Back to Details

longbridge-graham-stock-analysis

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

longbridge-graham-stock-analysis

longbridge-graham-stock-analysis

Prompt-only deep-value diagnostic. Given a single ticker, produces a Graham-style cigar-butt verdict: static cheapness score, dynamic trend adjustments, value-trap flagging, liquidation-value table, and an expected holding-period view. Every numeric input is reconciled across statements and footnoted to its source.
Response language: match the user's input language — Simplified Chinese / Traditional Chinese / English.
纯Prompt驱动的深度价值诊断工具。给定单只股票代码，生成格雷厄姆风格的烟蒂股诊断结果：静态便宜度评分、动态趋势调整、价值陷阱标记、清算价值表，以及预期持有周期建议。所有数值输入均经过跨报表勾稽校验，并标注来源。
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

  • "帮我诊断一下腾讯控股 00700" / "幫我診斷一下騰訊控股 00700" / "diagnose 700.HK with Graham cigar-butt"
  • "BABA 是不是烟蒂股" / "BABA 是不是煙蒂股" / "is BABA a Graham net-net"
  • "600519 NCAV 多少" / "600519 NCAV 多少" / "what is 600519's NCAV"
  • "我持有这只股 6 个月了，还值得继续拿吗" / "我持有這隻股 6 個月了，還值得繼續拿嗎" / "I've held this 6 months, still worth holding"
  • "这只股是真便宜还是价值陷阱" / "這隻股是真便宜還是價值陷阱" / "is this a real bargain or a value trap"
For multi-stock value screening use 
longbridge-value-screen
. For DCF intrinsic value use 
longbridge-dcf
. For three-statement reading use 
longbridge-financial-report
.
  • "帮我诊断一下腾讯控股 00700" / "幫我診斷一下騰訊控股 00700" / "diagnose 700.HK with Graham cigar-butt"
  • "BABA 是不是烟蒂股" / "BABA 是不是煙蒂股" / "is BABA a Graham net-net"
  • "600519 NCAV 多少" / "600519 NCAV 多少" / "what is 600519's NCAV"
  • "我持有这只股 6 个月了，还值得继续拿吗" / "我持有這隻股 6 個月了，還值得繼續拿嗎" / "I've held this 6 months, still worth holding"
  • "这只股是真便宜还是价值陷阱" / "這隻股是真便宜還是價值陷阱" / "is this a real bargain or a value trap"
如需多只股票的价值筛选，请使用
longbridge-value-screen
。如需DCF内在价值分析，请使用
longbridge-dcf
。如需三报表解读，请使用
longbridge-financial-report
。

Cognitive frame (do not skip)

认知框架（不可跳过）

Graham cigar-butt is patient arbitrage, not a dip-buy signal. Expected holding periods: 6–18 months (explicit catalyst), 1–3 years (sector re-rating), 3–5 years (organic accrual), or never (value trap — exit). Every output must surface holding-period expectation alongside the score; never display a score number without it.
Two failure modes the user must be able to distinguish:
  • "Cheap but time hasn't come" → NCAV stable, keep holding.
  • "Value trap" → NCAV shrinking quarter on quarter, exit.
格雷厄姆烟蒂股策略是耐心套利，而非抄底信号。预期持有周期：6–18个月（有明确催化剂）、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）。输出内容必须将持有周期预期与评分一同展示；绝对不能只显示评分数字而不附带周期建议。
用户必须能够区分两种失败模式：
  • "价格便宜但时机未到" → NCAV稳定，继续持有。
  • "价值陷阱" → NCAV逐季缩水，卖出。

