Ross ROSS = Recommend OSS · open-source software intelligence for agents

lyra81604/zhengxi-views

可溯源的郑希(易方达基金经理)投研 Agent Skill——基于他全部公开观点原文 + 有原话佐证的投资方法 + 全市场基金真实数据,能溯源问答、按他框架给基金打分,绝不杜撰。⚠️仅研究学习辅助,不构成投资建议‼️website是郑希主页! observed · 2026-08-28

github.com/lyra81604/zhengxi-views · homepage · Python · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

55/100

  • Activity 93
  • Release rhythm 35
  • Longevity 5

Flags: no_releases young no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 74
  • days_rel: n/a
  • days_push: 42
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1390 stars · 151 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A traceable AI agent skill packaging the complete public statements of E Fund fund manager Zheng Xi (2012–2026 quarterly reports, notes, media interviews), a distilled investment-method framework with verbatim citations, and real data snapshots for his 8 funds plus ~27,000 market-wide funds. It enables sourced Q&A, method-based forward reasoning, style imitation, holdings-vs-words verification, and six-dimension fund scoring in his framework, across Claude, ChatGPT, Gemini, Cursor, and other AI platforms.

Use cases

  • look up what fund manager Zheng Xi actually said about a sector with original-text citations
  • learn Zheng Xi's stock-picking methodology backed by his own quotes
  • generate forward-looking analysis using his framework when the corpus has no direct answer
  • write commentary imitating his quarterly-report style
  • verify whether his stated views match his actual holdings and performance
  • compare and score any of ~27,000 Chinese funds using his criteria
  • automate a daily trading-day research report pipeline via WorkBuddy and MCP

When to choose

  • you need verifiable, source-cited answers about a specific fund manager's views instead of model hallucinations
  • you want to study or replicate a Chinese tech/growth fund manager's investment framework
  • you need fund comparison and scoring grounded in real holdings and NAV data
  • you want an automated daily fund-research assistant wired into an AI agent with MCP connectors

When to avoid

  • you need actual investment advice or buy/sell recommendations - the project explicitly disclaims that
  • you need real-time market data without your own data connectors
  • you need coverage of fund managers other than Zheng Xi beyond basic fund lookup
  • you require a license-clear dependency - the repo license is marked NOASSERTION

Facets

plugin · maturity active

rag search-engine data-science agent-framework mcp fintech artificial-intelligence large-language-models data-science analytics python cli cross-platform agent-skill fund-manager chinese-funds mutual-funds traceable-qa investment-research e-funds zhengxi corpus fund-scoring

2 sources

Member repositories

RepositoryRoleHealth v2
lyra81604/zhengxi-viewsmain55

For agents

markdown · JSON · MCP: product_card(name="lyra81604/zhengxi-views")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem