Rq Thesis Tracker
Generate a structured investment-thesis tracking report from RiceQuant-style JSON inputs in a data directory for a single listed company.
Overview
rq-thesis-tracker is an agent skill for the Operate phase that assembles a company investment-thesis tracking report from a documented JSON data contract in a local data directory.
Install
npx skills add https://github.com/ricequant/ricequant-skills --skill rq-thesis-trackerWhat is this skill?
- Chinese-language report template with placeholders for thesis snapshot, pillar verification, and catalyst tracking
- Documented data contract: thesis_definition.json plus instrument, financials, price, valuation, dividend, and announceme
- Optional pillars with metric, operator, threshold, and falsifier fields for systematic validation
- Sections for market performance vs benchmark, capital return, shareholder structure, and risk monitoring
- Flexible JSON envelopes: top-level data array/object or raw array/object per file
- 12+ named raw input files in --data-dir (thesis_definition optional)
- Report outline with 10 main sections from executive summary through appendix
Adoption & trust: 1 installs on skills.sh; 26 GitHub stars; 2/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You maintain an equity thesis in spreadsheets and notes but lack a repeatable report that ties pillars, catalysts, and new filings to one dated artifact.
Who is it for?
Solo investors and indie research stacks using RiceQuant-style exports who want agent-generated thesis maintenance reports.
Skip if: Builders without listed-equity data feeds, non-finance product work, or anyone needing trade execution rather than narrative tracking.
When should I use this skill?
You have a --data-dir of thesis and market JSON for one company and need the standardized thesis tracking report generated.
What do I get? / Deliverables
You get a filled thesis-tracker report with verification, performance, catalyst, and risk sections driven by your latest JSON inputs.
- Completed investment thesis tracking report (markdown/text from template)
- Filled pillar verification and risk monitoring sections
- Update log and appendix口径说明
Recommended Skills
Journey fit
Thesis tracking is an Operate activity: you already hold a view and need ongoing verification, catalyst logs, and risk monitoring—not initial idea research. Iterate fits because the skill ingests rolling price, financials, announcements, and pillar checks to update conviction and response plans over time.
How it compares
A structured equity report generator from local JSON—not a generic CRM or SaaS analytics skill.
Common Questions / FAQ
Who is rq-thesis-tracker for?
Solo quants and indie builders doing fundamental equity research who already collect RiceQuant-compatible JSON slices per ticker.
When should I use rq-thesis-tracker?
In Operate/iterate when refreshing a holding thesis after new financials, price windows, announcements, or catalyst dates; after Validate/scoping when you first formalize pillars in thesis_definition.json.
Is rq-thesis-tracker safe to install?
The skill processes local research files you supply—review the Security Audits panel on this page and never embed brokerage credentials in the data directory.
SKILL.md
READMESKILL.md - Rq Thesis Tracker
# 投资论文跟踪报告 报告日期：[[REPORT_DATE]] 信息截面：[[AS_OF_TIME]] 公司：[[COMPANY_NAME]]（[[STOCK_CODE]]） 逻辑定义来源：[[THESIS_SOURCE]] ## 执行摘要 [[EXEC_SUMMARY]] ## 论文快照 [[THESIS_SNAPSHOT]] ## 关键支柱验证 [[PILLAR_VERIFICATION]] ## 股价与相对收益回顾 [[MARKET_PERFORMANCE]] ## 资本回报与股东结构 [[CAPITAL_RETURN]] ## 催化剂跟踪 [[CATALYST_TRACKING]] ## 风险监控 [[RISK_MONITORING]] ## 更新日志 [[UPDATE_LOG]] ## 附录：口径说明 [[APPENDIX]] # Thesis Tracker Data Contract ## Raw Inputs The generator looks for these files inside `--data-dir`: - `thesis_definition.json` (optional) - `instrument_meta.json` - `latest_financials.json` - `historical_financials.json` - `roe.json` - `price_6m.json` - `hs300_6m.json` - `pe_ratio.json` - `pb_ratio.json` - `dividend.json` - `shareholder_top10.json` - `announcement_raw.json` - `web_search_findings.json` (optional) Each file may be: - `{ "data": [...] }` - `{ "data": { ... } }` - `[...]` - `{ ... }` ## Thesis Definition `thesis_definition.json` is optional. When provided, it may include: - `thesis_name` - `core_view` - `confidence_label` - `holding_period` - `position_date` - `target_price` - `value` - `currency` - `pillars` - `name` - `metric` - `operator` - `threshold` - `falsifier` (optional) - `rationale` (optional) - `planned_catalysts` - `title` - `expected_window` - `expected_impact` (optional) - `risk_items` - `title` - `initial_assessment` (optional) - `monitor` - `response` (optional) Additional optional fields: - `current_position` / `position` - `direction` Supported metric keys for custom pillars: - `latest_revenue_yoy_pct` - `latest_net_profit_yoy_pct` - `latest_cash_profit_ratio` - `latest_roe` - `price_return_6m_pct` - `excess_return_6m_pct` - `top1_holder_pct` - `top10_holder_pct` Supported operators: - `>` - `>=` - `<` - `<=` - `==` If `falsifier` is omitted, the generator will derive a client-readable default refutation condition from the metric rule. ## Common Identifier Fields Ticker fields: - `order_book_id` - `ticker` - `stock_code` - `symbol` - `code` Company name fields: - `display_name` - `name` - `stock_name` - `company_name` - `symbol_name` - `symbol` ## Financial Records `latest_financials.json` and `historical_financials.json` are expected to include: - `order_book_id` - `quarter` - `info_date` - `revenue` - `net_profit` - `cash_from_operating_activities` The generator deduplicates records by quarter and keeps the latest disclosed version. ## Financial Indicator Records `roe.json` is expected to come from `stock cn financial-indicator` using: - `factor = return_on_equity_weighted_average` Returned fields typically include: - `order_book_id` - `date` - `return_on_equity_weighted_average` `pe_ratio.json` / `pb_ratio.json` should also come from `stock cn financial-indicator` using: - `factor = pe_ratio` - `factor = pb_ratio` Returned fields typically include: - `order_book_id` - `date` - `pe_ratio` or `pb_ratio` ## Price Records `price_6m.json` should include: - `order_book_id` - `datetime` - `close` - `total_turnover` (optional) `hs300_6m.json` should include: - `order_book_id` - `datetime` - `close` ## Dividend Records `dividend.json` may include: - `quarter` - `advance_date` - `declaration_announcement_date` - `book_closure_date` - `ex_dividend_date` - `payable_date` - `dividend_cash_before_tax` - `round_lot` ## Shareholder Records `shareholder_top10.json` may include: - `end_date` - `info_date` - `rank` - `shareholder_name` - `hold_percent_total` - `hold_percent_float` The generator summarizes the latest disclosure period and compares concentration with the previous period when possible. ## Announcement Records `announcement_raw.json` may include: - `info_date` - `title` - `info_type` - `media` - `announcement_link` Low-signal governance boilerplate is filtered out before catalyst classification. When `announcement_link` exists, material realized catalysts should keep the source link so later workflows can read the original PDF/HTML. ## Ex