Back to Details

longbridge-graham-screener

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

longbridge-graham-screener

Longbridge格雷厄姆烟蒂股批量筛选器

Prompt-only batch screener. Given a market or index universe, applies Graham's six hard filters (NCAV, PE, PB, dividend yield, debt coverage, earnings stability), scores each name on a 100-point static + dynamic composite, and returns a ranked cigar-butt candidate list with Graham buy lines, holding-period expectation, and value-trap warnings.
Response language: match the user's input language — Simplified Chinese / Traditional Chinese / English.
仅基于提示词的批量筛选器。针对指定市场或指数标的池，应用格雷厄姆的六项严格筛选规则（NCAV、PE、PB、股息率、偿债能力、盈利稳定性），以100分制的静态+动态综合指标对每个标的评分，返回包含格雷厄姆买入价、持有周期预期及价值陷阱预警的烟蒂股候选榜单。
回复语言：匹配用户输入语言——简体中文 / 繁体中文 / 英文。

When to use

使用场景

  • "港股里现在有没有 NCAV<1 的股票" / "港股裡現在有沒有 NCAV<1 的股票" / "any HK stocks with NCAV < 1"
  • "给我 A 股 PE 最低的 20 只股票，格雷厄姆标准" / "給我 A 股 PE 最低的 20 隻股票，格雷厄姆標準" / "top 20 lowest-PE A-shares by Graham standard"
  • "帮我筛一下符合格雷厄姆防御型投资者条件的美股" / "幫我篩一下符合格雷厄姆防禦型投資者條件的美股" / "screen US stocks meeting Graham defensive-investor rules"
  • "沪深300里的烟蒂股" / "滬深300裡的煙蒂股" / "cigar-butt names in CSI 300"
  • "每周更新港股 NCAV 排行榜" / "每週更新港股 NCAV 排行榜" / "weekly HK NCAV leaderboard"
For single-stock deep diagnostic use 
longbridge-graham-stock-analysis
. For broader low-PE / low-PB / high-ROE value (not NCAV-centric) use 
longbridge-value-screen
. For high-dividend-only screens use 
longbridge-dividend-screen
.
  • "港股里现在有没有 NCAV<1 的股票" / "港股裡現在有沒有 NCAV<1 的股票" / "any HK stocks with NCAV < 1"
  • "给我 A 股 PE 最低的 20 只股票，格雷厄姆标准" / "給我 A 股 PE 最低的 20 隻股票，格雷厄姆標準" / "top 20 lowest-PE A-shares by Graham standard"
  • "帮我筛一下符合格雷厄姆防御型投资者条件的美股" / "幫我篩一下符合格雷厄姆防禦型投資者條件的美股" / "screen US stocks meeting Graham defensive-investor rules"
  • "沪深300里的烟蒂股" / "滬深300裡的煙蒂股" / "cigar-butt names in CSI 300"
  • "每周更新港股 NCAV 排行榜" / "每週更新港股 NCAV 排行榜" / "weekly HK NCAV leaderboard"
如需单股深度诊断，请使用 
longbridge-graham-stock-analysis
。如需更广泛的低PE/低PB/高ROE价值股筛选（非NCAV核心），请使用 
longbridge-value-screen
。如需仅高股息筛选，请使用 
longbridge-dividend-screen
。

Cognitive frame (do not skip)