Workflow

工作流程

  1. Resolve symbol to 
    <CODE>.<MARKET>
    (e.g. 
    00700.HK
    , 
    BABA.US
    , 
    600519.SH
    ).
  2. Detect sector. If banking / insurance / REIT / pure financial → halt and tell the user NCAV is not the right model; suggest 
    longbridge-valuation-methodology
    instead.
  3. Fetch raw data via Longbridge CLI first (parallel where possible). See §CLI.
  4. Reconciliation gate (勾稽校验) — internal correctness check; must pass before scoring. Do not print this check or its results in the report unless it fails. See §Reconciliation.
  5. Static score (0–100). See 
    references/scoring.md
    for the six-dimension table and NCAV haircut defaults.
  6. Dynamic adjustments — four factors (industry cycle, earnings trend, insider activity, NCAV trajectory). Industry-cycle data may not be in Longbridge; use WebSearch for PMI / inventory cycle / capacity utilisation. See 
    references/scoring.md
    §Dynamic.
  7. Value-trap check — if any 2 of 5 rules trip, override to "⚠️ value trap" regardless of static score. See 
    references/scoring.md
    §Value-trap.
  8. Output the 8-section report defined in 
    references/output.md
    ; finish with the Data source appendix (mandatory — every figure tagged to its source).
  1. 解析股票代码为
    <CODE>.<MARKET>
    格式（例如
    00700.HK
    、
    BABA.US
    、
    600519.SH
    ）。
  2. 检测行业。若为银行/保险/REIT/纯金融行业→终止分析，告知用户NCAV模型不适用；建议使用
    longbridge-valuation-methodology
    。
  3. 优先通过Longbridge CLI获取原始数据（尽可能并行获取）。详见§CLI。
  4. 勾稽校验 gate——内部正确性检查；必须通过后才能进行评分。除非检查失败，否则不要在报告中打印该检查或结果。详见§Reconciliation。
  5. 静态评分（0–100分）。六个维度的评分表及NCAV默认折扣规则详见
    references/scoring.md
    。
  6. 动态调整——四个因素（行业周期、盈利趋势、内幕交易活动、NCAV变动轨迹）。行业周期数据可能无法从Longbridge获取；使用WebSearch获取PMI/库存周期/产能利用率数据。详见
    references/scoring.md
    的动态调整部分。
  7. 价值陷阱检查——若5条规则中有任意2条触发，则无论静态评分如何，都标记为"⚠️ 价值陷阱"。详见
    references/scoring.md
    的价值陷阱部分。
  8. 输出
    references/output.md
    中定义的8部分报告；结尾必须附上数据源附录（强制要求——每个数据都标注来源）。

CLI

CLI

Run 
longbridge <subcommand> --help
to verify exact flags before each call. Primary calls (run in parallel):
bash
undefined
每次调用前运行
longbridge <subcommand> --help
确认准确参数。主要调用命令（并行运行）：
bash
undefined

Balance sheet — NCAV inputs (cash, AR, inventory, other CA, ST/LT debt)

资产负债表——NCAV相关数据（现金、应收账款、存货、其他流动资产、短期/长期负债）

longbridge financial-report <SYMBOL> --kind BS --report af --format json # last 5 annual longbridge financial-statement <SYMBOL> --kind BS --report qf --format json # last 4 quarterly (NCAV trajectory)
longbridge financial-report <SYMBOL> --kind BS --report af --format json # 最近5期年报 longbridge financial-statement <SYMBOL> --kind BS --report qf --format json # 最近4期季报（用于NCAV变动轨迹分析）

Income statement — PE, earnings stability (5y no-loss), EPS trend (4q)

利润表——市盈率（PE）、盈利稳定性（连续5年无亏损）、每股收益（EPS）趋势（最近4期季报）

longbridge financial-report <SYMBOL> --kind IS --report af --format json longbridge financial-report <SYMBOL> --kind IS --report qf --format json
longbridge financial-report <SYMBOL> --kind IS --report af --format json longbridge financial-report <SYMBOL> --kind IS --report qf --format json

Cash flow — operating CF (value-trap rule 4: persistent negative OCF)

现金流量表——经营活动现金流（价值陷阱规则4：持续负经营现金流）

longbridge financial-report <SYMBOL> --kind CF --report qf --format json
longbridge financial-report <SYMBOL> --kind CF --report qf --format json

Snapshot: PE, PB, market cap, dividend yield, shares outstanding

快照数据：市盈率（PE）、市净率（PB）、市值、股息率、已发行股份数

longbridge calc-index <SYMBOL> --format json longbridge quote <SYMBOL> --format json
longbridge calc-index <SYMBOL> --format json longbridge quote <SYMBOL> --format json

Dividend history (for "等待成本" — 3% threshold)

股息历史（用于计算「等待成本」——3%阈值）

longbridge dividend <SYMBOL> --format json
longbridge dividend <SYMBOL> --format json

Ownership / insider activity (value-trap rule 2: 大股东持续减持)

股权结构/内幕交易活动（价值陷阱规则2：大股东持续减持）

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

WebSearch fallback (only when Longbridge has a gap)

WebSearch fallback（仅当Longbridge数据存在缺口时使用）

Use WebSearch only for items not available from Longbridge:
Missing dataWebSearch query pattern
Industry PMI / inventory cycle
"<industry name> PMI 2025"
, 
"<industry> inventory cycle"
, 
"中国制造业PMI"
Capacity utilisation
"<industry> capacity utilization"
Sector outlook (qualitative)
"<sector> outlook 2025 site:reuters.com OR site:bloomberg.com"
Recent insider transactions if 
ownership
is stale
"<ticker> insider selling 2025"
Each WebSearch-sourced figure must be tagged 
[Source: WebSearch — <publisher>, <date>]
in the appendix; do not mix it silently with Longbridge data.
仅在Longbridge无法获取以下数据时使用WebSearch：
缺失数据WebSearch查询模板
行业PMI/库存周期
"<行业名称> PMI 2025"
, 
"<行业> inventory cycle"
, 
"中国制造业PMI"
产能利用率
"<industry> capacity utilization"
行业前景（定性）
"<sector> outlook 2025 site:reuters.com OR site:bloomberg.com"
最新内幕交易（若
ownership
数据过时）
"<ticker> insider selling 2025"
每个来自WebSearch的数据必须在附录中标注
[来源：WebSearch — <发布方>, <日期>]
；不得与Longbridge数据混同而不标注。

Reconciliation (勾稽校验) — internal gate, not user-facing

Reconciliation（勾稽校验）——内部校验环节，不面向用户

Before any scoring, verify the fetched figures internally. Reconciliation is a correctness gate for the analysis pipeline; it is not part of the user-facing report. Do not print the check table, do not show per-row gap percentages, do not narrate "勾稽通过" in the conclusion. Reconciliation results only surface to the user in two situations:
  • A check fails by > tolerance → halt scoring, tell the user which specific figure(s) cannot be relied on and why no score is emitted.
  • A field carries a residual gap within tolerance that materially affects a downstream number → note it inline in the Data Source Appendix row for that field (e.g. "BS current-assets sum −1.4% vs reported total — within tolerance").
CheckFormulaTolerance
IS↔BSThis-period net income ≈ Δ Retained earnings (BS) − dividends paid (CF)±3%
IS↔CFNet income + non-cash items (D&A + impairments + WC changes) ≈ Operating CF±5%
CF↔BSΔCash from CF = Cash(t) − Cash(t−1) on BS±1%
Current assets sumCash + AR + Inventory + Other CA ≈ Total current assets (BS)±2%
Liabilities sumST debt + LT debt + Other liabilities ≈ Total liabilities (BS)±2%
Shares outstanding
calc-index
shares × current price ≈ market cap from 
quote
±2%
Period alignmentAll statements from the same fiscal period (or note the lag)exact
Silent-pass principle: if everything passes within tolerance, emit the scored report directly without referencing the reconciliation step at all.
在进行任何评分前，需对获取的数据进行内部校验。勾稽校验是分析流程的正确性关卡；不属于面向用户的报告内容。 不要打印校验表格、不要展示每行的缺口百分比、不要在结论中提及「勾稽通过」。仅在以下两种情况下向用户展示勾稽校验结果：
  • 校验结果超出容差范围→终止评分，告知用户哪些具体数据不可靠，以及无法生成评分的原因。
  • 某字段存在在容差范围内的残留缺口，但会对下游数据产生实质性影响→在数据源附录中对应字段的行内标注（例如：「资产负债表流动资产合计与报告总额相差−1.4%——在容差范围内」）。
校验项公式容差
利润表↔资产负债表本期净利润 ≈ 留存收益变动（资产负债表）− 已支付股息（现金流量表）±3%
利润表↔现金流量表净利润 + 非现金项目（折旧摊销+减值+营运资金变动） ≈ 经营活动现金流±5%
现金流量表↔资产负债表现金流量表中现金变动 = 资产负债表中当期现金 − 上期现金±1%
流动资产合计现金 + 应收账款 + 存货 + 其他流动资产 ≈ 资产负债表中流动资产总额±2%
负债合计短期负债 + 长期负债 + 其他负债 ≈ 资产负债表中负债总额±2%
已发行股份数
calc-index
中的股份数 × 当前股价 ≈ 
quote
中的市值		±2%
期间一致性所有报表均来自同一会计期间（或标注时间差）完全一致
静默通过原则：若所有校验均在容差范围内，则直接生成带评分的报告，完全不提及勾稽校验环节。

