The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches Y Combinator company metadata, batch listings, and industry data from https://yc-oss.github.io/api/. This behavior is the primary intended function of the skill and targets a public, open-source repository.
[COMMAND_EXECUTION]: The skill relies on standard shell utilities curl and jq to retrieve and filter remote JSON content. It also utilizes dynamic context injection (!command syntax) in SKILL.md to perform a diagnostic check for these tools at load time.
[PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill ingests external JSON data from yc-oss.github.io and incorporates it into the agent's context for research purposes.
Ingestion points: Data is fetched from multiple endpoints defined in SKILL.md and references/api_reference.md via curl.
Boundary markers: The skill does not currently define explicit boundary markers or "ignore instructions" warnings for the fetched data.
Capability inventory: The skill has the capability to execute shell commands (curl, jq) to process the incoming data.
Sanitization: No explicit sanitization or validation of the remote JSON content is performed before processing.

yc-reader