opencode-skills-collection 4.0.68 → 4.0.70

package/bundled-skills/longbridge-research/references/finance-calendar.md

@@ -0,0 +1,165 @@
+# Financial Calendar Tracking & Insights
+
+## Overview
+
+This Skill targets general retail investors, proactively providing financial calendar summaries, impact analysis for holdings and watchlist, cross-market linkage conclusions — **and helping users discover market opportunities beyond their portfolio**. Users do not need professional financial knowledge; the system handles all reasoning from events to impacts. Conclusions cover all relevant securities — tagged if they belong to the user's holdings or watchlist — while also extending to noteworthy market highlights.
+
+Prerequisite: The user must have completed Longbridge account authorization. See `references/data-fetching.md` for the degradation strategy when unauthorized.
+
+Dependent files:
+
+- `references/output-template.md` — Field specifications and templates for the four output card types
+- `references/data-fetching.md` — Data source priorities, degradation rules, and CLI usage instructions
+
+## Data-Driven, Not Pre-Configured
+
+This Skill does not maintain separate user preference settings. All required information is obtained from the following sources:
+
+- **Holdings & Watchlist**: Fetched in real time from the Longbridge account to automatically determine the securities and markets the user cares about. **Holdings and watchlist are equally important for event coverage — both must be fully scanned; neither source may be omitted.** Holdings and watchlist are not grouped separately; they are unified and sorted by event time, differentiated only by tags.
+- **Market-Wide Events**: In addition to holdings and watchlist events, fetch high-importance market-wide events (without the `--filter` parameter). These events cover securities the user does not hold, tagged with "Market" to help users discover new opportunities. Selection criteria: high market attention (e.g., marquee earnings, hot IPOs, industry leader movements), relevance to current market themes, or potential to create trading opportunities.
+- **Time Range**: Determined from the user's request, with the following defaults. The CLI may not support time parameters — fetch data first, then filter results by time.
+
+| User Expression     | Scan Range                             |
+| ------------------- | -------------------------------------- |
+| Today               | Current day (T+0)                      |
+| Tomorrow            | T+1                                    |
+| This week           | Monday to Sunday of the current week   |
+| Next week           | Monday to Sunday of the following week |
+| Recently / Upcoming | T+0 ~ T+3 (next 3 calendar days)       |
+| No time specified   | Default T+0 ~ T+3                      |
+
+**Weekend & Non-Trading Day Rules:**
+
+Time ranges are calculated in calendar days but must ensure coverage through the next trading day. Specific rules:
+
+1. **Auto-Extension**: When the end of the time range falls on a weekend or holiday, automatically extend to that market's next trading day. For example, saying "next 3 days" on Friday (T+0 ~ T+3 = Friday to Monday) — if Monday is a trading day, cover through Monday's after-hours; if Monday is also a holiday, extend to Tuesday.
+2. **Per-Market Judgment**: When a user's holdings span multiple markets (e.g., US + HK + A-shares), each market has a different trading calendar and must be evaluated separately. For example, US markets are closed on Christmas but HK markets are not — the effective time windows differ.
+3. **Use Market Closure Calendar Data**: The data collection phase already fetches market closure calendars — use them to determine actual trading day boundaries for each market.
+4. **Indicate in Output**: When the time window extends due to weekends/holidays, reflect the actual coverage range in the title (e.g., "May 8 to May 11" rather than "next 3 days"), and note weekend/holiday arrangements where appropriate.
+
+- **Output Style**: Default to plain language (everyday terms, no jargon); if the user demonstrates professional background or explicitly requests it, switch to fundamental-style output (preserving raw data).
+- **Filtering & Priority**: Prioritize high-importance events. Specific filtering strategies are determined based on the importance fields returned by data sources and the user's request. **Event scope is not limited to the user's holdings and watchlist**: major global events (e.g., Fed meetings, non-farm payrolls) and trending events related to the industries of the user's holdings/watchlist should also be included, to avoid missing important market information by focusing only on existing positions.
+- **Market Opportunity Discovery**: Beyond scanning events for holdings and watchlist, proactively discover market-level opportunities and trends. This includes:
+  - **Sector Rotation & Market Themes**: What themes/sectors the market is currently focused on (e.g., AI, tech, nuclear energy, GLP-1 weight-loss drugs), which sectors show significant capital inflows.
+  - **Cross-Market Linkages & Arbitrage Opportunities**: Recent cross-market linkage signals (e.g., A/H share premium changes, Chinese ADR and HK stock correlations, commodity and related stock correlations, ADR and underlying share price differentials), which may not be in the user's current portfolio but are worth watching.
+  - **Event-Driven Trading Opportunities**: Short-term trading windows potentially created by upcoming events (e.g., volatility trading around earnings, sector positioning before policy announcements).
+  - This information is proactively obtained via WebSearch, independent of the user's holdings scope, with the goal of helping users discover "the world beyond their portfolio".
+
+The above default behaviors require no pre-configuration by the user. If the user requests adjustments during a conversation, follow those instructions for the current session.
+
+## Execution Flow
+
+Each request executes the full flow, producing output in four sections. Each section is generated if data exists and omitted if not (but the first section must always be included). Generate as much content as possible, covering all dimensions the user might care about. The same event should appear only once and not be repeated across sections.
+
+### Data Collection (Unified Upfront)
+
+1. Retrieve the user's holdings and watchlist (if unauthorized, stop and prompt login)
+2. Following the `data-fetching.md` specification, **fetch all data sources in parallel** (all without `--filter`, fetching market-wide data):
+   - Earnings/performance calendar, macroeconomic calendar, dividend/ex-date calendar, market closure/trading calendar, stock split calendar, IPO/new listing calendar
+   - **Market trends and opportunity data** (proactively searched via WebSearch, fetched in parallel with the CLI data above)
+3. After obtaining the full dataset, **tag each event** based on the holdings and watchlist (Holdings / Watchlist / Market) — tags are classification labels only and do not affect data retrieval scope
+4. Filter results by the user's requested time range (default T+0 ~ T+3)
+5. **Time direction: Focus on the future.** Only retain events that **have not yet occurred** (from today onward). The sole exception is earnings results released "last night / pre-market today" (i.e., published between the previous trading day's close and today's open), which may be briefly mentioned in sections one and three. Earlier historical events are excluded entirely.
+6. If the user specifies a particular stock, provide in-depth expansion on that stock's dimension
+
+### Section 1: Event Overview (Template 1)
+
