The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill generates Python code for dashboards at runtime using templates located in rules/assets/. This is the core functionality of the skill and relies on standard, well-documented frameworks like Plotly Dash and Streamlit.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data through financial symbols and market data feeds. While this is an entry point for external content, the data is typically numerical and structured, presenting a very low risk of containing malicious prompt instructions.
Ingestion points: The symbol argument ($1) and external market data fetched during dashboard execution.
Boundary markers: No specific delimiters or warnings for the agent to ignore embedded instructions are present in the skill text.
Capability inventory: The skill uses Bash to run the apps and Write/Edit to create the application files.
Sanitization: The skill relies on the inherent sanitization provided by the Plotly and Streamlit rendering engines.
[COMMAND_EXECUTION]: The skill provides instructions to execute the generated dashboard code using python or streamlit run via the Bash tool, which is necessary for the skill's stated purpose.

indicator-dashboard