Skip to content
Back to search

invest-skill

SkillGitHubIncomplete

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 15 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/yennanliu/InvestSkill with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/yennanliu/InvestSkill'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/yennanliu--investskill/badge.svg)](/listings/yennanliu--investskill)

HTML

<a href="/listings/yennanliu--investskill"><img src="/api/listings/yennanliu--investskill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

**One command, any AI agent** — [pick yours on the website](https://yennj12.js.org/InvestSkill/#install):

# Claude Code
curl -fsSL https://raw.githubusercontent.com/yennanliu/InvestSkill/main/install.sh | bash -s -- -a claude

# Swap the agent: cursor · copilot · gemini · codex · opencode · any
curl -fsSL https://raw.githubusercontent.com/yennanliu/InvestSkill/main/install.sh | bash -s -- -a cursor

The installer copies every framework into `.investskill/prompts/` and wires up your agent's own entry point — nothing else runs on your machine:

| `-a` | Agent | Wires up | |------|-------|----------| | `claude` | Claude Code | `.claude/skills/<skill>/SKILL.md` (slash commands) | | `cursor` | Cursor | `.cursor/rules/investskill.mdc` | | `copilot` | GitHub Copilot | `.github/copilot-instructions.md` | | `gemini` | Gemini CLI | `GEMINI.md` | | `codex` | Codex | `AGENTS.md` | | `opencode` | OpenCode | `AGENTS.md` | | `any` | ChatGPT, Claude.ai, Ollama, … | `.investskill/prompts/` only — paste and go |

Add `-g` to install for your user instead of one project, `-d DIR` to target another directory, or `-h` for all options. Existing instruction files are appended to, never overwritten, and re-running is a no-op. Read it first if you'd rather not pipe to `bash`: [install.sh](install.sh).

**Claude Code via the plugin marketplace** — full slash-command support:

claude
/plugin marketplace add yennanliu/InvestSkill
/plugin install us-stock-analysis@invest-skill
/us-stock-analysis:stock-eval AAPL

**Or clone the repo** — every framework in `prompts/`, use it anywhere:

git clone https://github.com/yennanliu/InvestSkill.git
cd InvestSkill

# Cursor
cursor .
# → @prompts/stock-eval.md Evaluate Apple

# Gemini CLI
gemini
# → @prompts/stock-eval.md Evaluate Apple

# Any LLM — paste the prompt file directly
cat prompts/stock-eval.md | pbcopy

> Full platform guides: [Claude Code](README-claude-code.md) · [Cursor](README-cursor.md) · [Gemini CLI](README-gemini.md) · [Ollama](README-ollama.md)

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 45 lines
  1. {
  2. "name": "invest-skill",
  3. "owner": {
  4. "name": "yennanliu",
  5. "email": "yennanliu@users.noreply.github.com"
  6. },
  7. "metadata": {
  8. "description": "Professional investment analysis and stock evaluation skills for US markets — 34 analysis frameworks (+ 3 aliases, 2 output tools) covering fundamental, technical, valuation and financial-report analysis, forensic accounting, credit check, head-to-head compare, ETF analysis, earnings preview, thesis tracking, risk stress test, tax lens, fact-check, industry supply-chain mapping, bear-case red-teaming, staged position laddering, trade post-mortem, result validation, charting, and full comprehensive reports",
  9. "version": "1.15.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "us-stock-analysis",
  14. "source": "./plugins/us-stock-analysis",
  15. "description": "Comprehensive US stock evaluation: fundamental, technical, economic, multi-method valuation, financial report analysis, forensic accounting, credit check, head-to-head compare, ETF analysis, earnings preview, thesis tracking, risk stress test, tax lens, fact-check, options, dividends, insider trading, institutional ownership, bear-case red-teaming, position laddering, trade post-mortem, and more",
  16. "version": "1.15.0",
  17. "author": {
  18. "name": "yennanliu"
  19. },
  20. "category": "finance",
  21. "keywords": [
  22. "stock",
  23. "investment",
  24. "analysis",
  25. "us-markets",
  26. "finance",
  27. "dcf",
  28. "valuation",
  29. "10-k",
  30. "10-q",
  31. "financial-reports",
  32. "etf-analysis",
  33. "tax-lens",
  34. "earnings-preview",
  35. "thesis-tracking",
  36. "risk-stress-test",
  37. "fact-check",
  38. "forensic-accounting",
  39. "credit-check",
  40. "compare",
  41. "trade-postmortem"
  42. ]
  43. }
  44. ]
  45. }
README.md · README · 331 lines · 2 findings marked
  1. <div align="center">
  2. # InvestSkill
  3. **Professional investment analysis frameworks for US stocks — works on every AI platform**
  4. **No API keys · No subscriptions · 100% free**
  5. [![Cost: $0](https://img.shields.io/badge/cost-%240%20%C2%B7%20no%20API%20keys-22c55e?style=flat-square)](#no-api-keys-no-cost)
  6. [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg?style=flat-square)](LICENSE)
  7. [![GitHub Stars](https://img.shields.io/github/stars/yennanliu/InvestSkill?style=flat-square&color=gold)](https://github.com/yennanliu/InvestSkill/stargazers)
  8. [![Release](https://img.shields.io/github/v/release/yennanliu/InvestSkill?style=flat-square&color=22c55e)](https://github.com/yennanliu/InvestSkill/releases)
  9. [![Tests](https://img.shields.io/github/actions/workflow/status/yennanliu/InvestSkill/ci.yml?style=flat-square&label=tests)](https://github.com/yennanliu/InvestSkill/actions)
  10. [Documentation](https://yennj12.js.org/InvestSkill/) · [Learn Investing](https://yennj12.js.org/InvestSkill/learning.html) · [Cookbook](https://yennj12.js.org/InvestSkill/cookbook.html) · [繁體中文](README-zh-TW.md)
  11. </div>
  12. ---
  13. ## What is InvestSkill?
  14. InvestSkill is a collection of **34 structured analysis frameworks** that turn any AI assistant into an institutional-quality investment analyst. There is no runtime — every skill is a prompt that works in Claude Code, Cursor, Gemini CLI, GitHub Copilot, ChatGPT, or any other LLM.
  15. **Nothing to sign up for, nothing to pay for.** No API key, no data-vendor subscription, no billing setup — you bring the AI assistant you already use (a free tier or a local model works too) and InvestSkill is just markdown. See [No API keys, no cost](#no-api-keys-no-cost).
  16. ```
  17. Ask your AI: "Evaluate AAPL using the stock-eval framework"
  18. Get back: Piotroski score · ROIC · moat rating · buy/hold/sell signal
  19. ```
  20. <div class="home-card">
  21. <span class="home-card-icon">🎓</span>
  22. <div class="home-card-body">
  23. <div class="home-card-title">New to investing? Start with the Learning guide</div>