+All events (macro, holdings, watchlist, **high-attention market-wide events**) are merged into a single timeline, sorted uniformly by date and time, without duplication:
+
+- If there are earnings results released **last night or pre-market today** (limited to the period from the previous trading day's close to present), mention them briefly without expanding on history
+- Group by calendar day (e.g., "May 12 (Monday)"), sorted chronologically within each day
+- Macro events (CPI, PPI, Fed meetings, non-farm payrolls, etc.) and security-specific events are interleaved on the same timeline, not grouped separately
+- Source tags for securities:
+  - "Holdings" — currently held by the user
+  - "Watchlist" — in the user's watchlist
+  - "Market" — neither holdings nor watchlist, but a high-attention market event (e.g., marquee earnings, hot IPOs, industry leaders) included to help users discover opportunities
+- **Source of "Market" securities**: These naturally emerge from the market-wide calendar data fetched without the `--filter` parameter. After fetching unfiltered data, exclude holdings and watchlist codes, then select noteworthy events from the remainder and tag them as "Market". No hard quantity requirement — event-heavy days will naturally produce more, quiet days fewer. The key is **not to lose the ability to discover opportunities by filtering on securities**
+  - May include, but is not limited to, these types:
+    - Earnings from large-cap, high-attention companies (industry leaders, recently trending companies)
+    - Hot IPOs / new listings
+    - Securities closely related to current market themes
+    - Catalyst events for companies with recent price anomalies or heavy market discussion
+- Securities with no events do not appear
+- No cap on the number of events — list as many as there are
+- Output following Template 1 format in `output-template.md`
+
+### Section 2: Key Event Impact Analysis (Template 2)
+
+- Extract high-importance events (e.g., major earnings, Fed meetings, non-farm payrolls, significant industry policies)
+- Provide in-depth analysis for each key event:
+  - Event content and core data
+  - Impact classification for actually affected stocks (direct impact / indirect impact), tagged if they are watchlist/holdings, omitting unrelated securities
+  - Action reference (no buy/sell instructions)
+- If there are no high-importance events in the time range, this section may be omitted
+- Output following Template 2 format in `output-template.md`
+
+### Section 3: Earnings Results Express (Template 3)
+
+- Cover earnings results released **last night or pre-market today** across all securities (from the previous trading day's close to today's open) — earlier results are excluded. Generate an earnings result card for each:
+  - Beat/miss assessment and magnitude
+  - Core business highlights
+  - Market reaction (after-hours/pre-market price movement)
+  - Next-day market closure notice (if applicable)
+- If no earnings have been released, this section is omitted
+- Output following Template 3 format in `output-template.md`
+
+### Section 4: Market Trends & Opportunity Discovery (Template 4)
+
+This section goes beyond the user's existing holdings and watchlist to proactively discover market-level opportunities:
+
+- **Recent Market Trends & Sector Movements**: Search via WebSearch for currently trending themes, sector rotation directions, and capital flows. Not limited to securities the user already follows — the goal is to help users discover new opportunities.
+- **Cross-Market Linkages & Arbitrage Signals**: Scan recent (especially yesterday's) cross-market linkage activity, including but not limited to:
+  - A/H share premium anomalies (price spreads for the same company listed on both A-shares and HK)
+  - Chinese ADR vs. HK underlying share price differentials
+  - Commodity price fluctuations transmitting to related listed company stock prices (e.g., copper price rise → copper mining stocks)
+  - Exchange rate movements creating cross-market impacts
+  - "Time-zone arbitrage" windows where a policy/event has already been priced into one market but another market hasn't opened yet
+- **Event-Driven Potential Opportunities**: Based on upcoming events (earnings, policies, data releases), identify potential short-term trading opportunity windows, even if the securities involved are not in the user's portfolio
+- Each opportunity point must explain the logic and risks; no specific buy/sell recommendations
+- If searches yield no valuable opportunity information, this section may be omitted
+- Output following Template 4 format in `output-template.md`
+
+### Wrap-Up
+
+- Append disclaimer text at the end (see output specifications)
+- Prompt the user that they can follow up: "If you'd like to dive deeper into any event, or when earnings results come out, feel free to ask me anytime."
+
+## Output Specifications
+
+### Language Rules
+
+- Sentence length ≤ 30 words; avoid long compound sentences
+- Each event conclusion should not exceed 2 lines
+- Use hedging language such as "may", "likely", etc.; do not make definitive predictions
+- Action suggestions should use phrases like "consider monitoring", "wait until after the open to assess" — not "you should buy/sell"
+- Do not use jargon such as EPS, guidance, Beta, IV, etc.; convert all terms to everyday language
+
+### Terminology Conversion Reference
+
+| Professional Term          | Output Phrasing                                                                             |
+| -------------------------- | ------------------------------------------------------------------------------------------- |
+| Ex-Dividend Date (Ex-Date) | Note: rules differ by market — buying after this date means you won't receive this dividend |
+| Half-Day Trading           | HK stocks only trade until noon today                                                       |
+| Supply Chain Transmission  | News from this company may cause related stocks to move together                            |
+| Liquidity Risk             | Trading volume will be thin that day, so price swings may be larger                         |
+| Macro Data Beat            | The economic data came in better than the market expected                                   |
+
+### Prohibitions
+
+- Never respond with "nothing important today" or empty results
+- No specific price predictions
+- No direct buy or sell recommendations
+- Events must always display tags; securities with no events are simply omitted from the output
+- Securities not held and not in the watchlist may appear in the following cases:
+  - Major global events (e.g., Fed meetings, non-farm payrolls) should be displayed regardless of whether the user holds them
+  - Securities tagged "Market" in Section 1 — high-attention events (marquee earnings, hot IPOs, industry leaders, etc.)
+  - Trending event securities directly related to the industries of the user's holdings or watchlist
+  - Securities in Section 4 (Market Trends & Opportunity Discovery) — this section is specifically designed to help users discover opportunities beyond their portfolio
+- Overall principle: **Full coverage** for holdings and watchlist events (no omissions); **selective coverage** for Market-tagged events (only high-value ones)
+
+### Disclaimer Text
+
+Appended once at the end of each complete report (not repeated in each section):
+
+> If you'd like to dive deeper into any event, or when earnings results come out, feel free to ask me anytime.
+> The above content is compiled from Longbridge data sources and publicly available information, provided for reference only. It does not constitute investment advice. Please make decisions based on your own judgment.

