longbridge-earnings
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseEarnings Update Skill
财报更新Skill
Response language: match the user's input language — Simplified Chinese / Traditional Chinese / English. Both the DOCX report body and the in-chat summary follow the user's language; chart labels, axis titles, and file names always stay in English.
响应语言:匹配用户输入语言——简体中文/繁体中文/英文。DOCX报告正文和聊天内摘要均遵循用户使用的语言;图表标签、轴标题及文件名始终保持英文。
When to Use
使用场景
| Trigger | Example |
|---|---|
| Post-earnings analysis | "Analyze TSLA.US latest earnings" / "帮我分析腾讯最新财报" |
| Specific quarter update | "Tencent Q4 2024 earnings update" / "业绩更新" |
| Quarterly results | "Q1/Q2/Q3/Q4 results for [company]" |
Do not trigger if: user wants an initiation report.
| 触发类型 | 示例 |
|---|---|
| 财报后分析 | "Analyze TSLA.US latest earnings" / "帮我分析腾讯最新财报" |
| 指定季度更新 | "Tencent Q4 2024 earnings update" / "业绩更新" |
| 季度业绩 | "Q1/Q2/Q3/Q4 results for [company]" |
请勿触发的场景:用户需要初始研究报告时。
Data Sources
数据源
Priority: CLI (primary) → Web Search (supplement)
Use the Longbridge CLI for all market data. Before using any command, run to check available options — the CLI is updated frequently.
longbridge <command> --helpCLI + Python pattern: prefer reading from a file over piping into . Multi-line JSON with embedded quotes can hit shell-quoting edge cases (especially under zsh's argument handling), so the safer pattern is:
python3 -c-cbash
longbridge institution-rating 700.HK --format json > /tmp/rating.json
python3 -c "import json; d = json.load(open('/tmp/rating.json')); print(d)"If you do prefer pipes, use a heredoc-fed Python script () or save to a file and run a file.
python3 <<'PY' ... PY.pyCLI docs: https://open.longbridge.com/zh-CN/docs/cli/
MCP endpoint:
https://openapi.longbridge.com/mcpKey CLI entry points for earnings analysis:
| Data Needed | CLI Entry Point |
|---|---|
| Filings & reports | |
| Financial statements | |
| Analyst consensus & estimates | |
| Quote & valuation metrics | |
| Price history | |
| Analyst ratings | |
| News | |
Web Search supplements for content not in CLI: consensus estimates vintage, earnings call transcripts, M&A precedent data.
优先级:CLI(主数据源)→ 网页搜索(补充)
使用Longbridge CLI获取所有市场数据。执行任何命令前,先运行 查看可用选项——CLI会频繁更新。
longbridge <command> --helpCLI + Python 模式:优先从文件读取数据,而非通过管道传入 。带有嵌入引号的多行JSON可能会触发shell引用的边缘情况(尤其是在zsh的 参数处理下),因此更安全的模式是:
python3 -c-cbash
longbridge institution-rating 700.HK --format json > /tmp/rating.json
python3 -c "import json; d = json.load(open('/tmp/rating.json')); print(d)"如果偏好使用管道,可使用 heredoc 传入Python脚本(),或保存为 文件后运行。
python3 <<'PY' ... PY.pyCLI文档:https://open.longbridge.com/zh-CN/docs/cli/
MCP端点:
https://openapi.longbridge.com/mcp财报分析核心CLI入口:
| 所需数据 | CLI入口 |
|---|---|
| 公告与报告 | |
| 财务报表 | |
| 分析师一致预期 | |
| 报价与估值指标 | |
| 价格历史 | |
| 机构评级 | |
| 新闻 | |
对于CLI未覆盖的内容,可通过网页搜索补充:一致预期时效、财报电话会议记录、并购先例数据等。
Execution Workflow
执行流程
Step 1 — Identify reporting period
Use to find the latest quarterly or annual filing. Confirm the period with the user before proceeding.
longbridge filing --helpStep 2 — Collect data & analyze
See references/workflow.md
Step 3 — Update valuation
See references/valuation-methodologies.md
Step 4 — Generate DOCX report
See references/report-structure.md
Step 5 — Output conversation summary
See references/summary-card-spec.md
步骤1 — 确定报告期
使用 查找最新的季度或年度公告。继续操作前需与用户确认报告期。
longbridge filing --help步骤2 — 数据收集与分析
详见 references/workflow.md
步骤3 — 更新估值
详见 references/valuation-methodologies.md
步骤4 — 生成DOCX报告
详见 references/report-structure.md
步骤5 — 输出对话摘要
详见 references/summary-card-spec.md
Output
输出内容
- DOCX report: (8-12 pages, 8-12 charts)
[SYMBOL]_Q[N]_[YEAR]_Earnings_Update.docx - Conversation summary: 8-module structured output directly in chat
IMPORTANT: Do NOT append a Sources section or reference links to the conversation output. All citations belong in the DOCX only.