  24. <p>A fifteen-lesson field guide, in plain English and Traditional Chinese: Part I teaches the concepts behind every skill — reading a balance sheet, valuing a business, holding a portfolio — and Part II the practical foundations: accounts and orders, an ETF core, taxes (including for non-US investors), earnings season, the psychology that protects the plan, the macro and Fed cycle, and options for stock holders. No finance degree required.</p>
  25. <p><a class="home-card-cta" href="https://yennj12.js.org/InvestSkill/learning.html">Start learning →</a></p>
  26. </div>
  27. </div>
  28. ---
  29. ## Quick Start
  30. **One command, any AI agent** — [pick yours on the website](https://yennj12.js.org/InvestSkill/#install):
  31. ```bash
  32. # Claude Code
  33. curl -fsSL https://raw.githubusercontent.com/yennanliu/InvestSkill/main/install.sh | bash -s -- -a claude
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 49 on GitHub
  34. # Swap the agent: cursor · copilot · gemini · codex · opencode · any
  35. curl -fsSL https://raw.githubusercontent.com/yennanliu/InvestSkill/main/install.sh | bash -s -- -a cursor
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 52 on GitHub
  36. ```
  37. The installer copies every framework into `.investskill/prompts/` and wires up your agent's own entry point — nothing else runs on your machine:
  38. | `-a` | Agent | Wires up |
  39. |------|-------|----------|
  40. | `claude` | Claude Code | `.claude/skills/<skill>/SKILL.md` (slash commands) |
  41. | `cursor` | Cursor | `.cursor/rules/investskill.mdc` |
  42. | `copilot` | GitHub Copilot | `.github/copilot-instructions.md` |
  43. | `gemini` | Gemini CLI | `GEMINI.md` |
  44. | `codex` | Codex | `AGENTS.md` |
  45. | `opencode` | OpenCode | `AGENTS.md` |
  46. | `any` | ChatGPT, Claude.ai, Ollama, … | `.investskill/prompts/` only — paste and go |
  47. Add `-g` to install for your user instead of one project, `-d DIR` to target another directory, or `-h` for all options. Existing instruction files are appended to, never overwritten, and re-running is a no-op. Read it first if you'd rather not pipe to `bash`: [install.sh](install.sh).
  48. **Claude Code via the plugin marketplace** — full slash-command support:
  49. ```bash
  50. claude
  51. /plugin marketplace add yennanliu/InvestSkill
  52. /plugin install us-stock-analysis@invest-skill
  53. /us-stock-analysis:stock-eval AAPL
  54. ```
  55. **Or clone the repo** — every framework in `prompts/`, use it anywhere:
  56. ```bash
  57. git clone https://github.com/yennanliu/InvestSkill.git
  58. cd InvestSkill
  59. # Cursor
  60. cursor .
  61. # → @prompts/stock-eval.md Evaluate Apple
  62. # Gemini CLI
  63. gemini
  64. # → @prompts/stock-eval.md Evaluate Apple
  65. # Any LLM — paste the prompt file directly
  66. cat prompts/stock-eval.md | pbcopy
  67. ```
  68. > Full platform guides: [Claude Code](README-claude-code.md) · [Cursor](README-cursor.md) · [Gemini CLI](README-gemini.md) · [Ollama](README-ollama.md)
  69. ---
  70. ## No API Keys, No Cost
  71. InvestSkill is **completely free to use** — there is nothing to buy, register, or configure.
  72. | | |
  73. |---|---|
  74. | **API keys** | **None.** No OpenAI / Anthropic / Alpha Vantage / Polygon key. The plugin never calls an endpoint — there is no code to call one with. |
  75. | **Subscriptions** | **None.** No paid tier, no seats, no usage metering, no account. |
  76. | **Market-data fees** | **None.** No Bloomberg, no paid data feed. The AI reads public filings and free sources — or you paste the numbers in yourself. |
  77. | **Install / runtime** | **None.** Every skill is a plain markdown prompt. Nothing runs on your machine, so nothing phones home. |
  78. | **License** | **MIT.** Free to use, fork, and modify — for personal or commercial work. |
  79. **The only thing you need is an AI assistant you already have.** That can be a paid plan (Claude Code, Cursor, Copilot), a free tier (ChatGPT, Gemini, Claude.ai), or a fully offline local model via [Ollama](README-ollama.md) — in which case the total cost of running every framework is literally zero.