认知框架（请勿跳过）

Graham screening is patient arbitrage, not a dip-buy signal. Hold periods: 6–18 months (explicit catalyst), 1–3 years (sector re-rating), 3–5 years (organic accrual), or never (value trap — exit). Every ranking output must carry the waiting-cost (dividend yield) and the holding-period framing; never display a score number on its own.
Two failure modes the user must be able to distinguish — and the screener must signal:
  • "Cheap but time hasn't come" → NCAV stable QoQ, keep on the list.
  • "Value trap" → NCAV shrinking ≥3 quarters, persistent insider selling, negative OCF, PMI persistently <50, AR growth outpacing revenue. Override to ⚠️ regardless of static score.
格雷厄姆筛选是耐心套利，而非抄底信号。持有周期：6–18个月（明确催化剂）、1–3年（行业重估）、3–5年（自然增值），或永不持有（价值陷阱——卖出）。所有排名输出必须包含等待成本（股息率）及持有周期说明；不得单独展示评分数字。
用户必须能够区分两种失败模式，筛选器必须发出信号：
  • 「价格低廉但时机未到」 → NCAV季度环比稳定，保留在榜单中。
  • 「价值陷阱」 → NCAV连续≥3个季度缩水、持续内部人抛售、经营现金流为负、PMI持续<50、应收账款增长超过营收增长。无论静态评分如何，均标记为⚠️。

Workflow

工作流程

  1. Confirm market + universe. Ask the user for: (a) market — HK / US / A-share, (b) screening pool — single index (HSI, S&P 500, CSI 300, NDX, etc.) or a watchlist. Default batch ceiling: 300 names per run.
  2. Fetch constituent list for the chosen index (or watchlist) — see §CLI.
  3. Sector pre-classification: exclude banks / insurance / REITs / pure financials / negative-equity / pure-holding shells from the universe before scoring — NCAV does not apply to balance sheets dominated by financial assets, so these are removed, not run through a substitute model. Count the exclusion in the Market Summary "Excluded — NCAV inapplicable" line. Separately, flag IPOs < 2 years (pro-rata earnings-stability sub-score, noted in row) and suspended names (last-trade snapshot, prepend ⏸).
  4. Batch-fetch fundamentals in parallel (≤20 symbols per wave): balance sheet (annual + last 4Q), income statement (5y annual + 4Q quarterly), cash flow (4Q quarterly), 
    calc-index
    + 
    quote
    snapshot, 
    dividend
    , 
    ownership
    .
  5. Apply hard filters with user-overridable thresholds — see §Filters.
  6. Score each candidate — static (0–100) + dynamic adjustments + value-trap override. See 
    references/criteria.md
    .
  7. Reconciliation gate per row: if balance-sheet sum / current-assets sum / shares×price mismatches the reported total by >3%, drop the row from the leaderboard with a "data anomaly" note (do not silently average).
  8. Rank by adjusted score (descending); default top 10–20 returned. Emit the table + market summary + waiting-cost note + suggested next step.
  9. Append a Data Source Appendix (mandatory) listing every Longbridge endpoint hit, every WebSearch hit (publisher + URL + access date), fetch timestamps, and any field substitutions.
  10. End every output with the recommendation: «本筛选器仅静态硬指标 + 通用动态因子，未考虑公司层面主观估值陷阱。命中候选请用 
    longbridge-graham-stock-analysis
    做单股深度诊断。»
  1. 确认市场+标的池。向用户确认：(a) 市场——港股/美股/A股，(b) 筛选池——单一指数（如恒生指数HSI、标普500 S&P 500、沪深300 CSI 300、纳斯达克100 NDX等）或自选股列表。默认单次运行上限：300个标的。
  2. 获取所选指数（或自选股）的成分股列表——参见§CLI。
  3. 行业预分类：在评分前排除银行/保险/REITs/纯金融类/负权益/纯控股壳公司——NCAV不适用于以金融资产为主的资产负债表，因此这些标的将被移除，不使用替代模型运行。在市场摘要的「排除——NCAV不适用」项中统计排除数量。另外，标记上市不足2年的IPO（盈利稳定性子评分按可用年份折算，在行中注明）及停牌标的（最新交易快照，前缀添加⏸）。
  4. 并行批量获取基本面数据（每批≤20个标的）：资产负债表（年度+最近4季度）、利润表（5年年度+4季度季度数据）、现金流量表（4季度季度数据）、
    calc-index
    + 
    quote
    快照、
    dividend
    、
    ownership
    。
  5. 应用严格筛选规则，阈值可由用户覆盖——参见§筛选规则。
  6. 为每个候选标的评分——静态评分（0–100）+动态调整+价值陷阱覆盖。详见
    references/criteria.md
    。
  7. 逐行核对校验：若资产负债表总和/流动资产总和/股价×股份数与报告总额差异超过3%，则将该行从榜单中移除，并标注「数据异常」说明（不得默默取平均值）。
  8. 按调整后评分降序排名；默认返回前10–20个标的。输出表格+市场摘要+等待成本说明+下一步建议。
  9. 添加数据源附录（必填），列出所有调用的Longbridge接口、所有WebSearch结果（发布商+URL+访问日期）、获取时间戳及任何字段替换情况。
  10. 所有输出结尾必须包含推荐语：«本筛选器仅基于静态硬指标+通用动态因子，未考虑公司层面主观估值陷阱。命中候选请用 
    longbridge-graham-stock-analysis
    做单股深度诊断。»