Output

输出

Single-stock diagnostic with 8 fixed sections (full template in 
references/output.md
). The reconciliation check is an internal gate — do NOT include its table or pass/fail rows in the user-facing report; reconciliation only appears if a check failed (in which case no score is emitted) or if a residual within-tolerance gap needs to be flagged inline against a specific Data Source Appendix row.
  1. Adjusted cigar-butt score card (静态分 → 动态调整 → 调整后分, with verdict tier 🟢🟡🟠🔴)
  2. Six-dimension static breakdown (NCAV / PE / PB / dividend / debt coverage / earnings stability)
  3. Dynamic adjustment detail (industry cycle, EPS trend, insider activity, NCAV trajectory, value-trap verdict)
  4. Holding-period view (catalyst presence, waiting cost via dividend yield, expected horizon range)
  5. Liquidation-value table (default vs industry-adjusted haircuts, adjusted NCAV per share)
  6. Safety-margin price band (current price / default NCAV line / adjusted NCAV line / Graham buy line = adjusted NCAV × 0.67)
  7. Three-line verdict (valuation level / adjusted safety margin / holding recommendation)
  8. Data source appendix — mandatory; every figure tagged with source, fetch time, and period (and any within-tolerance reconciliation note for that field)
Always close with the boilerplate disclaimer (see 
references/output.md
§Disclaimer).
单只股票诊断报告包含8个固定部分（完整模板见
references/output.md
）。勾稽校验是内部关卡——请勿在校验表格或通过/失败行包含在面向用户的报告中；仅在校验失败（此时不生成评分）或某字段存在容差范围内的残留缺口需标注时，才在数据源附录的对应行提及勾稽校验。
  1. 调整后烟蒂股评分卡（静态分 → 动态调整 → 调整后分，附带 verdict 等级 🟢🟡🟠🔴）
  2. 六维度静态评分拆解（NCAV / PE / PB / 股息率 / 偿债能力 / 盈利稳定性）
  3. 动态调整详情（行业周期、EPS趋势、内幕交易活动、NCAV变动轨迹、价值陷阱判定）
  4. 持有周期建议（是否存在催化剂、通过股息率计算的等待成本、预期持有区间）
  5. 清算价值表（默认折扣 vs 行业调整后折扣、调整后每股NCAV）
  6. 安全边际价格区间（当前价格 / 默认NCAV线 / 调整后NCAV线 / 格雷厄姆买入线 = 调整后NCAV × 0.67）
  7. 三行结论（估值水平 / 调整后安全边际 / 持有建议）
  8. 数据源附录——强制要求；每个数据都标注来源、获取时间、期间（以及该字段的容差范围内勾稽校验备注）
结尾必须附上免责声明（见
references/output.md
的免责声明部分）。