package/bundled-skills/longbridge-research/references/financial-planning.md

@@ -0,0 +1,77 @@
+# longbridge-financial-planning
+
+Personal financial planning framework — retirement targets, education fund, balance sheet, and portfolio gap analysis.
+
+## Workflow
+
+1. Fetch current account value, positions, and multi-currency cash.
+2. Ask the user for planning inputs (or use defaults):
+   - Retirement age target (default: 60)
+   - Annual living expenses in retirement
+   - Children's education fund target (if applicable)
+   - Monthly savings capacity
+   - Expected portfolio return assumption
+3. Build the financial plan:
+   - **Net worth snapshot**: investments + cash − liabilities
+   - **Retirement gap**: target corpus − current portfolio (compounded)
+   - **Education fund gap**: target − dedicated savings
+   - **Savings rate**: monthly contribution vs. income
+   - **Years to goal**: solve for `n` given current value, rate, contribution
+4. Output a structured plan with actionable recommendations.
+5. Convert multi-currency assets to a common base using FX rates.
+
+> If unsure of exact flag names, run `longbridge <subcommand> --help` before proceeding.
+
+## CLI
+
+```bash
+# Account portfolio market value
+longbridge portfolio --format json
+
+# Current positions (stocks, funds)
+longbridge positions --format json
+
+# Multi-currency exchange rates for normalisation
+longbridge exchange-rate --format json
+```
+
+## Output structure
+
+```
+PERSONAL FINANCIAL PLAN  <Date>
+
+NET WORTH SNAPSHOT
+Investment Portfolio:  $xxx,xxx (USD equivalent)
+Cash & Money Market:  $xx,xxx
+Total Net Worth:       $xxx,xxx
+
+RETIREMENT PLANNING
+Target Age:      60   Current Age: xx   Years: xx
+Annual Expense:  $xx,xxx/yr   Corpus Needed: $x,xxx,xxx
+Current Progress: $xxx,xxx (xx% of target)
+Gap:             $xxx,xxx
+Required Monthly Savings: $x,xxx (at x.x% p.a.)
+
+EDUCATION FUND
+Target:       $xxx,xxx  by Year 20xx
+Current:      $xx,xxx   Gap: $xx,xxx
+Monthly Top-up Needed: $x,xxx
+
+SAVINGS RATE ANALYSIS
+Monthly Income (estimated): $x,xxx
+Monthly Savings:            $x,xxx  (xx%)
+Recommendation: [On track | Increase savings by $x,xxx/month]
+
+ACTION ITEMS
+1. ...
+2. ...
+```
+
+## Error handling
+
+| Situation                       | 简体回复                                           | 繁體回復                                           | English reply                                        |
+| ------------------------------- | -------------------------------------------------- | -------------------------------------------------- | ---------------------------------------------------- |
+| Not logged in                   | 请运行 `longbridge auth login` 并授予 Trade 权限。 | 請執行 `longbridge auth login` 並授予 Trade 權限。 | Run `longbridge auth login` with Trade scope.        |
+| Empty portfolio                 | 账户暂无持仓，请先建立投资组合。                   | 賬戶暫無持倉，請先建立投資組合。                   | No positions found — build a portfolio first.        |
+| FX rate unavailable             | 部分货币汇率不可用，已使用近似值。                 | 部分貨幣匯率不可用，已使用近似值。                 | Some FX rates unavailable — approximate values used. |
+| `command not found: longbridge` | 请安装 longbridge-terminal 或通过 MCP 连接。       | 請安裝 longbridge-terminal 或透過 MCP 連線。       | Install longbridge-terminal or connect via MCP.      |