CLI

CLI

Run 
longbridge <subcommand> --help
to verify exact flags before each call — the CLI is the source of truth, do not hard-code flag spellings from memory.
bash
undefined
每次调用前运行 
longbridge <subcommand> --help
验证准确参数——CLI为权威来源，请勿凭记忆硬编码参数拼写。
bash
undefined

Universe

标的池

longbridge constituent <INDEX> --format json # e.g. 000300.SH, HSI.HK, SPX.US
longbridge constituent <INDEX> --format json # 示例：000300.SH, HSI.HK, SPX.US

Per-symbol snapshot (run in parallel, batches of ≤20)

单标的快照（并行运行，每批≤20个）

longbridge calc-index <SYMBOL> --format json # PE / PB / market cap / ROE / dividend yield longbridge quote <SYMBOL> --format json # current price + suspended flag longbridge dividend <SYMBOL> --format json # TTM dividend (waiting-cost)
longbridge calc-index <SYMBOL> --format json # PE / PB / 市值 / ROE / 股息率 longbridge quote <SYMBOL> --format json # 当前价格 + 停牌标记 longbridge dividend <SYMBOL> --format json # TTM股息（等待成本）

Per-symbol fundamentals (run in parallel)

单标的基本面数据（并行运行）

longbridge financial-report <SYMBOL> --kind BS --report af --format json # 5y annual BS → NCAV longbridge financial-statement <SYMBOL> --kind BS --report qf --format json # last 4Q BS → NCAV trajectory longbridge financial-report <SYMBOL> --kind IS --report af --format json # 5y annual IS → earnings stability longbridge financial-report <SYMBOL> --kind CF --report qf --format json # 4Q CF → OCF rule
longbridge financial-report <SYMBOL> --kind BS --report af --format json # 5年年度资产负债表 → NCAV计算 longbridge financial-statement <SYMBOL> --kind BS --report qf --format json # 最近4季度资产负债表 → NCAV趋势 longbridge financial-report <SYMBOL> --kind IS --report af --format json # 5年年度利润表 → 盈利稳定性 longbridge financial-report <SYMBOL> --kind CF --report qf --format json # 4季度现金流量表 → 经营现金流规则

Insider / institutional flow (value-trap rule 2)

内部人/机构资金流向（价值陷阱规则2）

longbridge ownership <SYMBOL> --format json longbridge insresearch <SYMBOL> --format json
undefined
longbridge ownership <SYMBOL> --format json longbridge insresearch <SYMBOL> --format json
undefined

WebSearch fallback (use only when Longbridge has the gap)

