Generate complete VectorBT backtesting scripts with data fetch, signals, stats, and plots.
Automate repetitive workflows and reduce manual effort
Example: Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example: Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example: Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
Time estimate: 15-45 minutes depending on use case complexity
Prerequisites
Submit your Claude Code skill and start earning
epx add marketcalls/vectorbt-backtesting-skills --skill backtestCompatible with
Supported agents
Supports 10+ pre-built strategies (EMA crossover, RSI, Donchian, Supertrend, MACD, SDA2, momentum, and more) with template-based script generation
Fetches data from OpenAlgo API or loads directly from DuckDB; auto-detects Historify vs custom formats
Uses TA-Lib for standard indicators and OpenAlgo ta for specialty indicators (Supertrend, Donchian, Ichimoku); includes signal deduplication via ex
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionbacktestExecute the skills CLI command in your project's root directory to begin installation:
epx add marketcalls/vectorbt-backtesting-skills --skill backtestFetches backtest from marketcalls/vectorbt-backtesting-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
.cursor/skills/backtest
Restart Cursor to activate backtest. Access via /backtestin your agent's command palette.
Learn more:View source on GitHubSkills CLI docsAbout CursorWhat are agent skills?
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
accessibility-testing
aj-geddes/useful-ai-prompts · Testing · same category
vitest
jezweb/claude-skills · Testing · same category
usability-testing
refoundai/lenny-skills · Testing · same category
playwright-generate-test
github/awesome-copilot · Testing · same category
pentest-checklist
sickn33/antigravity-awesome-skills · Testing · same category
idor-vulnerability-testing
davila7/claude-code-templates · Testing · same category
I recommend backtest for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
backtest fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
backtest is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
We added backtest from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
backtest reduced setup friction for our internal harness; good balance of opinion and flexibility.
I recommend backtest for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Registry listing for backtest matched our evaluation — installs cleanly and behaves as described in the markdown.
Keeps context tight: backtest is the kind of skill you can hand to a new teammate without a long onboarding doc.
Useful defaults in backtest — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
backtest has been reliable in day-to-day use. Documentation quality is above average for community skills.
showing 1-10 of 52