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.
git clone --depth 1 https://github.com/taxueseek/fund-investment-guidenpx agentmods add skills/taxueseek/fund-investment-guide/invest-fundWrote 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/skills/taxueseek/fund-investment-guide/invest-fund)<a href="https://agentmods.dev/skills/taxueseek/fund-investment-guide/invest-fund"><img src="https://agentmods.dev/badge/skills/taxueseek/fund-investment-guide/invest-fund/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.
<a href="https://agentmods.dev/skills/taxueseek/fund-investment-guide/invest-fund"><img src="https://agentmods.dev/badge/skills/taxueseek/fund-investment-guide/invest-fund.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00142 | $0.04694 |
| Opus 5 | $0.00071 | $0.02347 |
| Sonnet 5 | $0.00028 | $0.00939 |
| Haiku 4.5 | $0.00014 | $0.00469 |
Grade A, and why
invest-fund 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
invest-fund：基金分析
买基金是委托他人管理资产。不了解策略、不信任经理、成本不合理，就不买。
场景路由（收到请求后先判断，再执行）
| 用户说了什么 | 场景 | 读取 |
|---|---|---|
| "选哪个" "对比" + 同经理 | B：同经理多选一 | references/scene-b.md |
| "对比" "比较" "选哪个" + 不同基金 | F：多基金横向对比 | references/scene-f.md |
| "刚成立" "新发" "不到一年" "次新" | C：次新基金 | references/scene-c.md |
| "ETF" "指数基金" "联接" "跟踪误差" | E：ETF分析 | references/scene-e.md |
| 单一行业/主题（新能源、医药、白酒等） | G：行业主题 | references/scene-g.md |
| "体检" "诊断" "分析报告" "怎么样"（单基金） | A：标准体检 | references/scene-a.md |
| （其他，默认） | A：标准体检 | references/scene-a.md |
场景优先级：B(同经理) > F(跨基金对比) > G(行业) > C(次新) > E(ETF) > A(默认)
命中场景后只加载该场景的 reference 文件，不要预加载其他场景。一个场景走完再判断是否需要切换。
命中场景后加载对应 reference，按场景专属流程分析，不跑通用三关。
核心方法论
- 成果导向：不看宣传材料，看风险收益是否匹配目标
- 调查研究：看持仓、费率、经理操作逻辑——不做表面分析
- 抓主要矛盾：每类基金只有一个核心判断轴 → 主动基金看经理 | ETF看费率+跟踪 | 行业看纯度 | 次新看经理推断
通用三关审查（场景A默认使用，其他场景可参考）
当前日期 T，自动推导数据基准：
财年锚点 N = T.year if T > 4/30 else T.year - 1
分析周期 = [N-4, N-3, N-2, N-1, N]
| 当前日期 | 最新完整报告 | 数据新鲜度 | 搜索优先级 |
|---|---|---|---|
| 1-3月 | N-1年报 | 60-90% | 年报+最新净值 |
| 4月 | N年报 | 100% | 年报（强制披露） |
| 5-7月 | N年报 | 90-100% | 年报+季报 |
| 8月 | N半年报 | 100% | 半年报 |
| 9-10月 | N半年报 | 60-90% | 半年报+季报 |
| 11-12月 | N三季报 | 100% | 三季报 |
第一关：懂不懂（策略理解）
第一性原理：不懂投什么的基金，涨跌都不知道为什么。
验证问题：
- 基金投什么？（股票/债券/混合/商品/海外）
- 策略是什么？（主动选股/指数跟踪/量化/行业主题）
- 基准是什么？超额收益从哪来？
主动基金验证：
- 投资范围：股票占比区间？行业集中度？
- 策略描述：价值/成长/均衡？大盘/中盘/小盘？
- 能力圈：经理擅长什么？风格漂移过吗？
ETF/指数基金验证：
- 跟踪指数：编制规则透明吗？成分股多久调整？
- 跟踪误差：年化跟踪误差 < 0.3%？
- 流动性：日均成交额 > 5000万？
次新基金（成立<1年，无季报）：
- 基金合同：投资目标与策略是否清晰一致？
- 经理推断：历史能力圈能否迁移到新产品？
- 公司基因：同类策略历史表现如何？
未通过：策略不透明或超出理解 → 停止分析，不买
第二关：好不好（业绩与持续性）
第一性原理：好基金能持续跑赢基准，坏基金靠运气。
验证问题：
- 长期跑赢基准吗？（非短期运气）
- 风险调整后收益如何？
- 经理稳定吗？
数据验证（5年趋势 N-4至N年）：
| 指标 | N-4 | N-3 | N-2 | N-1 | N | 判断标准 |
|---|---|---|---|---|---|---|
| 年度收益 | __% | __% | __% | __% | __% | 跑赢基准 |
| 相对基准超额 | __% | __% | __% | __% | __% | 稳定正超额 |
| 最大回撤 | __% | __% | __% | __% | __% | 小于基准 |
| 规模（亿） | __ | __ | __ | __ | __ | 观察 |
What ships with it
8 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.
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.
- 8d ago Changed · +6 lines · +67 tokens per session a8f53d423497
- 12d ago First seen · 411 lines · 75 tokens per session scan A 12fef0b82b46
invest-fund is a skill published in the GitHub repository taxueseek/fund-investment-guide (18 stars, last pushed 9d ago), licensed MIT. It adds 142 tokens to every session and 4,694 once invoked, about $0.0007 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 skills, from other repositories
weekly-fno-trade-planner
Weekly F&O trade planning skill for Indian markets. Analyzes news/macro events, identifies trending sectors and instruments, determines probable direction, suggests option strategy with entry/exit levels, and manages stop-loss and profit booking after position entry. Use when user wants a weekly trade idea, F&O…
india-news-tracker
Track and analyze Indian stock market news, corporate announcements, SEBI circulars, bulk/block deals, and earnings calendars. Auto-fetches headlines from MoneyControl, Economic Times, LiveMint, BSE/NSE filings. Use when the user asks about recent news, corporate actions, upcoming events, or wants a daily market news…
options-strategy-advisor
Options strategy analysis for Indian F&O markets (NSE). Use when user requests options strategy recommendations, P/L analysis, Greeks calculation, risk management, or F&O strategy planning for Nifty, Bank Nifty, or stock options.
india-market-breadth
Analyze Indian market breadth health using advance/decline data, stocks above moving averages, new highs/lows, and sector participation. Use when assessing rally quality, market participation width, or equity exposure levels for NSE/BSE.
india-stock-analysis
Use when user requests analysis of Indian stocks, fundamental assessment, technical review, comparisons, or investment reports for NSE/BSE listed companies.
backtest-expert
Expert guidance for systematic backtesting of trading strategies on Indian markets (NSE/BSE). Use when developing strategies, testing robustness, avoiding overfitting, or validating trading ideas.