Finance Skills is a collection of agent skills for financial analysis and trading, covering activities such as company valuation, earnings research, market analysis, and options calculations. It is for users who want coding agents to perform structured finance workflows, and the catalogue contains its skills, plugins, instructions, and MCP integration.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add himself65/finance-skills --skill startup-analysisgit clone --depth 1 https://github.com/himself65/finance-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/himself65/finance-skills/startup-analysis)<a href="https://agentmods.dev/skills/himself65/finance-skills/startup-analysis"><img src="https://agentmods.dev/badge/skills/himself65/finance-skills/startup-analysis.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00192 | $0.01997 |
| Opus 5 | $0.00096 | $0.00999 |
| Sonnet 5 | $0.00038 | $0.00399 |
| Haiku 4.5 | $0.00019 | $0.00200 |
Grade A, and why
startup-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Startup Analysis
Produces a multi-perspective analysis of a startup, examining it through three lenses that each reveal different aspects of company health and potential:
- VC Investor Lens — Is this a good investment? Market size, unit economics, growth trajectory, team quality, defensibility
- Job Applicant Lens — Should I work here? Equity value, runway risk, culture signals, career growth, compensation fairness
- CEO/Founder Lens — How healthy is this company? Product-market fit, burn efficiency, competitive moat, organizational health
Each perspective surfaces insights the others miss. A company can be a great investment but a terrible place to work (or vice versa). The goal is to give the user a 360-degree view so they can make informed decisions.
Step 1: Gather Information
Before analyzing, collect as much public information as possible about the startup. Use web search, the company's website, Crunchbase data, press coverage, and any other available sources.
Key data to gather:
| Category | What to find |
|---|---|
| Basics | Founded year, HQ location, employee count, what the product does |
| Funding | Total raised, last round (size, date, valuation if known), key investors |
| Product | What they sell, who buys it, pricing model, key competitors |
| Traction | Users, revenue (if public), growth signals, notable customers |
| Team | Founders' backgrounds, key hires, LinkedIn headcount trends |
| Market | Industry, market size estimates, tailwinds/headwinds |
| News | Recent press, product launches, partnerships, layoffs, pivots |
If certain data isn't publicly available (e.g., revenue for private companies), note the gap and infer what you can from indirect signals (hiring pace, customer logos, web traffic proxies, job postings).
When information is insufficient
Many startups — especially early-stage or niche ones — have limited public presence. If web search does not return enough information to produce a meaningful analysis (e.g., you can't determine what the company does, who founded it, or how it's funded), ask the user to provide the company's website URL before proceeding. The company website is often the single most information-dense source, and reading it directly (about page, pricing page, team page, blog) can fill most gaps.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 185 lines · 192 tokens per session scan A 71b7b2ec563d
startup-analysis is a skill published in the GitHub repository himself65/finance-skills (3,290 stars, last pushed 10d ago), licensed MIT. It adds 192 tokens to every session and 1,997 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
quotient
Prediction-market intelligence for Polymarket agents. Quotient runs a multi-role AI forecasting pipeline over 1,600+ sources and publishes daily trade signals with side, entry prices, conviction tiers, capacity, and convergence reads. Pull forecasts (with what-changed deltas), recent sources (articles + X posts), the…
delu-oracle
Full-cognition token analysis for Base EVM tokens via the deluagent oracle. Pass a CA or cashtag, get back a flat decision header (action, conviction, entry/stop/size, read) plus full cognition report. Tiered x402 pricing — 100M+ DELU free, 50M+ 50k DELU, public 250k DELU. Sequential calls only.
lonestaroracle-data
Live pay-per-call data for crypto and DeFi protocol risk, funding rates, open interest, liquidations, stablecoin health, macro, equities, and on-chain intelligence — settled per query in USDC on Base via x402, no signup or API key.
backtesting-sim
Backtesting and simulation: vectorized backtesting, paper trading simulation, strategy A/B testing, automated strategy building, natural language to strategy, and trading plan generation. USE FOR: backtest, backtesting, paper trading, simulation, strategy builder, A/B test strategies, natural language strategy…
cross-asset-relationships
Cross-asset and quantitative analysis: pair correlations, correlation heatmaps, currency strength, cross-timeframe divergence, intermarket analysis, market breadth, carry trades, swap rates, risk premia, and multi-pair baskets. USE FOR: correlation, currency strength, intermarket, market breadth, carry trade, swap…
freqtrade-bot
Freqtrade — open-source Python crypto trading bot. Backtesting, hyperopt (ML parameter optimization), FreqAI (self-training adaptive strategies), Telegram + WebUI control. Supports Binance, Kraken, Bybit, OKX, Gate.io (spot + futures). SQLite trade h.