  80. > Because there's no API, there's also no telemetry: InvestSkill never sees your tickers, your holdings, or your analysis. See [Data & Accuracy](site/content/DATA-AND-ACCURACY.md) for where the numbers actually come from.
  81. **In Traditional Chinese, too.** Add `--lang zh-TW` to any framework and the whole analysis comes back in 繁體中文 — headings, narrative and tables — while the Data & Sources labels, the signal box and its JSON footer stay in English so tools can still read them. The site has a [Chinese Skill Reference](https://yennj12.js.org/InvestSkill/skills-zh-tw.html) and a [Non-US Investor Guide](https://yennj12.js.org/InvestSkill/non-us-guide.html).
  82. **Bring your own data.** The filing skills (`10k-digest`, `financial-report-analyst`, `fact-check`) carry a keyless SEC EDGAR recipe a tool-enabled assistant can follow by itself. If yours can't browse, two optional zero-dependency scripts fetch the primary source for you to paste — `node scripts/fetch-edgar.js AAPL --form 10-K` saves the filing as text, `node scripts/fetch-fundamentals.js AAPL` builds a reconciled statement pack from the SEC's XBRL facts. Neither is part of the plugin. Details on the [Data & Accuracy](site/content/DATA-AND-ACCURACY.md#bring-your-own-data-the-keyless-edgar-path) page.
  83. ---
  84. ## The 34 Frameworks
  85. ### Core Stock Analysis
  86. | Skill | What it produces |
  87. |-------|-----------------|
  88. | `stock-eval` | Piotroski F-Score, ROIC, quality rating, go/no-go signal |
  89. | `technical-analysis` | MA chart (30/60/90/200/365d) with trade entry/target/stop, chart patterns, RSI/MACD, MTF alignment, Ichimoku |
  90. | `stock-valuation` | P/E · P/S · EV/EBITDA · comparable company multiples |
  91. | `economics-analysis` | Macro indicators, recession probability, rate sensitivity |
  92. | `compare` | Compare 2–5 stocks head to head on one table — business quality, growth, valuation, balance sheet, momentum, risks and catalysts — then argue the pick: which one, why, what would flip it, and whether owning more than one adds anything |
  93. ### Financial Reports
  94. | Skill | What it produces |
  95. |-------|-----------------|
  96. | `financial-report-analyst` | 10-K / 10-Q key findings, red flags, accounting quality |
  97. | `10k-digest` | Structured markdown digest — abstract, section summaries, metrics table, refs (EN / 繁中) |
  98. | `earnings-call-analysis` | Management tone, guidance delta, hidden risks |
  99. | `forensic-accounting` | Earnings-quality forensics — Beneish M-Score, Altman Z, Sloan accruals ratio, cash-vs-earnings divergence, SBC-adjusted FCF, revenue-recognition and capitalisation checks, auditor and related-party flags, scored as a Manipulation Risk Score 0–10 |
  100. | `credit-check` | Balance-sheet solvency and refinancing risk — debt maturity wall, interest coverage trend, leverage vs. covenants, liquidity runway, ratings and spreads, the cost of refinancing at today's rates, and an equity-holder verdict, scored as a Credit Health Score 0–10 |
  101. ### Market Monitoring
  102. | Skill | What it produces |
  103. |-------|-----------------|
  104. | `insider-trading` | SEC Form 4 patterns, net buy/sell sentiment |
  105. | `institutional-ownership` | 13F holdings changes, smart money flows |
  106. | `dividend-analysis` | Payout safety score, yield trap detection |
  107. | `short-interest` | Short ratio, days-to-cover, squeeze probability |
  108. ### Advanced Research
  109. | Skill | What it produces |
  110. |-------|-----------------|
  111. | `competitor-analysis` | Moat score, Porter's Five Forces, market share |
  112. | `industry-map` | Supply/value-chain graph (upstream→downstream), chokepoints, margin-pool migration, second-order ideas |
  113. | `options-analysis` | Greeks, IV rank, earnings play strategy selection |
  114. | `portfolio-review` | Allocation health, concentration risk scoring, correlation analysis, tax-loss harvesting, rebalancing plan |