WebSearch fallback（仅当Longbridge存在数据缺口时使用）

Missing inputWebSearch query pattern
Industry PMI / inventory cycle
"<industry> PMI <year>"
, 
"中国制造业 PMI <month>"
, 
"<industry> inventory cycle <year>"
Capacity utilisation
"<industry> capacity utilization <year>"
Sector outlook (qualitative)
"<sector> outlook <year> site:reuters.com OR site:bloomberg.com OR site:wsj.com"
Recent insider transactions (if 
ownership
is stale)
"<ticker> insider selling <year>"
, 
"<公司> 大股东减持 <month>"
Each WebSearch-sourced figure must be tagged with publisher + URL + access date in the Data Source Appendix; never silently mix it into a Longbridge column.
缺失输入WebSearch查询模式
行业PMI/库存周期
"<industry> PMI <year>"
, 
"中国制造业 PMI <month>"
, 
"<industry> inventory cycle <year>"
产能利用率
"<industry> capacity utilization <year>"
行业展望（定性）
"<sector> outlook <year> site:reuters.com OR site:bloomberg.com OR site:wsj.com"
近期内部人交易（若
ownership
数据过时）
"<ticker> insider selling <year>"
, 
"<公司> 大股东减持 <month>"
每个WebSearch来源的数据必须在数据源附录中标注发布商+URL+访问日期；不得直接混入Longbridge数据列中。

Filters

筛选规则

User-overridable. Defaults from Graham's Intelligent Investor with light modernisation; threshold detail and the composite scoring weights live in 
references/criteria.md
.
FilterGraham thresholdNotes
NCAV ratio (market cap ÷ haircut NCAV)< 1.0 ideal, < 1.5 acceptableCore. Haircut: cash 100% / AR 75% / inventory 50% / other CA 25% / liabilities 100%
PE (TTM)< 10 (defensive)Rolling TTM
PB< 1.5—
Dividend yield (TTM)> 3%Waiting-cost compensation
Current assets ÷ total liabilities> 2.0Debt safety
Consecutive no-loss years≥ 5Earnings stability
Dynamic warning statenone triggeredOptional pre-filter; defaults to "show but flag"
Default rank key = adjusted cigar-butt score (static composite + dynamic adjustments + value-trap override). The user can override the rank key to: static-only, NCAV ratio asc, PE asc, dividend yield desc.
可由用户覆盖阈值。默认值基于格雷厄姆《聪明的投资者》并结合现代市场轻微调整；阈值细节及综合评分权重详见
references/criteria.md
。
筛选规则格雷厄姆阈值说明
NCAV比率（市值÷调整后NCAV）理想值<1.0，可接受值<1.5核心规则。调整方式：现金100%/应收账款75%/存货50%/其他流动资产25%/负债100%
PE（TTM）<10（防御型）滚动TTM数据
PB<1.5—
股息率（TTM）>3%等待成本补偿
流动资产÷总负债>2.0偿债安全
连续无亏损年份≥5盈利稳定性
动态预警状态无触发可选预筛选；默认「展示但标记」
默认排名依据=调整后烟蒂股评分（静态综合评分+动态调整+价值陷阱覆盖）。用户可覆盖排名依据为：仅静态评分、NCAV比率升序、PE升序、股息率降序。

Special handling

特殊处理

CohortTreatment
Banks / insurance / REITs / pure financials / negative-equity / pure-holding shellsExcluded — NCAV is not a valid valuation lens for these business models. No substitute model is run; the symbols are dropped from the universe before scoring and counted in the Market Summary "Excluded — NCAV inapplicable" line. If the user wants these analysed, point them to 
longbridge-valuation-methodology
or 
longbridge-valuation
.
IPOs listed < 2 yearsEarnings-stability sub-score pro-rated on available years. Mark row "数据局限".
Suspended stocksShow last-trade snapshot, prepend "⏸ 停牌" / "⏸ Suspended" to the name, exclude from default top-N (still listable on request).
Reconciliation fail >3%Drop from leaderboard; surface in a "数据异常待复核" footer list with the failing check named.
标的组处理方式
银行/保险/REITs/纯金融类/负权益/纯控股壳公司排除——NCAV对这些商业模式并非有效估值指标。不运行替代模型；这些标的在评分前从标的池中移除，并在市场摘要的「排除——NCAV不适用」项中统计。若用户希望分析此类标的，请引导至
longbridge-valuation-methodology
或
longbridge-valuation
。
上市不足2年的IPO盈利稳定性子评分按可用年份折算。在行中标记「数据局限」。
停牌股票展示最新交易快照，在名称前添加「⏸ 停牌」/「⏸ Suspended」，默认不纳入前N榜单（可按需列出）。
核对差异>3%从榜单中剔除，并在「数据异常待复核」页脚列表中列出失败项及差异。

