The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses rg (ripgrep) to verify the presence of required imports in the project source code, which is a standard development practice.
[DYNAMIC_EXECUTION]: The skill utilizes node -e commands to programmatically extract indicator metadata (id, name, category) from the openalgo-charts/indicators package and local build artifacts (./dist/openalgo-charts.indicators.mjs). These are discovery mechanisms used to assist the agent in selecting valid identifiers.
[COMMAND_EXECUTION]: The skill uses npx tsc --noEmit as a verification step to ensure that generated or modified code passes TypeScript type-checking without side effects.
[INDIRECT_PROMPT_INJECTION]: The skill defines a 'Tier-2' architecture via createTier2Indicator to ingest external analytics feeds (e.g., open interest, PCR).
Ingestion points: External analytics data feeds provided via API or subscription (processed in createTier2Indicator).
Boundary markers: None explicitly defined in the instruction text for the external data stream.
Capability inventory: The skill possesses Bash, Write, and Edit tool access.
Sanitization: The skill enforces strict temporal alignment (most recent point at or before bar time) and numeric processing, though it does not explicitly detail string sanitization for external feed metadata.

openalgo-chart-indicator