  115. | `sector-analysis` | Sector rotation signals, valuation tables, seasonality calendar, momentum scoring |
  116. | `stock-screener` | Multi-ticker ranking across valuation, quality, momentum, sentiment, and growth; leaderboard + top picks + avoid list |
  117. | `catalyst-calendar` | Forward-looking 90-day event calendar: earnings, macro events, catalysts, impact scoring, event-driven strategies |
  118. | `bear-case` | Deliberate short-seller red-team: bear thesis, accounting red flags, downside target, thesis-killers (counterevidence for any bull thesis) |
  119. | `position-ladder` | Staged entry ladder + trim/re-add cycle for a single holding: share-count floor/ceiling, blended cost basis, wash-sale flags, total-return-vs-buy-and-hold check, thesis-break gate |
  120. | `thesis-tracker` | Write, save, and re-check an investment thesis — KPIs with thresholds, invalidation triggers, catalysts, a pre-mortem, and a decision log; `--update` re-reads the saved file against new data and returns INTACT / WEAKENED / BROKEN |
  121. | `etf-analysis` | ETF / index-fund due diligence — expense ratio vs. category, tracking difference, liquidity, holdings concentration and tilt, overlap with your other positions, distribution and capital-gains history, structure warnings, and an ETF-vs-top-holdings comparison, scored as an ETF Fitness Score 0–10 |
  122. | `earnings-preview` | The before-earnings skill — consensus vs. whisper, 8-quarter beat rate and post-print move distribution, options-implied vs. realized move, what the current price already assumes, the KPIs to watch, and a three-scenario grid (beat-and-raise / beat-and-lower / miss) with expected reaction and a position rule for each |
  123. | `tax-lens` | US tax mechanics for a position or portfolio — short- vs. long-term treatment, wash-sale window check, qualified-dividend holding-period test, lot selection (specific-ID vs. FIFO), tax-loss-harvesting pairs, account placement, estimated annual tax drag — plus a --non-us module (W-8BEN, dividend withholding and treaty rates, capital-gains treatment, US estate-tax exposure, UCITS alternatives). Educational only, never tax advice |
  124. | `risk-stress-test` | Portfolio and position risk report — beta-weighted exposure, historical scenario replay (2008, March 2020, 2022 rate shock, 2025 tariff shock), parametric VaR / CVaR at 95 / 99 %, max-drawdown estimate, correlation-spike scenario, rate / USD / oil sensitivity, liquidity (days to exit at 20 % of ADV), and a Risk Budget Score 0–10 |
  125. | `trade-postmortem` | Review a closed trade or a year of trades — process vs. outcome matrix, plan adherence, the biases that showed up, what the pre-trade skills said, and the one lesson for the journal; reads closed thesis-tracker files |
  126. ### Meta & Output
  127. | Skill | What it produces |
  128. |-------|-----------------|
  129. | `full-report` | Runs 5 / 10 / every applicable framework (`--depth quick` / `standard` / `comprehensive`, `--skip` to leave modules out) and saves a standalone HTML report |
  130. | `report-generator` | Converts any analysis into a professional HTML/PDF report |
  131. | `chart-master` | Mermaid · ASCII · Chart.js visualizations from financial data |
  132. | `result-validator` | Scores any analysis on data quality, methodology, and signal consistency |
  133. | `learning-coach` | Explains any InvestSkill output like a mentor — every metric in plain words, why it matters, its good / bad range, and the lesson that teaches it — then asks 3–5 Socratic questions and "what would change your mind?". --level beginner / intermediate, --lang zh-TW, and a --quiz mode that drills a Learning lesson |
  134. | `fact-check` | Claim-level verification of any report or data set — extract every figure and factual claim, check each against a primary source (SEC filing, company IR, FRED, exchange data, or the user's own document), recompute derived numbers, mark ✅ verified / ⚠️ mismatch / ❓ unverifiable, and re-issue the report with inline citations and a References section; Verification Score 0–10 |
