This generates production-ready technical indicators with Numba JIT compilation, so you get O(n) performance on price data without writing C extensions. It scaffolds the full package: the core computation function decorated with @njit, a pandas-friendly public API, a Plotly charting script, and a benchmark suite. The workflow checks if your indicator already exists in openalgo.ta before creating anything, which saves you from reinventing RSI. Most useful when you need a custom signal like a Z-score oscillator or squeeze momentum detector and you want it fast enough to backtest on years of tick data without waiting. The Numba constraints are strict but documented: no fastmath, no pandas inside jitted code, explicit loops only.
npx -y skills add marketcalls/openalgo-indicator-skills --skill custom-indicator --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills