Stock API
zhangxiangliang/stock-api
Fetch real-time stock quotes, K-line (candlestick) history, and search symbols for China A-shares, Hong Kong, and US markets.
Runs a layered value-investing screen on an industry or theme, narrowing from a 30-to-60 company market scan down to 3 final candidates with documented elimination reasons at each layer.
SKILL.md written in Chinese; this summary is our English description.
Install Industry Value-Investing Funnel
$ npx skills add xbtlin/ai-berkshire --skill industry-funnel -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install xbtlin/ai-berkshire industry-funnel --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .claude/skills && cp -r skills-src/codex-skills/industry-funnel .claude/skills/industry-funnel && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "industry-funnel" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/industry-funnel into .claude/skills/industry-funnel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "industry-funnel", 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.
$skill-installer install https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/industry-funnelType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add xbtlin/ai-berkshire --skill industry-funnel -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install xbtlin/ai-berkshire industry-funnel --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .agents/skills && cp -r skills-src/codex-skills/industry-funnel .agents/skills/industry-funnel && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "industry-funnel" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/industry-funnel into .agents/skills/industry-funnel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "industry-funnel", 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 xbtlin/ai-berkshire --skill industry-funnel -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install xbtlin/ai-berkshire industry-funnel --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/codex-skills/industry-funnel .cursor/skills/industry-funnel && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "industry-funnel" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/industry-funnel into .cursor/skills/industry-funnel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "industry-funnel", 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.
$ gemini skills install https://github.com/xbtlin/ai-berkshire.git --path codex-skills/industry-funnel--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add xbtlin/ai-berkshire --skill industry-funnel -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install xbtlin/ai-berkshire industry-funnel --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/codex-skills/industry-funnel .gemini/skills/industry-funnel && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "industry-funnel" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/industry-funnel into .gemini/skills/industry-funnel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "industry-funnel", 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 xbtlin/ai-berkshire industry-funnelInstalls 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 xbtlin/ai-berkshire --skill industry-funnel -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .github/skills && cp -r skills-src/codex-skills/industry-funnel .github/skills/industry-funnel && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "industry-funnel" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/industry-funnel into .github/skills/industry-funnel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "industry-funnel", 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 xbtlin/ai-berkshire --skill industry-funnel -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install xbtlin/ai-berkshire industry-funnel --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/codex-skills/industry-funnel .opencode/skills/industry-funnel && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "industry-funnel" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/industry-funnel into .opencode/skills/industry-funnel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "industry-funnel", 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.
Facts
- Skill name
industry-funnel- GitHub stars
- 17k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 586 words
- Files
- 1
- Skills in repo
- 22
- Repo updated
- First seen
- Licence
- MIT
At a glance
Runs a layered value-investing screen on an industry or theme, narrowing from a 30-to-60 company market scan down to 3 final candidates with documented elimination reasons at each layer.
- Works in 4 steps: 不遗漏任何重要标的（含 A 股、港股、美股、未上市候选） → 用统一标准过滤掉"故事股"和质量不足的公司 → 把精力聚焦到真正值得深度研究的 3 家头部 → …
- Screening a sector for a handful of value-investing candidates
- SKILL.md covers Codex adapter note, 适用场景, 漏斗结构总览 and 第一步：全市场扫描入口, plus 7 more sections
- Calls python3
What it does
Given an industry or direction, this Chinese-language skill scans the full market (A-shares, Hong Kong, US and unlisted candidates) for active stocks by three criteria: trading activity (top 30 by average daily turnover per market), price momentum (top 20 gainers over 30 and 90 days) and market-cap anchoring (top 30 by market cap regardless of performance), unioned into an expected pool of 30 to 60 names. It explicitly warns not to drop Chinese or Asian names for lack of English coverage and not to drop small-cap names out of a bias toward sector leaders.
From there the funnel narrows in further layers using five hard value-investing metrics and a moat-strength filter, continuing down to a final shortlist of 3 companies for deep research. Every eliminated candidate at every layer must keep its elimination reason recorded rather than disappearing silently. The skill is distinguished from a sibling industry-research skill, which maps the industry's chain and landscape rather than screening individual stocks; the two are meant to be used together.
A Codex adapter note at the top explains that the skill is generated from a shared canonical markdown source so Claude Code and Codex users follow one workflow, substituting the closest available capability (subagent, web search, shell command) for any Claude-specific tool the source mentions, and instructs running the date command first so research is dated against the actual current date rather than assumed from training data.
When your agent uses it
- Screening a sector for a handful of value-investing candidates
- Narrowing a long list of industry stocks to a few worth deep research
- Scanning A-share, Hong Kong and US markets together for one industry theme
Example prompts
- “对 AI 算力行业执行漏斗式筛选，给我最终 3 家候选。”
- “Run the industry funnel on robotics stocks across A-shares, Hong Kong and the US.”
- “筛选创新药行业，从全市场扫描到 3 家终选标的。”
Requirements
- Shared project tools under tools/, such as tools/financial_rigor.py
- The AGENTS.md research quality rules in the repository
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- 不遗漏任何重要标的（含 A 股、港股、美股、未上市候选）
- 用统一标准过滤掉"故事股"和质量不足的公司
- 把精力聚焦到真正值得深度研究的 3 家头部
- 每层有明确的留/弃标准，可复盘可追溯
What it can do on your machine
Read from SKILL.md and the folder at commit a221a20. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Industry Value-Investing Funnel loads about 1.6k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 586 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.
Safety
Auto-check passed
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from xbtlin/ai-berkshire at commit a221a20, republished under its MIT licence (© xbtlin). 586 words, ~1,625 tokens.
Download SKILL.mdSave it as
.claude/skills/industry-funnel/SKILL.md (or your agent's skills folder).- name
- industry-funnel
- description
- AI Berkshire skill: 行业漏斗筛选：从全市场到 3 家的价值投资精选流程. Source: skills/industry-funnel.md.
Codex adapter note
This skill is generated from skills/industry-funnel.md so Claude Code and Codex users share one canonical workflow.
- Treat
$ARGUMENTSas the user's request in the current Codex thread. - When the source mentions Claude-only surfaces such as Task, Agent, WebSearch, Bash, Read, or Write, use the closest Codex capability available in this session: subagents when available, web search when needed, shell commands for local tools, and normal file edits for workspace files.
- Use shared project tools from
tools/in this repository. Prefer running commands from the repository root with paths likepython3 tools/financial_rigor.py ...; if the current thread starts outside the repo, locate the actual checkout path first instead of assuming a fixed home-directory path. - Before starting research, run the
datecommand to confirm today's date; treat it as the baseline for "latest" data and state the data cutoff date in the report header. Never assume the current date from training data. - Preserve the research quality rules from
AGENTS.md: cross-check financial data, use exact arithmetic tools for valuation/math, and clearly label uncertainty and source gaps.
行业漏斗筛选：从全市场到 3 家的价值投资精选流程
对 $ARGUMENTS 行业/方向执行漏斗式价值投资筛选，从全市场扫描逐层精选到 3 家终选标的。
适用场景
当你说出一个行业或投资方向（如"AI 算力"、"创新药"、"机器人"），想要：
- 不遗漏任何重要标的（含 A 股、港股、美股、未上市候选）
- 用统一标准过滤掉"故事股"和质量不足的公司
- 把精力聚焦到真正值得深度研究的 3 家头部
- 每层有明确的留/弃标准，可复盘可追溯
与 industry-research 的区别：
industry-research偏重产业链结构与全景，环节切片industry-funnel偏重个股筛选漏斗，从全市场逐层精选到 3 家
两者可以互补：先用 industry-research 看清产业链格局，再用 industry-funnel 精选标的。
漏斗结构总览
第一层：全市场扫描 30-60 家 （活跃度+涨幅+市值前 30 的并集）
↓ 价值投资 5 条硬指标
第二层：粗筛 ≤ 10 家 （5 条全部及格 + 护城河 ★★★ 以上）
↓ 精细分析
第三层：精细分析 ≤ 10 家 （每家 300-500 字结构化分析）
↓ 终选
第四层：四大师深度分析 3 家 （每家 800-1200 字，巴芒段李四视角）
↓
输出：投资建议 + 操作信号 + 仓位建议每层"过滤掉的标的"必须留下淘汰理由，不能黑箱。
第一步：全市场扫描入口
1.1 活跃股票定义（三类并集）
A 类 - 成交活跃度：
- 近 30 天日均成交额排名行业前列（A 股/港股/美股各自取前 30）
B 类 - 涨幅榜：
- 近 30 天涨幅前 20
- 近 90 天涨幅前 20
- 两者并集
C 类 - 市值锚定：
- 行业内市值前 30（无论涨跌）
最终扫描池 = A ∪ B ∪ C，预期 30-60 家。
1.2 必须搜索的市场
| 市场 | 来源建议 |
|---|---|
| A 股（沪深） | 同花顺/东方财富行业板块、通达信 |
| 港股 | 富途/同花顺港股、HKEX 行业分类 |
| 美股 | NASDAQ/NYSE 行业 ETF 持仓、Yahoo Finance |
| 国际市场 | 日韩台欧的相关公司不能漏（特别是半导体、电子） |
| 未上市公司 | 单列"未来 IPO 候选"小节，注明最新估值与潜在 IPO 时间 |
1.3 输出格式
| 公司名 | 代码 | 市场 | 市值 | 主业一句话 | 该行业占比 | 入选类别(A/B/C) |
|---|
关键自查：
- 行业占比 < 30% 的"沾边股"要谨慎，标注"非纯正标的"
- 中国/亚洲市场不要因英文资料少而漏掉
- 小市值公司不要因为 AI 偏好龙头而漏
第二步：价值投资 5 条硬指标粗筛 → ≤ 10 家
对第一步的 30-60 家公司，逐家应用 5 条硬指标。
2.1 5 条硬指标
| # | 指标 | 通过标准 | 放宽条件 | 数据来源 |
|---|---|---|---|---|
| 1 | PE 估值 | 合理（与历史区间、同业对比） | 高成长可放宽到 PEG < 1.5 | 财报+wind/同花顺 |
| 2 | ROE | > 15% 或近 3 年趋势改善 | 重资产行业可放宽 | 财报 |
| 3 | 经营现金流 | 为正且占净利润 > 70% | — | 财报 |
| 4 | 资产负债率 | < 60% | 公用事业/电力可放宽至 70% | 财报 |
| 5 | 护城河快评 | ★★★ 以上 | — | 定性判断 |
护城河 5 类：
- 品牌/定价权
- 转换成本/用户黏性
- 网络效应
- 规模效应
- 技术/牌照/资源壁垒
Show full SKILL.md (241 more words)Show less
2.2 输出格式
| 公司 | PE | ROE | 现金流/净利 | 负债率 | 护城河 | 综合 | 留/弃 | 淘汰理由 |
|---|
保留规则：
- 5 条全部及格 → 直接保留
- 4 条及格 + 1 条接近 → 保留但标黄
- 不足 4 条 → 淘汰，注明理由
目标：保留 ≤ 10 家。如果保留过多（> 12），把护城河标准提到 ★★★★ 再筛一次。
第三步：精细分析（≤ 10 家，每家 300-500 字）
对粗筛保留的公司，逐家做结构化分析。
3.1 每家公司分析模板
## {公司名}（{代码}）
**一句话商业模式**：
（卖什么、卖给谁、怎么收钱）
**财务质量**：
- 收入增速 / 利润增速 / 毛利率 / ROE / 现金流
- 关键变化（近 1-2 年最重要的财务转折点）
**护城河深度**：
- 主要护城河类型 + 具体证据
- 护城河 5 年后是否还在的简要判断
**主要风险（前 3）**：
1.