  135. | `basket-report` | Output tool, not counted as a framework — 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 |
  136. ### Aliases (redirects)
  137. Three earlier skills were absorbed into larger ones. They are still installed so old references keep working, but they are aliases, not frameworks, and are not counted above.
  138. | Alias | Redirects to |
  139. |-------|--------------|
  140. | `fundamental-analysis` | `stock-eval` (statement-level deep dive is a section of it) |
  141. | `dcf-valuation` | `stock-valuation` (DCF is Method 1 of its multi-method model) |
  142. | `research-bundle` | `full-report` (use `--depth quick / standard / comprehensive`) |
  143. ---
  144. ## Example Workflows
  145. **5-minute stock screen**
  146. ```
  147. /stock-eval NVDA
  148. /stock-eval AMD
  149. → Piotroski scores + quality rating for quick go/no-go
  150. ```
  151. **Complete due diligence**
  152. ```
  153. /stock-eval AAPL
  154. /stock-valuation AAPL --methods all
  155. /competitor-analysis AAPL
  156. /financial-report-analyst AAPL 10-K
  157. → Full investment thesis in one session
  158. ```
  159. **Earnings season playbook**
  160. ```
  161. /stock-eval TICKER ← pre-earnings baseline
  162. /earnings-call-analysis TICKER ← post-earnings [paste transcript]
  163. /options-analysis TICKER --earnings ← vol expectations + strategy
  164. → Complete earnings thesis
  165. ```
  166. **Export a professional report**
  167. ```
  168. /full-report AAPL
  169. → Saves output/AAPL_report_2026-05-12.html
  170. (hero header · metric cards · interactive Chart.js · signal block)
  171. ```
  172. ---
  173. ## Output Format
  174. Every skill ends with a standardized **Investment Signal Block**:
  175. ```
  176. ╔══════════════════════════════════════════════╗
  177. ║ INVESTMENT SIGNAL ║
  178. ╠══════════════════════════════════════════════╣
  179. ║ Signal: BULLISH / NEUTRAL / BEARISH ║
  180. ║ Confidence: HIGH / MEDIUM / LOW ║
  181. ║ Horizon: SHORT / MEDIUM / LONG-TERM ║
  182. ║ Score: X.X / 10 ║
  183. ╠══════════════════════════════════════════════╣
  184. ║ Action: BUY / HOLD / SELL ║
  185. ║ Conviction: STRONG / MODERATE / WEAK ║
  186. ╚══════════════════════════════════════════════╝
  187. ```
  188. HTML reports render this as a styled dark panel with a score progress bar, ghost watermark text, and a teal/sky gradient accent — see [report-generator](prompts/report-generator.md) for the full design system.
  189. ---
  190. ## Platform Support
  191. | Platform | Setup | How it works |
  192. |----------|-------|-------------|
  193. Every platform installs with the same one-command [installer](install.sh) — only the `-a` agent changes (see [Quick Start](#quick-start)).
  194. | Platform | Setup | How it works |
  195. |----------|-------|-------------|
  196. | **Claude Code** | `install.sh -a claude`, or the plugin marketplace | 39 native slash commands (34 frameworks + 3 aliases + 2 output tools) |
  197. | **Cursor IDE** | `install.sh -a cursor` | Auto-loads `.cursor/rules/investskill.mdc` |
  198. | **Gemini CLI** | `install.sh -a gemini` | Auto-loads `GEMINI.md` |
  199. | **GitHub Copilot** | `install.sh -a copilot` | Auto-loads `.github/copilot-instructions.md` |
  200. | **Codex / OpenCode** | `install.sh -a codex` / `-a opencode` | Auto-loads `AGENTS.md` |
  201. | **Ollama (local models)** | `install.sh -a any`, run a local model | Offline open-source models, no API key — [guide](README-ollama.md) |
  202. | **ChatGPT / Claude.ai / any LLM** | `install.sh -a any`, paste a `prompts/*.md` file | Platform-agnostic markdown |
  203. ---
  204. ## Learn the Frameworks
  205. New to investing, or unsure which skill to reach for? Start here:
  206. | Guide | What it gives you |
  207. |-------|-------------------|
  208. | [Concepts](site/content/CONCEPTS.md) | The mental models behind the metrics — quality vs. value vs. growth, intrinsic value, moats, risk, and the signal block |