package/bundled-skills/longbridge-research/references/forecast-eps.md

@@ -0,0 +1,39 @@
+# forecast-eps
+
+```
+EPS forecasts and analyst consensus estimates for a symbol
+
+Example: longbridge forecast-eps TSLA.US Example: longbridge forecast-eps TSLA.US --format json
+
+Usage: longbridge forecast-eps [OPTIONS] <SYMBOL>
+
+Arguments:
+  <SYMBOL>
+          Symbol in <CODE>.<MARKET> format
+
+Options:
+      --format <FORMAT>
+          Output format: 'pretty' for human-readable, 'json' for AI agents and scripting
+          
+          [default: pretty]
+          [possible values: table, json]
+
+  -v, --verbose
+          Print verbose request info (host, elapsed) to stderr, prefixed with `*` like curl -v
+
+      --lang <LANG>
+          Language for content fetched from longbridge.com: zh-CN or en. Defaults to system LANG env var, then en
+
+  -h, --help
+          Print help (see a summary with '-h')
+```
+
+## Usage
+
+```bash
+# Run with JSON output for AI agents
+longbridge forecast-eps --format json
+
+# See all options
+longbridge forecast-eps --help
+```

package/bundled-skills/longbridge-research/references/fund-holder.md

@@ -0,0 +1,44 @@
+# fund-holder
+
+```
+Funds and ETFs that hold a given symbol
+
+Returns: fund name, ticker, currency, weight (position ratio), and report date. Pass --count -1 to return all holders. Example: longbridge fund-holder AAPL.US Example: longbridge fund-holder AAPL.US --count 20 Example: longbridge fund-holder AAPL.US --format json
+
+Usage: longbridge fund-holder [OPTIONS] <SYMBOL>
+
+Arguments:
+  <SYMBOL>
+          Symbol in <CODE>.<MARKET> format
+
+Options:
+      --count <COUNT>
+          Number of results to return (-1 for all)
+          
+          [default: 20]
+
+      --format <FORMAT>
+          Output format: 'pretty' for human-readable, 'json' for AI agents and scripting
+          
+          [default: pretty]
+          [possible values: table, json]
+
+  -v, --verbose
+          Print verbose request info (host, elapsed) to stderr, prefixed with `*` like curl -v
+
+      --lang <LANG>
+          Language for content fetched from longbridge.com: zh-CN or en. Defaults to system LANG env var, then en
+
+  -h, --help
+          Print help (see a summary with '-h')
+```
+
+## Usage
+
+```bash
+# Run with JSON output for AI agents
+longbridge fund-holder --format json
+
+# See all options
+longbridge fund-holder --help
+```

