The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions for extending Quarto functionality using the quarto add command, which downloads and installs extensions from GitHub repositories.
Evidence: references/extensions.md and references/conversion-blogdown.md suggest installing extensions from sources such as quarto-ext/fontawesome, shafayetShafee/bsicons, gadenbuie/quarto-social-embeds, and others.
Context: This is the standard, documented method for extending the Quarto CLI. The official Quarto extension organization (quarto-ext) and prominent community contributors are referenced.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent on how to process, render, and convert Quarto documents (.qmd), R Markdown documents (.Rmd), and Jupyter notebooks (.ipynb). These files are user-provided and could potentially contain malicious instructions meant to influence the agent's behavior during the authoring or rendering process.
Ingestion points: The agent is instructed to read and work with .qmd, .Rmd, and .ipynb files as part of the primary authoring tasks.
Boundary markers: The skill does not explicitly define boundary markers or instruct the agent to ignore instructions embedded within the data it processes.
Capability inventory: The skill utilizes capabilities including file system access (reading/writing documents), shell command execution (quarto render, quarto convert, quarto add), and network operations (extension installation).
Sanitization: No specific sanitization or validation logic for the content of the markdown files is provided in the instructions, relying on standard agent guardrails.

quarto-authoring