The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches job description data from Jina Reader (r.jina.ai) to parse URLs into markdown. This is an expected operation for the skill's functionality.
[COMMAND_EXECUTION]: Shell commands are used to fetch data via curl and generate application files. The skill also generates a CommonJS module (cv-data.js) intended for execution during the project's build process ('bun run build').
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it ingests untrusted data from external job URLs. * Ingestion points: Job posting content fetched in Step 1. * Boundary markers: None are specified when passing this content to the cover-letter-writer sub-agent or using it for CV data generation. * Capability inventory: The skill has file writing permissions and the ability to dispatch sub-agents. * Sanitization: No sanitization is performed on the fetched external content before it is used in prompt construction.

generate-application