Skip to content
Finance
Skill

/basket-report

Run a 2–5 stock basket as one linked deliverable — a hub page that states the question and argues the pick, one report per ticker, all from a single shared as-of snapshot; orchestrates compare, full-report and industry-map, with stock-screener first to shortlist a longer list

From plugin
investskill
28539 skills

Claude Code

$ npx -y skills add yennanliu/investskill --skill basket-report --agent claude-code

SKILL.md

basket-report.SKILL.md
description: Run a 2–5 stock basket as one linked deliverable — a hub page that states the question and argues the pick, one report per ticker, all from a single shared as-of snapshot; orchestrates compare, full-report and industry-map, with stock-screener first to shortlist a longer list

Basket Report

⚠️ Data Verification — Do This Before Any Analysis

Before running any analysis, always retrieve the latest market data for every ticker in the basket:

1. **Fetch current price** — use web search or ask the user for the live price, 52-week range, and market cap. Never assume a price from training data. 2. **Confirm key figures** — for **every** ticker, on the **same as-of date**: price, market cap, the last four fiscal years and five quarters of statements, shares outstanding, consensus estimates and the next earnings date. Gather them **once**, save them as the basket snapshot (Phase 1), and run every module from that snapshot — a basket in which two pages quote different prices for the same stock has failed before any analysis starts. 3. **State your data source** — fill in the `Data & Sources` header (next section) so the origin, as-of date, retrieval path, and confidence of every figure are explicit at the top of the output. 4. **Flag stale data explicitly** — if live data is unavailable, display this warning before proceeding:

> ⚠️ **Live data unavailable.** The following analysis uses training-data estimates which may be significantly out of date. Verify all prices and metrics before making any decisions.

Never silently substitute training-data estimates for current prices. When in doubt, ask the user to paste the latest quote.

---

📋 Data & Sources Header — Open Every Output With It

The first thing in the output is this provenance block, filled in — never left as placeholders. It is the standard documented on the [Data & Accuracy](https://yennanliu.github.io/InvestSkill/data-and-accuracy.html) page and the first thing `result-validator` looks for:

Data & Sources
  As of:      <date the figures represent, e.g. 2026-06-30>
  Source:     <primary docs — SEC EDGAR 10-K/10-Q, company IR, FRED, exchange data …>
  Retrieval:  <pasted by user | web/tool retrieval | model memory>
  Confidence: <HIGH | MEDIUM | LOW>
  • `Retrieval: model memory` must be paired with `Confidence: LOW` — memory is a placeholder until confirmed against a primary source.
  • Mixed sources: list each with its own as-of date rather than blending them.
  • Sources disagree on the same figure (a closing price, a deal term): prefer the primary source (SEC filing, company release, exchange data) over an aggregator, then the most recent dated one. Show both values with their sources and dates, say which you used and why, and never average them.
  • Data the user pasted is reported as `pasted by user`; do not upgrade its confidence beyond what the user's own source supports.

---

🌐 Output Language — `--lang zh-TW`

English is the default. With `--lang zh-TW` — or when the user writes in Traditional Chinese and asks for a Chinese answer — write the whole analysis in Traditional Chinese (繁體中文, Taiwan usage), keeping it machine-checkable:

  • **Translate** every heading, narrative paragraph, table header and bullet. Give each metric's English name in brackets the first time it appears — 自由現金流(Free Cash Flow, FCF) — so the reader can match it to the glossary and to English analyses.
  • **Keep in English** tickers, figures and units, SEC form and item names (10-K Item 7, Form 4), the four `Data & Sources` field labels (`As of`, `Source`, `Retrieval`, `Confidence` — the Retrieval value may be written in Chinese, e.g. 使用者提供), and the Investment Signal box and JSON footer exactly as specified — field names and the BULLISH / NEUTRAL / BEARISH, HIGH / MEDIUM / LOW, BUY / HOLD / SELL, STRONG / MODERATE / WEAK values. Tools parse them.
  • Title the invalidation section **論點失效條件(Thesis Invalidation)**, and close with the disclaimer in Chinese: **免責聲明:** 僅供教育用途,非投資建議。
  • Use Taiwan financial terms: 殖利率、本益比、營業利益率、自由現金流、聯準會、選擇權、買權/賣權、除息日、預扣稅.

---

Overview

`full-report` answers "tell me everything about this one stock". `compare` answers "which of these should I own?" and ends in one Markdown table. Neither produces what a person researching a small group of names actually wants to keep: **one deliverable in which every stock has its own report, every report quotes the same prices, and a front page says what the group has in common and which one to pick.** Running `full-report` four times gives four files written on four sets of assumptions, with nothing joining them.

**This skill is an orchestrator, not a new analysis.** It runs existing frameworks over a basket of 2–5 tickers from one shared data snapshot and assembles the results into a small linked site: a hub page, one report per ticker, and a value-chain page when the names share one. It adds no scoring of its own — every number on the hub comes from `compare` or from a per-ticker `full-report`, and the closing signal is the pick's.

| Skill | Question it answers | Output | |-------|---------------------|--------| | `stock-screener` | Which of these 20–50 names deserve a closer look? | One ranked table | | `compare` | Which of these 2–5 should I own, and why? | One table and an argued pick (Markdown) | | `full-report` | What is the whole picture on this one stock? | One HTML report | | **`basket-report`** | **What is the whole picture on these 2–5 stocks, together?** | **A hub page + one report per ticker, linked, on one snapshot** |

**It is the most expensive skill in the plugin.** At the default depth it runs 10 modules per ticker, so a four-stock basket is 40 module runs before the hub. Say so before starting, and offer `--depth quick` (5 per ticker) when the user has not asked for depth.

---

1. Inputs

| Input | Required | Default if unstated | |-------|----------|---------------------| | Tickers | ✅ 2–5 | One ticker → stop and suggest `fu

Read more
@yennanliu
Ships withinvestskill

Professional investment analysis frameworks for US stocks — works on every AI platform

Stars on GitHub

Momentum

stars in total
285
Star history of yennanliu/investskill on GitHub, a chart by star-history.com

Other skills on investskill.

10k-digest

10k-digest

Deep-read a 10-K annual report and output a structured markdown digest — abstract, section summaries, key metrics, and sourced…

bear-case

bear-case

Build the strongest possible bear case against a stock — a deliberate short-seller red-team that argues why NOT to hold,…

chart-master

chart-master

Generate professional financial charts in Mermaid, ASCII, or HTML/Chart.js — MA lines, histograms, candlestick, volume, RSI/MACD,…

compare

compare

Compare 2–5 stocks head to head on one table — business quality, growth, valuation, balance sheet, momentum, risks and catalysts…

competitor-analysis

competitor-analysis

Deep competitive moat analysis, market position assessment, and industry dynamics for one company against its direct rivals. To…

More skills from other plugins.

ccxt-cli

ccxt-cli

CCXT command-line interface (ccxt-cli) for interacting with 100+ cryptocurrency exchanges directly from the terminal — no code…

ccxt6d45k
@ccxt@ccxtInstall Skill

Questions about basket-report.

Which coding agents can use basket-report?
basket-report installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.