package/bundled-skills/longbridge-research/references/hkipo-analysis.md

@@ -0,0 +1,101 @@
+# longbridge-hkipo-analysis
+
+Prompt-only 港股打新分析。给定一只新股代码或公司名，输出「推荐打新 / 中性观望 / 建议回避」三档评级 + 四维评分明细 + 招股书精华 + 风险提示 + 申购手数参考；或在日历模式下输出未来 4 周打新日程表 + 评级速览。报告结尾固定输出「数据来源明细」附录，每一行注明来源（Longbridge CLI 子命令 / MCP 工具 / WebSearch URL）、抓取时间和数据期间。
+
+> **Independence statement (mandatory)**: this skill is an independent打新 analysis framework. It is **not** affiliated with the issuer, the sponsoring underwriters, the HKEx, or any cornerstone investor. The rating is model-derived and never a buy / sell recommendation; arrange margin financing (孖展) only after independently understanding the leverage risk.
+
+## Cognitive frame (do not skip)
+
+港股打新分析与二级市场分析的关键区别是 **可用数据窗口非常窄**（招股期通常 3–5 个工作日），且分析对象是「**尚未上市**」或「**刚上市**」的标的，没有 K 线、没有历史财报趋势可读。三件事每次输出都必须明确：
+
+1. **评级是给散户的决策锚，不是预测**。"推荐 / 中性 / 回避" 是基于四维评分的当下判断，不预测首日涨跌幅。任何"预计首日 +XX%"的写法都违反护栏。
+2. **数据缺失要披露，不要编造**。招股书未披露的（如尚未公布的回拨倍数、未定的基石名单）必须显式标"招股书未披露 / 待公告"，对应维度按"信息不足"降级，而非用行业均值占位。
+3. **孖展（融资打新）必须单独提示**。一旦用户问"打几手"或"借钱打"，输出必须包含一行杠杆风险提示，且不得默认推荐孖展方案。
+
+四种情形要能分辨：
+
+- **招股期内 + 数据齐全** → 走单股完整分析（场景一），输出四维评分 + 招股书精华 + 申购参考。
+- **没有具体标的，只问"最近"** → 走日历模式（场景二），输出未来 4 周打新日程 + 每只一句话评级。
+- **已上市 ≤ 30 天，用户问"没打中追不追"** → 走次新股追涨模式（场景四），加入暗盘 / 首日实际表现 / 当前价位与发行价偏离度，参考目标价区间，不出具"追 / 不追"指令。
+- **已上市 > 30 天** → 拒绝接管，建议改用 `longbridge-stock-research` / `longbridge-fundamental`，本 Skill 不覆盖。
+
+## Workflow
+
+1. **识别模式**。从用户输入判定走「单股」「日历」还是「次新股」分支。模糊或多公司命中时先反问消歧；纯公司名时尝试自动解析为 `<CODE>.HK`，多匹配则列出让用户确认。
+2. **市场合法性检查**。本 Skill 只接受港股主板 / GEM 标的。若输入是 `.US` / `.SH` / `.SZ` / `.SG`，直接拒绝并建议改用 `longbridge-ipo` + 对应市场的分析 Skill。
+3. **工具发现（必做）**。每次执行前先 `longbridge --help` 拿当前可用子命令清单，再按 [§CLI](#cli) 的"数据需求 → 语义关键词"映射选择具体子命令。**不要把子命令名 / 标志名硬编码进对话**，CLI 会随版本演进。
+4. **并行拉取数据**。按当前模式拉取必需项（详见 [§CLI](#cli)）。CLI 命令缺失 → 走 [§MCP fallback](#mcp-fallback)；MCP 工具也没有 → 走 [§WebSearch fallback](#websearch-fallback-only-for-data-longbridge-does-not-provide)；仍然拿不到 → 在对应维度标记"数据不可得"，**不要降级到行业均值或猜测**。
+5. **数据一致性检查**。在评分之前做下列轻量校验：
+   - 招股书发行价区间、招股期间、上市日期与 `ipo detail` 字段一致；不一致取最新一条并在附录注明冲突。
+   - 基石比例、超购倍数、回拨档位若来自不同来源，必须显示各自来源行。
+   - 货币：所有金额按招股书原币（默认 HKD）展示，若用户持仓币种不同，附加备注汇率换算口径而不是默默换算。
+6. **四维评分**。按 `references/scoring.md` 的指标卡片、阈值、权重打分（满分 10 分）；权重总和 120%，归一化输出。三档评级的硬阈值见 `references/scoring.md` §Pass/reject matrix。**任一关键数据缺失（发行价、基石比例、超购倍数中至少两项缺失）时，不出评级，仅出"数据不足，无法评级"**。
+7. **招股书精华提取（标准模式 = 详细输出）**。按 `references/scoring.md` §Prospectus extraction 的章节优先级，从招股书提取 TAM / 财务三年趋势 / 募资用途 / 增长驱动 / 管理层背景 / 风险因素。所有数字必须可溯源到原文章节。
+8. **风险与申购参考**。3 条具体风险（不接受"市场风险"这种空话，须挂钩具体业务 / 财务 / 监管事实）+ 申购手数参考分稳健型 / 进取型两档，进取型须显式标杠杆放大损失。
+9. **输出报告**。按 `references/output.md` 的对应模板（单股 / 日历 / 次新股 / 拒绝 / 数据不足）渲染，**结尾必为「数据来源明细」附录**，附录之后是免责声明。
+
+## CLI
+
+> 工具发现优先：`longbridge --help` 看当前可用子命令；构造调用前再 `longbridge <subcommand> --help` 核对参数。**下面列出的子命令是"语义示例"，以 `--help` 输出为准。**
+
+按数据需求分类（语义关键词 → 示例子命令）：
+
+| 数据需求                                                             | 语义关键词                                                                                     | 示例子命令                                                                                                                                                                   |
+| -------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| 港股 IPO 日历                                                        | `ipo` + `calendar` / `subscriptions` / `wait-listing` / `listed`                               | `longbridge ipo calendar --format json` / `longbridge ipo subscriptions --format json` / `longbridge ipo wait-listing --format json` / `longbridge ipo listed --format json` |
+| 单只新股招股书摘要、发行价、时间线、基石、超购倍数                   | `ipo` + `detail`                                                                               | `longbridge ipo detail <SYMBOL> --format json`                                                                                                                               |
+| 招股书章节级数据（财务摘要 / 募资用途 / 风险因素 / 管理层 / 锁定期） | 先 `longbridge ipo --help` 看 `ipo` 子命令族能否覆盖；典型情况 `ipo detail` 已展开主要章节字段 | `longbridge ipo --help` → 选合适子命令 → `longbridge ipo <sub> <SYMBOL> --format json`；仍缺章节 → WebSearch 拿 HKEXnews 原文                                                |
+| 同业上市公司估值（PE / PS / PB 均值与中位数）                        | `valuation` / `peer` / `peer-comparison`                                                       | `longbridge peer-comparison <SYMBOL> --format json` / `longbridge valuation <SYMBOL> --format json`                                                                          |
