The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the gh issue view command to fetch ticket data from GitHub. This is a standard operation using an official CLI tool for a well-known service.
[EXTERNAL_DOWNLOADS]: The skill generates HTML slide decks that reference the reveal.js library via a CDN. This is a standard practice for web-based presentations and uses well-known, trusted infrastructure.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests untrusted data from GitHub issues, Linear tickets, or user-provided text to generate questions.
Ingestion points: External ticket data retrieved via GitHub CLI, Linear API, or direct user input.
Boundary markers: The instructions specify framing the context summary objectively, but do not provide technical delimiters for the ingested content.
Capability inventory: File system writes to thoughts/shared/ and execution of the gh CLI.
Sanitization: No explicit sanitization or escaping of ticket content is mentioned before it is included in the generated documents.
[DYNAMIC_EXECUTION]: The skill generates HTML and potentially JavaScript (via the reveal.js template) dynamically based on the ticket analysis. This is limited to presentation output and occurs within the project's documentation directory.

create-research-questions