The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill is configured to fetch missing supplementary files (instructions and templates) from the author's GitHub repository at https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/. This is a standard vendor resource used to maintain skill functionality when local files are absent.
[COMMAND_EXECUTION]: Utilizes the gh (GitHub CLI) and git commands to retrieve repository metadata, discussion categories, and commit logs for analysis.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data.
Ingestion points: Reads docs/community_engagement_strategy.md from the target project and processes output from GitHub API calls (discussions and issues).
Boundary markers: No explicit boundary markers or delimiters are used to isolate untrusted content.
Capability inventory: Uses the Bash tool for terminal commands and the Skill tool for delegating to other automated workers.
Sanitization: No sanitization or validation of the ingested external content is performed before processing.

ln-910-community-engagement