The Agent Skills Directory

[SAFE]: The skill implements a secure local data management strategy, storing user resumes and work history in a dedicated .proficiently directory. This practice ensures data persistence while maintaining user privacy.
[PROMPT_INJECTION]: The skill processes external content from job posting URLs provided by the user. While this creates a potential surface for indirect prompt injection, the risk is mitigated by strict instructions that require the agent to verify all information against the user's original resume and work history profile.
Ingestion points: Job descriptions are fetched from external URLs via browser MCP tools as described in references/browser-setup.md.
Boundary markers: The scripts/tailor-resume.md file contains non-negotiable "Strict Accuracy Rules" and "Quality Checks" to prevent the inclusion of fabricated data.
Capability inventory: The skill can perform local file writes to save tailored resumes and use browser tools for data extraction.
Sanitization: A mandatory "Critique and Rewrite" phase is used to filter out AI-generated filler and ensure the content remains factual.
[SAFE]: The skill utilizes standard browser MCP tools (e.g., tabs_context_mcp, get_page_text) to interact with job postings. The documentation in references/browser-setup.md provides guidance on safe tool usage to avoid context window exhaustion.

tailor-resume