2.
3.
**估值快评**：
- 当前 PE/PS/EV/EBITDA + 历史区间位置
- 同业对比
- 一句话结论：贵 / 合理 / 便宜
**进入终选 3 家？**：是 / 否（理由）3.2 终选 3 家的选择标准
不是按打分排序选前 3，而是按"投资组合互补性"选：
- 至少 1 家"高确定性低弹性"（巴菲特型）
- 至少 1 家"中等确定性中等弹性"（成长型）
- 可选 1 家"高弹性高风险"（期权型）
如果某子赛道找不到 3 家足够好的，宁可写"终选 2 家 + 1 家观察"，不要凑数。
第四步：四大师深度分析（3 家，每家 800-1200 字）
对终选 3 家执行四大师视角深度分析。
4.1 段永平视角：生意本质
- 一句话定义这家公司在做什么生意
- 这是好生意吗？为什么？
- 它的"本分"是什么？管理层有没有偏离？
- 商业模式的"持续性"在哪？
4.2 巴菲特视角：护城河深度
- 用五类护城河打分（★1-5），列具体证据
- 10 年后护城河还在吗？
- 现在买入的"安全边际"在哪？
| 护城河 | 强度 | 具体证据 |
|---|---|---|
| 品牌/定价权 | ||
| 转换成本 | ||
| 网络效应 | ||
| 规模效应 | ||
| 技术/牌照壁垒 |
4.3 芒格视角：风险与失败模式
- 这家公司最可能怎么失败？（列出前 3 失败路径）
- 最坏情景下值多少钱？（极简估值）
- 聪明人为什么不买？（反向论证）
- 是否有道德/合规/管理层风险？
4.4 李录视角：文明级趋势定位
- 这家公司所在的赛道是"文明级范式转移"还是"阶段性热潮"？
- 历史上最接近的技术革命类比？
- 10-20 年后这家公司的终局？
- 是不是赢家通吃格局？
4.5 综合推荐度
推荐度：★★★★☆
仓位类型：核心 / 卫星 / 期权 / 观察
建议买入区间：当前价 / 回调 N% / 有耐心等待
建议持仓比例：占该主题仓位 X%
关键监测指标：（这家公司逻辑一旦反转的信号是什么）第五步：综合输出
报告末尾整合：
5.1 终选 3 家组合表
| 公司 | 类型 | 推荐度 | 建议仓位 | 核心逻辑 | 关键风险 |
|---|---|---|---|---|---|
| A | 核心 | ★★★★★ | 50-60% | ||
| B | 卫星 | ★★★★☆ | 25-35% | ||
| C | 期权 | ★★★☆☆ | 5-15% |
5.2 行业级 ETF 替代
如果不想选股，列 1-3 个相关 ETF（A 股/港股/美股）。
5.3 整体行业位置判断
- 行业 PE/PB 历史分位
- 资金流向（北向、ETF 申赎、卖方覆盖密度）
- 整体处于"早期/扩张/成熟/衰退"哪个阶段
5.4 信息充分度自评（必填）
| 维度 | 等级 | 说明 |
|---|---|---|
| 公司财务数据完整性 | A/B/C | |
| 估值数据时效性 | A/B/C | |
| 行业格局判断 | A/B/C | |
| 管理层信息 | A/B/C |
A = 数据充分可信；B = 部分缺失但不影响主结论；C = 缺失较多，结论需谨慎。
5.5 待更新数据点
明确列出：哪些数据是估计值、哪些数据需要后续核实、哪个季度财报需要重点跟踪。
5.6 资料来源清单
每个数据/结论的来源链接，分类列出（财报、研报、新闻、行业报告）。
AI 研究偏见自觉（重要）
漏斗筛选过程中，AI 容易踩的坑：
| 偏见 | 表现 | 应对 |
|---|---|---|
| 龙头偏好 | 大市值公司资料多、分析篇幅长，看起来"更好" | 按硬指标和护城河打分，不按报告篇幅排序 |
| 英文偏好 | 美股资料丰富，A 股港股容易被低估 | 必须中英文都搜，A/H 公司不能漏 |
| 故事偏好 | 高涨幅 + 媒体热度 = 看起来更好的"AI 概念股" | 区分"AI 收入占比" vs "AI 故事占比"，看真实业务 |
| 当下偏好 | 当前财务好的公司容易入选，可能错过转型期黑马 | 第二层粗筛允许"趋势改善"作为放宽条件 |
| 上市偏好 | 只看上市公司可能错过赛道最好的玩家 | 必须列"未来 IPO 候选"，标注估值与时间窗 |
输出要求
- 报告位置：
reports/{行业名}-funnel-{YYYYMMDD}.md（行业报告放 reports/ 根目录） - 语言：中文
- 风格：直接、犀利、不说废话
- 数据：所有数据标注来源；估计值标"估计"
- 不预设立场：先摆数据 → 推逻辑 → 出结论
- 正反两面：每个核心判断附反面论据
- 每层留淘汰记录：被淘汰的公司也要留名字+理由
数据抽检（准出流程）
报告写入后，执行数据抽检，通过方可发布：
# Step 1 — 提取抽检清单（15% 随机抽样）
python3 tools/report_audit.py extract \
--report <报告文件路径>
# Step 2 — 对清单每项从可靠信源取数（参见 skills/financial-data.md）
# Step 3 — 输出准出/打回判决
python3 tools/report_audit.py verdict \
