Investment Research Bias Check
HKUDS/Vibe-Trading
A short checklist to read at the start of stock screens, sector studies and company deep-dives that counters leader, English-language, narrative, confirmation and recency bias.
Answers questions with sourced quotes from one Chinese fund manager's public writings, applies his stated investment method and compares his words with real fund holdings.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add lyra81604/zhengxi-views --skill zhengxi-views -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lyra81604/zhengxi-views zhengxi-views --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "zhengxi-views" agent skill from https://github.com/lyra81604/zhengxi-views/tree/main into .claude/skills/zhengxi-views/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhengxi-views", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lyra81604/zhengxi-views --skill zhengxi-views -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lyra81604/zhengxi-views zhengxi-views --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "zhengxi-views" agent skill from https://github.com/lyra81604/zhengxi-views/tree/main into .agents/skills/zhengxi-views/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhengxi-views", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lyra81604/zhengxi-views --skill zhengxi-views -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lyra81604/zhengxi-views zhengxi-views --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "zhengxi-views" agent skill from https://github.com/lyra81604/zhengxi-views/tree/main into .cursor/skills/zhengxi-views/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhengxi-views", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lyra81604/zhengxi-views --skill zhengxi-views -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lyra81604/zhengxi-views zhengxi-views --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "zhengxi-views" agent skill from https://github.com/lyra81604/zhengxi-views/tree/main into .gemini/skills/zhengxi-views/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhengxi-views", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lyra81604/zhengxi-views zhengxi-viewsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lyra81604/zhengxi-views --skill zhengxi-views -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "zhengxi-views" agent skill from https://github.com/lyra81604/zhengxi-views/tree/main into .github/skills/zhengxi-views/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhengxi-views", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lyra81604/zhengxi-views --skill zhengxi-views -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lyra81604/zhengxi-views zhengxi-views --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "zhengxi-views" agent skill from https://github.com/lyra81604/zhengxi-views/tree/main into .opencode/skills/zhengxi-views/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zhengxi-views", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
zhengxi-viewsAnswers questions with sourced quotes from one Chinese fund manager's public writings, applies his stated investment method and compares his words with real fund holdings.
The skill rests on three sets of material under `references/`: a corpus of his public views, including periodic reports, manager notes and media interviews, a method framework distilled from that corpus with each point backed by his own words, and snapshots of real data for his funds such as quarterly top holdings, net value, performance, size and asset allocation. A list covering the whole mutual fund market lets the agent look up any fund and fetch its details on demand.