Output

输出

Default leaderboard (top 10–20 rows). Full template, market-summary block, waiting-cost line, subscription hook, and the mandatory Data Source Appendix structure live in 
references/output.md
.
Minimum columns:
排名  代码  名称  静态评分  调整后评分  NCAV比率  PE  PB  股息率  Graham买入价  动态预警  数据局限
After the table, every output must include:
  1. Market summary — universe size, hard-filter pass count, dynamic-clean count.
  2. Waiting-cost line — average dividend yield of the top-N; the «持有等待期间每年可获约 X% 股息回报作为补偿» line.
  3. Next-step recommendation — point users to 
    longbridge-graham-stock-analysis
    for any name they want to act on (筛选器未考虑主观估值陷阱因素).
  4. Data Source Appendix — mandatory; every field, every Longbridge endpoint, every WebSearch hit (publisher + URL + date).
  5. Disclaimer — full trilingual disclaimer from 
    references/output.md
    .
默认榜单（前10–20行）。完整模板、市场摘要块、等待成本说明、订阅钩子及必填数据源附录结构详见
references/output.md
。
最小列数：
排名  代码  名称  静态评分  调整后评分  NCAV比率  PE  PB  股息率  Graham买入价  动态预警  数据局限
表格之后，所有输出必须包含：
  1. 市场摘要——标的池规模、通过严格筛选的数量、通过动态校验的数量。
  2. 等待成本说明——前N标的的平均股息率；«持有等待期间每年可获约X%股息回报作为补偿»。
  3. 下一步建议——引导用户对任何拟操作的标的使用
    longbridge-graham-stock-analysis
    （筛选器未考虑主观估值陷阱因素）。
  4. 数据源附录——必填；每个字段、每个Longbridge接口、每个WebSearch结果（发布商+URL+日期）。
  5. 免责声明——来自
    references/output.md
    的完整三语免责声明。

Error handling

错误处理

Situation简体回复繁體回覆English reply
command not found: longbridge
回退到 MCP；若不可用，请安装 longbridge-terminal。回退到 MCP；若不可用，請安裝 longbridge-terminal。Fall back to MCP; if unavailable install longbridge-terminal.
stderr 
not logged in
/ 
unauthorized
请运行 
longbridge auth login
。		請執行 
longbridge auth login
。		Run 
longbridge auth login
.
constituent
returns empty		未能获取成分股，请确认指数代码（如 000300.SH / HSI.HK / SPX.US）。未能獲取成分股，請確認指數代碼（如 000300.SH / HSI.HK / SPX.US）。Cannot fetch constituents; verify index symbol (e.g. 000300.SH / HSI.HK / SPX.US).
BS / IS / CF partial fetch for a symbol该标的数据不完整，跳过并在「数据异常」脚注列出。該標的數據不完整，跳過並於「數據異常」腳註列出。Symbol has incomplete fundamentals; skipped and listed in the data-anomaly footer.
Industry-cycle data missing (Longbridge + WebSearch both empty)仅展示静态评分，动态层标注「数据不足」。僅展示靜態評分，動態層標註「數據不足」。Static score only; dynamic layer marked "unavailable".
Per-row reconciliation gap >3%从榜单剔除并在「数据异常」附录列出失败项及差异。自榜單剔除並於「數據異常」附錄列出失敗項及差異。Drop from leaderboard; list failing check + gap in data-anomaly appendix.
场景简体回复繁體回覆English reply
command not found: longbridge
回退到MCP；若不可用，请安装longbridge-terminal。回退到MCP；若不可用，請安裝longbridge-terminal。Fall back to MCP; if unavailable install longbridge-terminal.
stderr返回
not logged in
/ 
unauthorized
请运行 
longbridge auth login
。		請執行 
longbridge auth login
。		Run 
longbridge auth login
.
constituent
返回空		未能获取成分股，请确认指数代码（如000300.SH / HSI.HK / SPX.US）。未能獲取成分股，請確認指數代碼（如000300.SH / HSI.HK / SPX.US）。Cannot fetch constituents; verify index symbol (e.g. 000300.SH / HSI.HK / SPX.US).
某标的BS/IS/CF数据部分获取失败该标的数据不完整，跳过并在「数据异常」脚注列出。該標的數據不完整，跳過並於「數據異常」腳註列出。Symbol has incomplete fundamentals; skipped and listed in the data-anomaly footer.
行业周期数据缺失（Longbridge+WebSearch均无数据）仅展示静态评分，动态层标注「数据不足」。僅展示靜態評分，動態層標註「數據不足」。Static score only; dynamic layer marked "unavailable".
逐行核对差异>3%从榜单剔除并在「数据异常」附录列出失败项及差异。自榜單剔除並於「數據異常」附錄列出失敗項及差異。Drop from leaderboard; list failing check + gap in data-anomaly appendix.

