The fintech-focused Agent Skills collection — trading, crypto/DeFi & finance skills for Claude Code, Codex, Cursor & 26+ AI tools. By Viprasol Tech.
SaferSkills independently audited viprasol-agent-skills (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<div align="center">
The fintech-focused Agent Skills collection — trading, crypto/DeFi, finance, and developer skills that drop into Claude Code, Codex, Cursor & 26+ AI tools.
_Built and maintained by Viprasol Tech — Fintech Experts. Full-Stack Builders._
</div>
Most Agent Skill collections are general-purpose. This one is built for money — the workflows fintech teams, quant traders, crypto researchers, and finance analysts actually run. Every skill is portable (a plain skill.md), works across any Agent Skills–compatible tool, is grounded in a real framework (SWC Registry, López de Prado's backtest-overfitting research, Altman Z / Beneish M, OWASP/CWE), and ships with worked examples.
Each skill lives in its own repo so you can install just what you need. This hub is the index + one-command installer.
| Skill | What it does |
|---|---|
| smart-contract-audit | Solidity/EVM security audit — 18 vulnerability classes (reentrancy, access control, oracle manipulation…), exploit scenarios + fixes. Grounded in the SWC Registry. |
| tokenomics-review | Token economics red-flag review — supply/FDV, insider vesting, unlock overhang, liquidity, rug vectors → risk scorecard. |
| defi-protocol-review | DeFi protocol due-diligence — admin keys, audits, yield sustainability, TVL & oracle risk → risk matrix + verdict. |
| wallet-security-review | Before you sign — review a signature/approval request or audit a wallet for drainer & phishing risk (Permit2, setApprovalForAll, eth_sign, EIP-7702). |
| onchain-forensics | Trace funds across addresses & chains — MIH/change-address/FIFO mixer heuristics, bridge & DEX hop tracing, OFAC checks, Daubert-grade evidence notes. |
| Skill | What it does |
|---|---|
| trading-strategy-review | Vet a strategy/backtest for the failure modes that blow up live — look-ahead bias, overfitting, survivorship, slippage, risk-of-ruin. Grounded in PBO & Deflated Sharpe. |
| options-strategy-analyzer | Vet an options trade — pick the right structure for your view, compute Max P/L, break-evens, Greeks, IV-rank context & PoP-vs-EV with a risk-management plan. |
| risk-management-review | Risk-review a portfolio / strategy / position — σ, MDD, VaR/CVaR, Sharpe/Sortino/Calmar/UPI, Kelly & vol-target sizing, concentration & leverage caps, stress tests. |
| Skill | What it does |
|---|---|
| financial-statement-analysis | Fundamental analysis — liquidity/solvency/profitability ratios, DuPont, Altman Z, Beneish M, red flags, sector benchmarks. |
| earnings-call-analyzer | Digest an earnings call — KPIs vs guidance, management tone & candor, Q&A red flags, watch-items. |
| invoice-extractor | Extract invoices & receipts into clean validated JSON — vendor, line items, totals, tax — with math reconciliation. |
| Skill | What it does |
|---|---|
| code-review-skill | Rigorous, prioritized code review — correctness → security (OWASP/CWE) → performance → tests, with specific fixes, not nitpicks. |
| api-security-review | Review REST/GraphQL APIs against the OWASP API Top 10 2023 — BOLA, broken auth, mass assignment, SSRF, JWT/OAuth/CORS pitfalls — with curl PoCs and code-level fixes. |
| sql-optimizer | Make slow SQL fast — read EXPLAIN ANALYZE, propose composite/covering/partial indexes, catch N+1 / OFFSET / LIKE-%prefix, with a re-measure protocol. PG + MySQL. |
Agent Skills are just folders. Clone the ones you want into your tool's skills directory.
One skill (Claude Code):
git clone https://github.com/Viprasol-Tech/smart-contract-audit ~/.claude/skills/smart-contract-auditAll of them, one command (Claude Code — pass --codex to target ~/.codex/skills, or --dir <path> for any tool):
curl -fsSL https://raw.githubusercontent.com/Viprasol-Tech/viprasol-agent-skills/main/install.sh | bashWindows (PowerShell):
irm https://raw.githubusercontent.com/Viprasol-Tech/viprasol-agent-skills/main/install.ps1 | iexThen just ask your agent, e.g. Audit this staking contract for vulnerabilities or Review my MA-crossover backtest for look-ahead bias.
skill.md; works in Claude Code, OpenAI Codex, Cursor, GitHub Copilot, Gemini CLI, and 26+ Agent Skills tools.⚠️ Disclaimer: These skills are decision-support tools for research and education. They are not financial, investment, legal, or security-audit advice, and are no substitute for a professional audit or a licensed advisor. Always verify against primary sources. Crypto and trading carry real risk of loss.
⭐ If these help you, a star on the skills you use means a lot — it tells us what to build next.
Viprasol Tech — fintech software, AI agents, algorithmic trading systems, and B2B SaaS. Need a custom build? [Get in touch](mailto:[email protected]).
_Not affiliated with or endorsed by Anthropic, OpenAI, or any tool listed. "Agent Skills" is an open, cross-tool format._
MIT © 2025 Viprasol Tech Private Limited
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.