+| 近期港股新股首日表现（用于计算近 3 月破发率）                        | `ipo` + `listed` + `performance`                                                               | `longbridge ipo listed --format json`                                                                                                                                        |
+| 恒生指数近月行情（市场时机维度）                                     | `index-quote` / `kline` + HSI                                                                  | `longbridge index-quote HSI.HK --format json` / `longbridge kline HSI.HK --period day --count 60 --format json`                                                              |
+| 同行业板块近月平均涨跌                                               | `sector-monitor` / `industry-overview`                                                         | `longbridge sector-monitor --format json` / `longbridge industry-overview <SECTOR> --format json`                                                                            |
+| 基石投资者公告 / 招股相关舆情                                        | `news` / `topic`                                                                               | `longbridge news <SYMBOL> --format json` / `longbridge topic <SYMBOL> --format json`                                                                                         |
+| 公司基础信息（行业归属 / 注册地）                                    | `basicinfo` / `company-profile`                                                                | `longbridge basicinfo <SYMBOL> --format json` / `longbridge company-profile <SYMBOL> --format json`                                                                          |
+| 次新股模式：上市后实际行情 + 暗盘相关数据                            | `quote` / `kline` / `derivatives` / `ipo` + `grey market`                                      | `longbridge quote <SYMBOL> --format json` / `longbridge kline <SYMBOL> --period day --count 60 --format json`                                                                |
+
+并行调用：模式确定后，单股 / 次新股模式默认并行拉取 `ipo detail`、`peer-comparison`、`ipo listed`（破发率）、`index-quote HSI.HK`、`news`、`basicinfo`；招股书更深章节缺失时再按 `longbridge ipo --help` 选具体子命令补拉，仍缺则 WebSearch HKEXnews。日历模式只拉 `ipo subscriptions` + `ipo wait-listing` + `ipo listed`（计算近期破发率作为市场时机锚）。
+
+### WebSearch fallback — only for data Longbridge does not provide
+
+WebSearch 是兜底，**不是默认路径**。仅在 Longbridge CLI + MCP 都拿不到时使用，且必须在附录显式标 `[WebSearch — <publisher>, <date>, <url>]`，禁止伪造来源。
+
+| 缺失数据                                  | WebSearch 查询模式                                                          | 可接受的来源权威                                             |
+| ----------------------------------------- | --------------------------------------------------------------------------- | ------------------------------------------------------------ |
+| 港交所披露易招股书原文链接                | `"<公司名>" 招股书 site:hkexnews.hk`                                        | HKEXnews（披露易）                                           |
+| 行业 TAM / 增速                           | `"<行业名>" 市场规模 2030` / `"<industry>" market size 2030 Frost Sullivan` | 招股书引用机构（弗若斯特沙利文 / 灼识 / 艾瑞）、Gartner、IDC |
+| 主承销商近 3 年港股 IPO 承销排名          | `"<投行名>" 香港 IPO 承销 排名 2024` / `"HK IPO league table" 2024 sponsor` | Dealogic、Refinitiv、HKEx 年报                               |
+| 基石投资者公告原文 / 历史投资记录         | `"<基石投资者名>" "<公司名>" 基石`                                          | 港交所披露、彭博、路透、公司新闻稿                           |
+| 暗盘成交价 / 灰市报价（次新股模式）       | `"<公司名>" 暗盘 报价 / grey market price`                                  | 富途、辉立、耀才、华盛等公开暗盘平台报价（注明平台与时间戳） |
+| 近 3 个月港股新股破发率（CLI 数据不够时） | `"港股新股" "破发率" 2025` / `"HK IPO first-day return" YTD`                | 智通财经、华兴、HKEx 月报                                    |
+| 监管 / 政策风险（特定行业）               | `"<sector>" 港股 监管 2025`                                                 | SFC、HKEx、FT、Reuters                                       |
+
+每条 WebSearch 引用必须在附录写明 publisher + 报告 / 文章名 + 日期 + URL + 抓取时间；任何"无法核实出处"的数字一律按"数据不可得"处理。
+
+## Output
+
+输出由 `references/output.md` 模板驱动，按用户输入语言整体翻译后发出。三类主报告 + 两类异常报告：
+
+- **场景 A — 单只新股深度分析**（招股期内或刚开始招股）：评级条 → 核心数据卡 → 四维评分明细 → 招股书精华（行业空间 / 商业模式 / 三年财务表 / 募资用途 / 增长驱动 / 管理层）→ 3 条具体风险 → 申购手数参考（稳健 / 进取，附孖展提示）→ 延伸查询入口 → **数据来源明细附录** → 免责声明。
+- **场景 B — 打新日历**：未来 4 周日程表（公司名 / 截止日 / 上市日 / 募资规模 / 评级）→ 1–2 只重点关注 + 一句话理由 → 市场整体打新环境评估（基于近 3 月破发率） → **数据来源明细附录** → 免责声明。
+- **场景 C — 次新股追涨**：上市首日实际表现（开 / 收 / 振幅 / 当前价偏离发行价幅度）→ 简化四维（重点强调"市场时机"与"基本面展望"）→ 参考目标价区间（基于同业估值倒推，明确标"区间"非"目标点"）→ 3 条具体风险（强调追高与流动性）→ **数据来源明细附录** → 免责声明。
+- **异常 D — 数据不足，无法评级**：列出已尝试拉取但缺失的关键字段 → 引导用户等待招股截止日下午（超购倍数公告）或刷新数据源 → **数据来源明细附录**（仍然印出已成功获取的部分） → 免责声明。
+- **异常 E — 拒绝接管**：非港股 / 已上市 > 30 天 / 介绍上市 / SPAC 等，给出原因与替代 Skill 推荐，不再进入分析。
+
+字数约束：场景 A 快速模式（仅评级 + 核心数据 + 四维评分 + 风险 + 申购参考）≤ 400 字；详细模式（含完整招股书精华）≤ 2000 字。场景 B / C / D / E ≤ 800 字。