- DOCX报告:(8-12页,含8-12张图表)
[SYMBOL]_Q[N]_[YEAR]_Earnings_Update.docx - 对话摘要:直接在聊天中输出8模块结构化内容
重要提示:请勿在对话输出中添加来源章节或参考链接。所有引用仅需放入DOCX报告中。
MCP fallback
MCP fallback方案
If the local CLI is unavailable () and the user has run , the same data is reachable through MCP. Subcommand → MCP tool mapping:
longbridgecommand not found: longbridgeclaude mcp add --transport http longbridge https://openapi.longbridge.com/mcp| CLI subcommand | MCP tool |
|---|---|
| |
| |
| |
| |
| |
| |
| |
| |
| |
MCP-only extras worth pulling in for Step 3 valuation:
- — historical PE/PB time series for percentile context
mcp__longbridge__valuation_history - — industry-relative position
mcp__longbridge__industry_valuation_dist - /
mcp__longbridge__profit_analysis— only if the user wants a portfolio-level P&L view alongside the single-name updateprofit_analysis_detail
若本地 CLI不可用(提示 ),且用户已运行 ,则可通过MCP获取相同数据。子命令与MCP工具映射关系:
longbridgecommand not found: longbridgeclaude mcp add --transport http longbridge https://openapi.longbridge.com/mcp| CLI子命令 | MCP工具 |
|---|---|
| |
| |
| |
| |
| |
| |
| |
| |
| |
在步骤3估值环节,可调用MCP专属工具补充数据:
- — 历史PE/PB时间序列,用于百分位对比
mcp__longbridge__valuation_history - — 行业相对估值定位
mcp__longbridge__industry_valuation_dist - /
mcp__longbridge__profit_analysis— 仅当用户需要在个股更新之外查看组合层面损益视图时使用profit_analysis_detail
Related skills
关联Skill
This skill is the heaviest in the family (institutional-grade 8–12 page DOCX). For lighter or differently-framed asks, defer to a sibling:
| User asks for ... | Use |
|---|---|
| Historical PE/PB percentile, "is X expensive vs its own history / industry?" | |
| 5-dimension KPI overview (revenue / margins / ROE / dividend / consensus) without a DOCX deliverable | |
| Cross-symbol matrix, "X vs Y vs Z" | |
| Classified news + filings + community sentiment for a single name | |
| Daily incremental briefing across the user's watchlist | |
| Live quote / valuation indices | |
If the user wants the full earnings DOCX plus one of the above (e.g. "earnings update on TSLA and how it compares to Ford"), do this skill first, then chain to the other.
本Skill是同系列中功能最全面的(生成机构级8-12页DOCX报告)。对于轻量化或不同场景的需求,可使用其他关联Skill:
| 用户需求 | 对应Skill |
|---|---|
| 历史PE/PB百分位、“X相对于自身历史/行业是否高估?” | |
| 五维度KPI概览(营收/利润率/ROE/股息/一致预期),无需生成DOCX报告 | |
| 跨标的对比矩阵、“X vs Y vs Z” | |
| 个股分类新闻+公告+社区舆情 | |
| 用户关注标的每日增量简报 | |
| 实时报价/估值指数 | |
若用户需要完整财报DOCX报告+上述某一项需求(例如:“特斯拉财报更新及与福特的对比分析”),请先执行本Skill,再调用对应关联Skill。
Reference Files
参考文件
| File | Contents | When to Read |
|---|---|---|
| workflow.md | Data collection steps, beat/miss framework, segment/margin/guidance analysis | Before analysis |
| valuation-methodologies.md | DCF, trading comps, precedent transactions — full methodology | During valuation |
| report-structure.md | Page-by-page DOCX templates, table and chart formatting, citation rules | Before generating report |
| summary-card-spec.md | 8-module conversation summary format with examples | When outputting summary |
| best-practices.md | Quality checklist, common mistakes, headline examples | Quality check |
| 文件 | 内容 | 阅读时机 |
|---|---|---|
| workflow.md | 数据收集步骤、业绩达标/未达标分析框架、业务板块/利润率/业绩指引分析方法 | 分析前 |
| valuation-methodologies.md | DCF、可比公司估值、先例交易估值——完整方法论 | 估值环节 |
| report-structure.md | DOCX报告逐页模板、表格与图表格式规范、引用规则 | 生成报告前 |
| summary-card-spec.md | 8模块对话摘要格式及示例 | 输出摘要时 |
| best-practices.md | 质量检查清单、常见错误示例、标题撰写范例 | 质量检查环节 |