MCP fallback

MCP fallback

If 
longbridge
CLI is not installed, use MCP tools:
MCP toolCLI equivalent
mcp__longbridge__constituent
longbridge constituent
mcp__longbridge__calc_indexes
longbridge calc-index
mcp__longbridge__quote
longbridge quote
mcp__longbridge__dividend
longbridge dividend
mcp__longbridge__financial_report
longbridge financial-report
mcp__longbridge__financial_statement
longbridge financial-statement
mcp__longbridge__ownership
longbridge ownership
mcp__longbridge__insresearch
longbridge insresearch
MCP setup: 
claude mcp add --transport http longbridge https://openapi.longbridge.com/mcp
(
quote
scope).
若未安装
longbridge
CLI，使用MCP工具：
MCP工具CLI等效命令
mcp__longbridge__constituent
longbridge constituent
mcp__longbridge__calc_indexes
longbridge calc-index
mcp__longbridge__quote
longbridge quote
mcp__longbridge__dividend
longbridge dividend
mcp__longbridge__financial_report
longbridge financial-report
mcp__longbridge__financial_statement
longbridge financial-statement
mcp__longbridge__ownership
longbridge ownership
mcp__longbridge__insresearch
longbridge insresearch
MCP设置：
claude mcp add --transport http longbridge https://openapi.longbridge.com/mcp
（需
quote
权限）。

Related skills

相关技能

  • Single-stock Graham diagnostic → 
    longbridge-graham-stock-analysis
  • Broader value (PE / PB / ROE) screen → 
    longbridge-value-screen
  • High-dividend screen → 
    longbridge-dividend-screen
  • DCF intrinsic value → 
    longbridge-dcf
  • Method selection guide → 
    longbridge-valuation-methodology
  • Three-statement reading → 
    longbridge-financial-report
  • 单股格雷厄姆诊断 → 
    longbridge-graham-stock-analysis
  • 广泛价值股（PE/PB/ROE）筛选 → 
    longbridge-value-screen
  • 高股息筛选 → 
    longbridge-dividend-screen
  • DCF内在价值计算 → 
    longbridge-dcf
  • 估值方法选择指南 → 
    longbridge-valuation-methodology
  • 三表解读 → 
    longbridge-financial-report

File layout

文件结构

longbridge-graham-screener/
├── SKILL.md
└── references/
    ├── criteria.md   # filter thresholds, six-dimension static scoring, dynamic adjustments, value-trap override, NCAV-inapplicable exclusions
    └── output.md     # full leaderboard template, market-summary block, data-source appendix, disclaimer
longbridge-graham-screener/
├── SKILL.md
└── references/
    ├── criteria.md   # 筛选阈值、六维度静态评分、动态调整、价值陷阱覆盖规则、NCAV不适用排除项
    └── output.md     # 完整榜单模板、市场摘要块、数据源附录、免责声明