Answers should read naturally but follow one rule: look first, then speak. What he said is quoted with its source, and anything inferred is labeled as deduced from his method, including topics his corpus never covered. Supported requests include sector views, explaining the method, commentary in his reporting style marked as simulated, comparing words against holdings only for quarters he managed, and scoring a fund against his framework. Helper scripts search the corpus, look up funds and refresh data, and the skill states it is a research aid and not investment advice.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 304ac3e. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Zhengxi Fund Manager Views Library loads about 1.6k tokens when it runs, and up to ~1.8M if it reads all its reference files. Until then it costs about 201 tokens; SKILL.md has 263 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from lyra81604/zhengxi-views at commit 304ac3e, republished under its MIT licence (© lyra81604). 263 words, ~1,570 tokens.
.claude/skills/zhengxi-views/SKILL.md (or your agent's skills folder). This skill also uses 156 other files; get the full folder from GitHub.让 AI 既能查到、引用郑希(易方达权益投资管理部副总经理、基金经理)本人公开说过的话,也能用他自己的投资方法去聊任何相关的话题。
三块根基,都在 references/ 里,都来自他的公开内容、可溯源(具体收录数量见 README,回答用户时不用报"共多少篇"这类数字):
references/corpus/ —— 他 2012–2026 的全部公开观点:定期报告、基金经理手记、媒体采访,外加简介与基金清单。references/method.md —— 从上面的语料蒸馏出来的方法框架,每一条都有他本人原话佐证。这是它和"凭印象总结方法论"的 skill 的根本区别。references/fund_data/ —— 他全部 8 只基金(4 在任 + 4 曾任)的真实数据快照:每季前十大重仓股、净值/业绩/规模/资产配置/任职回报。来自天天基金公开数据,可用 scripts/fetch_fund_data.py 刷新。先看 references/fund_data/_index.md 了解有哪些基金、覆盖哪些季度。references/all_funds/fund_list.json —— 全市场约 2.7 万只基金的列表(代码/名称/类型/拼音),可检索、识别、按类型筛选。任意基金的明细按需实时抓取(见下面【查全市场任意基金】)。本 skill 的脚本都用绝对路径自己定位数据、并已自带输出上限,所以调用时务必保持成一条最朴素的命令:
python "<本skill目录>/scripts/search_corpus.py" "光通信"cd … && python …(组合命令里含 cd 会被强制人工确认)2>/dev/null、| head、> 等重定向或管道(同样触发确认); / && 把多个命令串起来——一次只跑一个脚本,要搜多个词就分多次调用<本skill目录> 就是本 SKILL.md 所在的目录(脚本在它的 scripts/ 子目录)。用它的绝对路径,不要先 cd 进去。脚本输出已限制长度,不需要再 | head。
像一个读熟了郑希全部公开材料、也吃透了他方法的人那样聊天,而不是填表。用户问得随意,你就答得随意;用户要深挖,你再展开。下面这些是可选的工具和惯例,不是必须套的模板——用得上就用,别为了结构牺牲自然。
核心就一句话:先查,再说;说他说过的,就引原文标出处;说推演的,就讲清是按他的方法推的。
search_corpus.py 找原文,引用关键段落并自然点明来源;有演变就把不同年份串起来讲。references/method.md 作答(它每条都配了他本人原话,引用时直接用那些话、自然说明出处即可)。references/fund_data/。见下面【言行对照】。这是接入真实基金数据后最有价值的用法。当用户问"他说看好 X,实际买了吗""他的持仓印证了哪些观点",或你想让一个观点更有说服力时:
references/fund_data/{基金}/季度持仓.md 拿到对应季度的真实持仓,两相对照。净值业绩规模.md(净值、区间收益、最大回撤、任职回报、规模、资产配置、业绩评价都在里面)。_index.md 和文件头都标了郑希的任职起止,对照前先按这个区间过滤,别把别人的持仓算到他头上。用户可能问别的基金、别的经理,或要把郑希和同类比。这时走全市场能力:
python scripts/fund_lookup.py 关键词(支持名称/拼音/代码、--type 按类型筛)。python scripts/fetch_any_fund.py <代码>(可多只一起抓,用于对比),数据落到 references/fund_data_cache/{代码}_{名称}/,结构和郑希的一样(季度持仓 + 净值业绩规模)。读缓存里的文件作答。references/fund_data/ 里郑希的数据并列分析(收益/回撤/持仓风格/重仓行业)。--force;② 郑希自己的 8 只基金用 references/fund_data/ 里的精编快照,不必用 fetch_any_fund;③ 全市场数据同样是公开披露的季度快照,引用标日期,不杜撰。用户说"给 XX 基金打个分""用郑希的标准评评这只基金""这只基金郑希会买吗"时:
python scripts/score_fund.py <代码或名称>。它会自动:解析代码 → 备齐数据(郑希的用精编快照,别的实时抓取并缓存)→ 算好集中度、换手代理、业绩/回撤、规模、资产配置、任职回报等机械指标,打印一份证据档案。不用再单独跑 lookup/fetch/读文件。references/scorecard.md,用它的六维(景气方向·ROE低位弹性·全球比较优势·流动性·集中度与周期拼接·业绩印证)逐项给分,给总分、评级、理由,并和郑希自己的基金对比风格。这是上一版的短板——以前碰到语料没覆盖的就只回一句"未见",显得很干。正确做法是退守到他的方法:
references/method.md 的框架去推演:"按他的方法看——他会先问 X 里哪一层在涨价/有通胀,是不是供给端创造的需求,中国在哪一环有比较优势,哪些标的 ROE 低位有修复弹性、流动性够……"。把方法落到这个具体话题上,给出有内容的判断。这样语料外的问题也能答得有料,而不是空手。
skill 的全部价值在于"可信"。可以灵活,但下面几条是底线:
references/corpus/ 里的文字一致,不改写、不缩写后当原话。[采2606]、method.md、§1、(类型|日期|标题) 这类格式、或语料的文件名/路径,都不要出现在给用户的文字里。来源的真实性已在 README 说明,正文里自然带一句即可,不必堆砌。references/fund_data/(并注明季度/日期),不能自己编;语料和数据里都没有的,就如实说没有。scripts/search_corpus.py "关键词" —— 在语料里搜,返回命中段落 + 出处。--any 命中任一词,--type 定期报告 限类型,--context 2 带上下文。中文术语跨年份措辞会变(光模块/光通信、算力/AI Capex),命中少时换近义词或加 --any。references/corpus_index.json —— 全部语料目录(类型/标题/日期/出处/路径),先看它了解有哪些材料。references/method.md —— 投资方法框架,回答方法类问题、做前瞻推演、写风格化点评时读它。references/fund_data/_index.md —— 8 只基金的数据快照入口;每只基金目录下有 季度持仓.md(前十大重仓股,逐季)与 净值业绩规模.md(净值/收益/回撤/任职回报/规模/资产配置/业绩评价),另有同名 .json 供精确取数。scripts/fund_lookup.py 关键词 —— 在全市场 2.7 万只基金里按名称/拼音/代码/类型查找,把基金名解析成代码、找同类基金。scripts/fetch_any_fund.py <代码> —— 按需抓取任意基金的持仓/净值/业绩到 references/fund_data_cache/(需联网,可多只、可 --force)。scripts/score_fund.py <代码或名称> —— 评分一键入口:自动找代码+备数据+算机械指标,输出证据档案,配合 references/scorecard.md 打分。references/scorecard.md —— 郑希框架评分卡(六维规则、打分区间、输出格式)。python scripts/build_index.py;郑希基金快照刷新跑 python scripts/fetch_fund_data.py(可加代码只刷一只);全市场列表刷新跑 python scripts/build_fund_list.py。研究与学习辅助,不构成投资建议,不预测涨跌、不给买卖指令、不承诺收益。语料与方法均来自郑希公开内容。
© lyra81604, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 156 other files (scripts, references, assets) in the repository root of lyra81604/zhengxi-views.