+
+> **数据来源明细附录是强制输出**。无论评级、日历、追涨、数据不足、拒绝接管哪条分支，都必须以「数据来源明细」结尾，每一行须包含：字段类别 / 来源（CLI 子命令 / MCP 工具 / WebSearch URL）/ 抓取时间（YYYY-MM-DD HH:MM）/ 数据期间。WebSearch 行必须额外给出 publisher + 报告名 + 文章日期。任何数据缺失项必须在附录里以 `[unavailable]` 或 `[未披露 — 等待公告]` 注明。
+
+## Error handling
+
+| Situation                                     | 简体回复                                                                                                                        | 繁體回覆                                                                                                                        | English reply                                                                                                                   |
+| --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
+| `command not found: longbridge`               | 回退到 MCP；若 MCP 也不可用，请安装 longbridge-terminal。                                                                       | 回退到 MCP；若 MCP 也不可用，請安裝 longbridge-terminal。                                                                       | Fall back to MCP; if MCP unavailable install longbridge-terminal.                                                               |
+| stderr `not logged in` / `unauthorized`       | 本 Skill 公开数据无需登录；若是 `ipo orders` / `ipo profit-loss` 等账户接口，请运行 `longbridge auth login` 并选择 Trade 权限。 | 本 Skill 公開數據無需登入；若是 `ipo orders` / `ipo profit-loss` 等帳戶接口，請執行 `longbridge auth login` 並選擇 Trade 權限。 | Public data needs no login; for `ipo orders` / `ipo profit-loss` run `longbridge auth login` with Trade scope.                  |
+| 非港股 IPO 输入                               | 本 Skill 仅覆盖港股主板与 GEM，美股 / A 股请用 `longbridge-ipo` + 对应市场的分析 Skill。                                        | 本 Skill 僅覆蓋港股主板與 GEM，美股 / A 股請用 `longbridge-ipo` + 對應市場的分析 Skill。                                        | This skill covers HK Main Board + GEM only; for US / A-share IPOs use `longbridge-ipo` + a market-specific analysis skill.      |
+| 已上市 > 30 天的标的                          | 本 Skill 已不覆盖，请改用 `longbridge-stock-research` / `longbridge-fundamental`。                                              | 本 Skill 已不覆蓋，請改用 `longbridge-stock-research` / `longbridge-fundamental`。                                              | Out of scope; switch to `longbridge-stock-research` / `longbridge-fundamental`.                                                 |
+| 介绍上市 / SPAC / 债券上市                    | 本 Skill 仅评估有募资的常规 IPO，不分析介绍上市 / SPAC / 债券。                                                                 | 本 Skill 僅評估有募資的常規 IPO，不分析介紹上市 / SPAC / 債券。                                                                 | Listings without fundraising (介绍上市 / SPAC / bond listing) are out of scope.                                                 |
+| 关键数据 ≥ 2 项缺失（发行价、基石、超购倍数） | 不出评级，仅出「数据不足，无法评级」并在附录列出缺失项。                                                                        | 不出評級，僅出「資料不足，無法評級」並在附錄列出缺失項。                                                                        | Do not emit a rating; emit "Insufficient data — no rating" and list missing fields in the appendix.                             |
+| 超购倍数尚未公布（招股期未结束）              | 在「发行质量」维度标「等待招股截止日下午公告」，不强行评分。                                                                    | 在「發行質量」維度標「等待招股截止日下午公告」，不強行評分。                                                                    | Tag the "Issue quality" dimension "awaiting close-of-book disclosure"; do not force-score.                                      |
+| WebSearch 找不到引用源                        | 该数据点附录写 `[unavailable]`，对应章节给定性描述而非编造数字。                                                                | 該數據點附錄寫 `[unavailable]`，對應章節給定性描述而非編造數字。                                                                | Tag the row `[unavailable]`; qualitative discussion only — never fabricate.                                                     |
+| 用户问孖展具体杠杆产品                        | 本 Skill 不推荐具体孖展产品；提示杠杆风险并引导至客服或 Longbridge 孖展页面。                                                   | 本 Skill 不推薦具體孖展產品；提示槓桿風險並引導至客服或 Longbridge 孖展頁面。                                                   | This skill does not recommend specific margin products; surface leverage risk and redirect to support / Longbridge margin page. |
+| 其他 stderr                                   | 原样透传错误，不静默重试。                                                                                                      | 原樣透傳錯誤，不靜默重試。                                                                                                      | Surface stderr verbatim; never silently retry.                                                                                  |

