<a href="https://agentmods.dev/skills/wbh604/fund-guy-skill/fund-manager-alpha"><img src="https://agentmods.dev/badge/skills/wbh604/fund-guy-skill/fund-manager-alpha/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 fund-manager-alpha

Your own site · 80×15
<a href="https://agentmods.dev/skills/wbh604/fund-guy-skill/fund-manager-alpha"><img src="https://agentmods.dev/badge/skills/wbh604/fund-guy-skill/fund-manager-alpha.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 666 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 10
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 34
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00166 $0.00666
Opus 5 $0.00083 $0.00333
Sonnet 5 $0.00033 $0.00133
Haiku 4.5 $0.00017 $0.00067

Measured 6d ago against content hash 82ecbca33a65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fund-manager-alpha 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 6d 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.

.agents/skills/fund-manager-alpha/SKILL.md · 37 lines

What it actually says

Fund Manager Alpha · 基金经理行为审计(入口)

评的是行为,不是净值。

完整方法论在本仓库 skills/fund-manager-alpha/SKILL.md(18 条硬规则、三层取数模型、 行为评分公式、报告模块规范)—— 动手前先完整读它,本文件只是入口。

快速开始

pip install -r requirements.txt
python run.py <基金代码>              # 一键:取数 → 分析 → 出报告
python run.py <基金代码> --skip-fetch # 已有 .cache 数据时

产出:assets/fund-<code>.html(自包含单文件,离线可看可分享)。请用浏览器直接打开本地文件;不要用 htmlpreview.github.io / gist 在线预览,那些页面经常不跑脚本,分数和 K 线会显示成空的。

参考脚本在仓库根 scripts/(fetch → analyze → build,README 有逐条命令)。 接口失效时不要死修脚本,按主文档的三层取数模型(公开 API → 浏览器抓取 → 请用户登录)自行补数。

三条不可违反

  1. 先做任期切割 —— 前任业绩混入现任评价 = 分析作废
  2. 绝不编数 —— 拿不到就标"未获取"并压置信度,没有出处的数字不进报告
  3. 定性判断由你做 —— 公告全文解读、Mandate 约束抽取仍没有脚本。造神九项能用本品公告/任期/持仓筛的已自动出结论(三级证据制);季报原文、亲属任职、招募书全文对照仍标未获取。行业用东财/港股公开分类自动取,禁止手写某只基金的对照表;窗口、费率、风格指数全部按所选基金重算

更多

  • 完整硬规则与工作流:skills/fund-manager-alpha/SKILL.md
  • 算法细节:skills/fund-manager-alpha/references/
  • 设计决策:DESIGN.md
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. 6d ago Changed 82ecbca33a65
  2. 10d ago First seen · 37 lines · 166 tokens per session scan A 4de49b9aabea

Subscribe to this mod's changes

fund-manager-alpha is a skill published in the GitHub repository wbh604/fund-guy-skill (514 stars, last pushed 6d ago), licensed MIT. It adds 166 tokens to every session and 666 once invoked, about $0.0008 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.

Related

Other skills, from other repositories