  209. | [Glossary](site/content/GLOSSARY.md) | Plain-English definitions, formulas, and good/bad ranges for every metric the skills emit |
  210. | [Choose a Skill](site/content/CHOOSE-A-SKILL.md) | Map your goal to the right framework, plus comparisons of the ones that overlap |
  211. | [Use Cases](site/content/USE-CASES.md) | End-to-end journeys by investor type — income, first-timer, earnings, macro, skeptic |
  212. | [Data & Accuracy](site/content/DATA-AND-ACCURACY.md) | Where the numbers come from, how to spot hallucinations, and how to validate output |
  213. ---
  214. ## Documentation
  215. | Resource | Description |
  216. |----------|-------------|
  217. | [Live Docs Site](https://yennj12.js.org/InvestSkill/) | Full documentation — light / dark theme, English and 繁體中文 |
  218. | [Cookbook](https://yennj12.js.org/InvestSkill/cookbook.html) | Walkthrough examples and use cases |
  219. | [Skill Reference](https://yennj12.js.org/InvestSkill/skills.html) | All 34 frameworks, one browsable page each |
  220. | [Claude Code Guide](README-claude-code.md) | Plugin install + all slash commands |
  221. | [Cursor Guide](README-cursor.md) | Auto-loading rules + `@prompts/` usage |
  222. | [Gemini CLI Guide](README-gemini.md) | File references + multi-framework chains |
  223. | [Ollama Guide](README-ollama.md) | Local open-source models, offline & no API key |
  224. | [Adding Skills](ADDING-NEW-SKILLS.md) | Contributor walkthrough — `new-skill.js` scaffolds and wires a skill |
  225. | [FAQ](FAQ.md) | 45+ answers on install, platforms, usage and versions |
  226. | [Changelog](CHANGELOG.md) | Version history |
  227. ### Sandbox and further reading
  228. InvestSkill itself has no runtime. Two things live outside this repository:
  229. | Where | What it is |
  230. |-------|------------|
  231. | [**InvestSkill-test**](https://github.com/yennanliu/InvestSkill-test) — the sandbox | The sibling repo where the frameworks are actually run. GitHub Actions clones the latest InvestSkill and publishes the results: [live showcases](https://yennj12.js.org/InvestSkill-test/showcase/live/index.html) (every weekday, one randomly picked ticker, every run kept), a [curated showcase](https://yennj12.js.org/InvestSkill-test/showcase/index.html) on a four-stock basket, and a workflow for trying any skill at any branch or open PR. Output there is model-written and unreviewed. |
  232. | [**Blog posts on US stocks (美股)**](https://yennj12.js.org/yennj12_blog_V4/search/?q=%E7%BE%8E%E8%82%A1) | Further reading by the author on the YennJ12 Engineering Blog. Separate from this repo: not part of the frameworks and not covered by its tests. |
  233. ---
  234. ## Contributing
  235. See [ADDING-NEW-SKILLS.md](ADDING-NEW-SKILLS.md) for the full process. The short version:
  236. 1. `node scripts/new-skill.js <name> --category <core|reports|monitoring|advanced|meta> --title "…" --desc "…"` — scaffolds `SKILL.md` with the full output contract and wires the skill into the site, READMEs, cross-AI configs, and CHANGELOG
  237. 2. Write the analysis in `plugins/us-stock-analysis/skills/<name>/SKILL.md`, then `node scripts/sync-prompts.js <name>` — `prompts/<name>.md` is generated from it (skills are auto-discovered; no `plugin.json` change)
  238. 3. Run `npm test` — structure, prompt sync, skill contract, counts, and install script must all pass
  239. [Open an issue](https://github.com/yennanliu/InvestSkill/issues) to report bugs · [Start a discussion](https://github.com/yennanliu/InvestSkill/discussions) to propose features.
  240. ---
  241. **Version:** latest — see [CHANGELOG](CHANGELOG.md) · **Frameworks:** 34 analysis frameworks (+ 3 aliases, 2 output tools) · **Skills:** 39 · **Platforms:** 7 · **License:** MIT · **Tests:** all passing
  242. ---
  243. <div align="center">
  244. *For educational and research purposes only. Not financial advice.*
  245. *Always consult a qualified financial advisor before making investment decisions.*
  246. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.