The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell script blocks to automate the discovery and verification of GitHub project settings. It invokes the gh CLI, git, and jq to inspect project fields and environment configurations. Environment variables such as GITHUB_PROJECT_NUM and GH_PROJECT_OWNER are derived through regex-based extraction from repository metadata.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process arbitrary user work requests and repository data (e.g., README.md, GitHub issues). While this represents a potential surface for indirect prompt injection, the risk is addressed through a structured triage process that requires explicit agent-user interaction for clarification. The skill uses regex filtering when deriving configuration values from external strings, providing a layer of sanitization for shell execution.

work-intake