The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using standard developer CLI tools (gh and glab) to retrieve pull request metadata, comments, and code diffs.
[DATA_EXFILTRATION]: Provides an optional feature to share the generated walkthrough using cloudflared to create a public tunnel. Cloudflare is a well-known service, and this network operation is a documented part of the skill's functionality for user-requested sharing.
[PROMPT_INJECTION]: The skill processes untrusted external data from pull requests (including PR descriptions and reviewer comments) which could contain indirect prompt injections.
Ingestion points: Pull request data is fetched from GitHub/GitLab via the view and diff commands as described in the workflow of SKILL.md.
Boundary markers: No specific delimiters or "ignore instructions" markers are used when the agent processes the fetched PR content.
Capability inventory: The skill can execute shell commands (gh, glab, python3, cloudflared) and has write access to the local file system (walkthrough/index.html).
Sanitization: The skill does not explicitly describe sanitization, escaping, or filtering of the fetched PR content before it is analyzed by the model.

pr-walkthrough