The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Existing resumes provided by the user and job descriptions (JDs) for companies and positions (SKILL.md).
Boundary markers: The instructions mandate that only facts explicitly confirmed by the user be written to the master facts file (resume-facts.yaml).
Capability inventory: The skill executes shell commands via npx, powershell, and python, and performs file write operations to create resumes and analysis reports (SKILL.md).
Sanitization: The workflow relies on manual user confirmation of extracted facts and visual verification of rendered outputs to mitigate injection risks.
[EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute a vendor-owned package from the NPM registry.
Evidence: Execution of npx -p @chasen-liao/resume-skills@latest resume-skills validate and npx -p @chasen-liao/resume-skills@latest resume-skills editor (SKILL.md).
[COMMAND_EXECUTION]: The skill executes local PowerShell and Python scripts to handle document rendering and validation.
Evidence: Use of powershell -ExecutionPolicy Bypass -File skills/resume-builder/scripts/render_resume.ps1 and python skills/resume-builder/scripts/validate_resume.py (SKILL.md).

resume-workflow