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
请运行 
longbridge auth login
。		請執行 
longbridge auth login
。		Run 
longbridge auth login
.
Sector = bank / insurance / REITNCAV 模型不适用于金融业，已切换提示；建议使用 
longbridge-valuation-methodology
。		NCAV 模型不適用於金融業，建議使用 
longbridge-valuation-methodology
。		NCAV does not fit financials; use 
longbridge-valuation-methodology
.
Reconciliation fails >3%明确披露差异项与差异比例，不输出评分；建议用户复核或换数据源。明確披露差異項與差異比例，不輸出評分。Disclose the failing check and the gap; do not emit a score.
Industry cycle data missing (WebSearch also empty)标注「动态调整层数据不足，仅显示静态评分」。標注「動態調整層數據不足，僅顯示靜態評分」。Mark "dynamic layer unavailable, static score only".
< 5 years of financial history盈利稳定性维度按已披露年限按比例打分，并在数据源附录注明。盈利穩定性按已披露年限比例打分，並於附錄註明。Score earnings stability pro-rata and note in source 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 
not logged in
请运行 
longbridge auth login
。		請執行 
longbridge auth login
。		Run 
longbridge auth login
.
行业为银行/保险/REITNCAV 模型不适用于金融业，已切换提示；建议使用 
longbridge-valuation-methodology
。		NCAV 模型不適用於金融業，建議使用 
longbridge-valuation-methodology
。		NCAV does not fit financials; use 
longbridge-valuation-methodology
.
勾稽校验失败超出3%明确披露差异项与差异比例，不输出评分；建议用户复核或换数据源。明確披露差異項與差異比例，不輸出評分。Disclose the failing check and the gap; do not emit a score.
行业周期数据缺失（WebSearch也无结果）标注「动态调整层数据不足，仅显示静态评分」。標注「動態調整層數據不足，僅顯示靜態評分」。Mark "dynamic layer unavailable, static score only".
财务历史不足5年盈利稳定性维度按已披露年限按比例打分，并在数据源附录注明。盈利穩定性按已披露年限比例打分，並於附錄註明。Score earnings stability pro-rata and note in source appendix.

MCP fallback

MCP fallback

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

Related skills

相关技能

  • Single-stock valuation (PE / PB / EV-EBITDA) → 
    longbridge-valuation
  • DCF intrinsic value → 
    longbridge-dcf
  • Multi-stock value screen → 
    longbridge-value-screen
  • Three-statement reading → 
    longbridge-financial-report
  • Cross-statement deep analysis → 
    longbridge-financial-analysis
  • Method selection guide → 
    longbridge-valuation-methodology
  • 单只股票估值（PE/PB/EV-EBITDA）→ 
    longbridge-valuation
  • DCF内在价值分析 → 
    longbridge-dcf
  • 多只股票价值筛选 → 
    longbridge-value-screen
  • 三报表解读 → 
    longbridge-financial-report
  • 跨报表深度分析 → 
    longbridge-financial-analysis
  • 估值方法选择指南 → 
    longbridge-valuation-methodology

File layout

文件结构

longbridge-graham-stock-analysis/
├── SKILL.md
└── references/
    ├── scoring.md      # static six-dimension table + NCAV haircuts + dynamic factors + value-trap rules
    └── output.md       # full 8-section output template + data-source appendix + disclaimer
longbridge-graham-stock-analysis/
├── SKILL.md
└── references/
    ├── scoring.md      # 静态六维度评分表 + NCAV折扣规则 + 动态调整因素 + 价值陷阱规则
    └── output.md       # 完整8部分输出模板 + 数据源附录 + 免责声明