--results '<填好的JSON>' \
--report <报告文件名>【准出】 全部通过 → 报告可发布；【打回】 有不通过 → 修正后重审。
后续动作
漏斗终选 3 家后，对每家可单独执行：
/investment-team—— 完整四大师并行深度研究（独立子目录 + 5 文档）/investment-checklist—— 巴菲特买入前 checklist 系统过一遍/management-deep-dive—— 管理层纵深研究
industry-funnel 是入口，后续 skill 是深挖。
© xbtlin, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in codex-skills/industry-funnel of xbtlin/ai-berkshire.
Open the folder on GitHubat commit a221a20
Compare with similar skills
Industry Value-Investing Funnel 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 |
|---|---|---|---|---|---|---|
| Industry Value-Investing Funnel this skillxbtlin/ai-berkshire | 17k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Stock APIzhangxiangliang/stock-api | 2k | — | ~507 | Automated safety check: Pass | MIT | |
| Tushare Datazillionare/zillionare | 321 | 2 repos | ~2.3k | Automated safety check: Pass | None | |
| Tradingview MCPatilaahmettaner/tradingview-mcp | 5k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Digital Oraclekomako-workshop/digital-oracle | 878 | — | ~5.9k | Automated safety check: Pass | MIT | |
| Longbridge Researchhelsome/folio | 271 | 3 repos | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
Tushare Data
zillionare/zillionare
面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求，转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。
Tradingview MCP
atilaahmettaner/tradingview-mcp
AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs, equity curves, licensed news sentiment (Marketaux), and…
Digital Oracle
komako-workshop/digital-oracle
Answer prediction questions using market trading data, not opinions.
Longbridge Research
helsome/folio
Institution ratings, consensus price targets, EPS/revenue forecasts, finance calendar, shareholder data, fund holders, insider trades (SEC Form 4), short interest, industry rankings, peer group…
Longbridge Earnings
helsome/folio
Earnings analysis — pre- and post-earnings. An agent skill from helsome/folio.
More from xbtlin/ai-berkshire
All 22 skills in this repoSupply Chain Bottleneck Hunter
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.