package/bundled-skills/longbridge-research/references/industry-peers.md

@@ -0,0 +1,46 @@
+# industry-peers
+
+```
+Industry peer group tree for a BK `counter_id`
+
+Returns the hierarchical sub-sector tree for an industry group, with stock count, daily change, and YTD change at each level.
+
+Use `industry-rank` to discover industry Counter IDs, then pass one here.
+
+Example: longbridge industry-peers BK/US/IN00258 Example: longbridge industry-peers BK/HK/IN20337
+
+Usage: longbridge industry-peers [OPTIONS] <SYMBOL>
+
+Arguments:
+  <SYMBOL>
+          BK `counter_id` from `industry-rank`, e.g. BK/US/IN00258
+
+Options:
+      --market <MARKET>
+          Market override (default: inferred from symbol suffix)
+
+      --format <FORMAT>
+          Output format: 'pretty' for human-readable, 'json' for AI agents and scripting
+          
+          [default: pretty]
+          [possible values: table, json]
+
+  -v, --verbose
+          Print verbose request info (host, elapsed) to stderr, prefixed with `*` like curl -v
+
+      --lang <LANG>
+          Language for content fetched from longbridge.com: zh-CN or en. Defaults to system LANG env var, then en
+
+  -h, --help
+          Print help (see a summary with '-h')
+```
+
+## Usage
+
+```bash
+# Run with JSON output for AI agents
+longbridge industry-peers --format json
+
+# See all options
+longbridge industry-peers --help
+```

package/bundled-skills/longbridge-research/references/industry-rank.md

@@ -0,0 +1,62 @@
+# industry-rank
+
+```
+Industry ranking list by market and indicator
+
+Returns a ranked list of industries. The "Counter ID" column contains BK `counter_ids` (e.g. BK/US/IN00258) that can be passed directly to `industry-peers` to explore the sub-sector hierarchy for that industry.
+
+Example: longbridge industry-rank --market US Example: longbridge industry-rank --market HK --indicator market-cap Example: longbridge industry-rank --market US --indicator revenue --limit 10
+
+Usage: longbridge industry-rank [OPTIONS] --market <MARKET>
+
+Options:
+      --market <MARKET>
+          Market: US | HK | SG | CN
+          
+          [possible values: US, HK, SG, CN]
+
+      --indicator <INDICATOR>
+          Ranking indicator (default: leading-gainer)
+          
+          [default: leading-gainer]
+          [possible values: leading-gainer, today-trend, popularity, market-cap, revenue, revenue-growth, net-profit, net-profit-growth]
+
+      --sort-type <SORT_TYPE>
+          Display mode: single (default, flat list) | multi (hierarchical)
+
+          Possible values:
+          - single: Flat single-level list (default)
+          - multi:  Hierarchical multi-level tree
+          
+          [default: single]
+
+      --count <COUNT>
+          Number of results (default: 20)
+          
+          [default: 20]
+
+      --format <FORMAT>
+          Output format: 'pretty' for human-readable, 'json' for AI agents and scripting
+          
+          [default: pretty]
+          [possible values: table, json]
+
+  -v, --verbose
+          Print verbose request info (host, elapsed) to stderr, prefixed with `*` like curl -v
+
+      --lang <LANG>
+          Language for content fetched from longbridge.com: zh-CN or en. Defaults to system LANG env var, then en
+
+  -h, --help
+          Print help (see a summary with '-h')
+```
+
+## Usage
+
+```bash
+# Run with JSON output for AI agents
+longbridge industry-rank --format json
+
+# See all options
+longbridge industry-rank --help
+```

package/bundled-skills/longbridge-research/references/insider-trades.md

@@ -0,0 +1,48 @@
+# insider-trades
+
+```
+SEC Form 4 insider trades for a US-listed company
+
+Shows non-derivative transactions (direct stock buys, sells, grants, etc.) filed by corporate insiders (officers, directors, 10% owners) with the SEC. Only US-listed equities are supported (data source: SEC EDGAR Form 4).
+
+Transaction types: BUY (P) | SELL (S) | GRANT (A) | DISP (D) | TAX (F) | EXERCISE (M/X) | GIFT (G)
+
+Example: longbridge insider-trades TSLA.US Example: longbridge insider-trades AAPL.US --count 40 Example: longbridge insider-trades NVDA.US --format json
+
+Usage: longbridge insider-trades [OPTIONS] <SYMBOL>
+
+Arguments:
+  <SYMBOL>
+          Symbol in <CODE>.<MARKET> format (US market only, e.g. TSLA.US AAPL.US)
+
+Options:
+      --count <COUNT>
+          Number of Form 4 filings to fetch (default: 20)
+          
+          [default: 20]
+
+      --format <FORMAT>
+          Output format: 'pretty' for human-readable, 'json' for AI agents and scripting
+          
+          [default: pretty]
+          [possible values: table, json]
+
+  -v, --verbose
+          Print verbose request info (host, elapsed) to stderr, prefixed with `*` like curl -v
+
+      --lang <LANG>
+          Language for content fetched from longbridge.com: zh-CN or en. Defaults to system LANG env var, then en
+
+  -h, --help
+          Print help (see a summary with '-h')
+```
+
+## Usage
+
+```bash
+# Run with JSON output for AI agents
+longbridge insider-trades --format json
+
+# See all options
+longbridge insider-trades --help
+```