Open the folder on GitHubat commit 304ac3e
Zhengxi Fund Manager Views Library next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Zhengxi Fund Manager Views Library this skilllyra81604/zhengxi-views | 1.8k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Investment Research Bias CheckHKUDS/Vibe-Trading | 35k | — | ~720 | Automated safety check: Pass | MIT | |
| AI-Trader Market IntelHKUDS/AI-Trader | 23k | — | ~1.1k | Automated safety check: Pass | None | |
| Eastmoney Market DataHKUDS/Vibe-Trading | 35k | — | ~1k | Automated safety check: Pass | MIT | |
| Stock Deep Analysis Workflowwbh604/UZI-Skill | 7.1k | — | ~9.1k | Automated safety check: Notes | MIT | |
| SEC EDGAR Filings FetcherHKUDS/Vibe-Trading | 35k | — | ~1.4k | Automated safety check: Pass | MIT |
HKUDS/Vibe-Trading
A short checklist to read at the start of stock screens, sector studies and company deep-dives that counters leader, English-language, narrative, confirmation and recency bias.
HKUDS/AI-Trader
Reads AI-Trader's read-only market snapshots, grouped financial news and events board through its market-intel endpoints, for context before trading or posting.
HKUDS/Vibe-Trading
Index of Eastmoney's free, no-token market data interfaces for China A-shares and Hong Kong stocks: fund flows, dragon-tiger lists, margin trading, reports and news.
wbh604/UZI-Skill
Runs a staged deep analysis of a single stock on China A-share, Hong Kong and US markets, ending in an HTML report with valuation models and investor-panel scores.
HKUDS/Vibe-Trading
Fetches U.S. SEC EDGAR data: resolves tickers to CIK numbers, lists recent 10-K, 10-Q and 8-K filings with document URLs, and pulls XBRL financial series.
xbtlin/ai-berkshire
Scans a long-running industry trend for supply chain chokepoints, aiming to find second- and third-layer suppliers that the market has not yet priced in.
Categories
Answers questions with sourced quotes from one Chinese fund manager's public writings, applies his stated investment method and compares his words with real fund holdings. The skill rests on three sets of material under `references/`: a corpus of his public views, including periodic reports, manager notes and media interviews, a method framework distilled from that corpus with each point backed by his own words, and snapshots of real data for his funds such as quarterly top holdings, net value, performance, size and asset allocation. A list covering the whole mutual fund market lets the agent look up any fund and fetch its details on demand.
Zhengxi Fund Manager Views Library fits situations like: asking how this fund manager views a sector such as optical communications; checking whether his stated views match his quarterly holdings; looking up or comparing the data of any China mutual fund; writing market commentary in his reporting style.
Run `npx skills add lyra81604/zhengxi-views --skill zhengxi-views -a claude-code`. Or copy the skill folder (the lyra81604/zhengxi-views repository) into .claude/skills/zhengxi-views in your project. Claude Code loads it when a task matches its description.
Run `npx skills add lyra81604/zhengxi-views --skill zhengxi-views -a codex`. Or copy the skill folder (the lyra81604/zhengxi-views repository) into .agents/skills/zhengxi-views in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lyra81604/zhengxi-views --skill zhengxi-views -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/zhengxi-views, .gemini/skills/zhengxi-views, .github/skills/zhengxi-views and .opencode/skills/zhengxi-views in your project.
Going by SKILL.md and its folder, Zhengxi Fund Manager Views Library needs the command-line tools its instructions call (python). Our summary lists: Python to run the bundled search and fund-data scripts; Network access to refresh fund data.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Zhengxi Fund Manager Views Library is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8M tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Zhengxi Fund Manager Views Library: Investment Research Bias Check (HKUDS/Vibe-Trading, 35k stars), AI-Trader Market Intel (HKUDS/AI-Trader, 23k stars), Eastmoney Market Data (HKUDS/Vibe-Trading, 35k stars) and Stock Deep Analysis Workflow (wbh604/UZI-Skill, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
lyra81604 (a GitHub user) maintains it in lyra81604/zhengxi-views, which has 1,751 GitHub stars. The repository was last updated on September 4, 2026.
Source: lyra81604/zhengxi-views on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.