Deep Company Article Series
xbtlin/ai-berkshire
Plans and writes a three-to-eight-part long-form article series that breaks down one company, built on fact-checked financials, valuation and management analysis.
Earnings Report Deep Reading
xbtlin/ai-berkshire
Reads a company's filings and earnings call material in depth, rates how complete the sources are and extracts the key figures into a structured review.
Earnings Report Deep-Read Team
xbtlin/ai-berkshire
Runs four parallel analyst personas over one earnings report, then an editor and reader-review pass turn the findings into a publishable article.
Era Alpha Investment Research Framework
xbtlin/ai-berkshire
A four-step research framework for finding and tracking high-growth core companies in one industry: map the sector, ask core questions, verify, then hold to the turning point.
Financial Data Cross-Validation
xbtlin/ai-berkshire
A research rule set for pulling company financials from prioritized sources by market and cross-checking every key figure against two independent sources.
Related
Categories
Questions about Industry Value-Investing Funnel
What does Industry Value-Investing Funnel do?
Runs a layered value-investing screen on an industry or theme, narrowing from a 30-to-60 company market scan down to 3 final candidates with documented elimination reasons at each layer. Given an industry or direction, this Chinese-language skill scans the full market (A-shares, Hong Kong, US and unlisted candidates) for active stocks by three criteria: trading activity (top 30 by average daily turnover per market), price momentum (top 20 gainers over 30 and 90 days) and market-cap anchoring (top 30 by market cap regardless of performance), unioned into an expected pool of 30 to 60 names. It explicitly warns not to drop Chinese or Asian names for lack of English coverage and not to drop small-cap names out of a bias toward sector leaders.
When should I use Industry Value-Investing Funnel?
Industry Value-Investing Funnel fits situations like: screening a sector for a handful of value-investing candidates; narrowing a long list of industry stocks to a few worth deep research; scanning A-share, Hong Kong and US markets together for one industry theme.
How do I install Industry Value-Investing Funnel in Claude Code?
Run `npx skills add xbtlin/ai-berkshire --skill industry-funnel -a claude-code`. Or copy the skill folder (codex-skills/industry-funnel in xbtlin/ai-berkshire) into .claude/skills/industry-funnel in your project. Claude Code loads it when a task matches its description.
How do I install Industry Value-Investing Funnel in Codex?
Run `npx skills add xbtlin/ai-berkshire --skill industry-funnel -a codex`. Or copy the skill folder (codex-skills/industry-funnel in xbtlin/ai-berkshire) into .agents/skills/industry-funnel in your project. Codex loads it when a task matches its description.
Can I use Industry Value-Investing Funnel in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xbtlin/ai-berkshire --skill industry-funnel -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/industry-funnel, .gemini/skills/industry-funnel, .github/skills/industry-funnel and .opencode/skills/industry-funnel in your project.
What does Industry Value-Investing Funnel need to run?
Going by SKILL.md and its folder, Industry Value-Investing Funnel needs the command-line tools its instructions call (python3). Our summary lists: Shared project tools under tools/, such as tools/financial_rigor.py; The AGENTS.md research quality rules in the repository.
Does Industry Value-Investing Funnel access the network?
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.
Is Industry Value-Investing Funnel safe to install?
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. Review the folder before installing.
What licence does Industry Value-Investing Funnel use?
Industry Value-Investing Funnel is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Industry Value-Investing Funnel use?
About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Industry Value-Investing Funnel?
Skills that share tags, products or a category with Industry Value-Investing Funnel: Stock API (zhangxiangliang/stock-api, 2k stars), Tushare Data (zillionare/zillionare, 321 stars), Tradingview MCP (atilaahmettaner/tradingview-mcp, 5k stars) and Digital Oracle (komako-workshop/digital-oracle, 878 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Industry Value-Investing Funnel?
xbtlin (a GitHub user) maintains it in xbtlin/ai-berkshire, which has 16,676 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 8, 2026.
Source: xbtlin/ai-berkshire on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.