Read Gist
Documentsread-gistRead Gist is an Agent Skill for documents published in the AztecProtocol/aztec-packages repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Fetch and display a GitHub gist. Triggers when the user asks to read, fetch, or view a URL from gist.github.com.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/AztecProtocol/aztec-packages/blob/HEAD/yarn-project/.claude/skills/read-gist/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/read-gist, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Read Gist
Fetch and display the contents of a GitHub gist.
Trigger
Activate this skill when the user provides a URL matching gist.github.com or asks to fetch/read a gist by ID.
Parameters
The argument is a gist URL or gist ID: $ARGUMENTS
Steps
-
Extract the gist ID from the input. It can be:
- A full URL like
https://gist.github.com/<user>/<id>-> extract<id> - A full URL like
https://gist.github.com/<id>-> extract<id> - A raw URL like
https://gist.githubusercontent.com/...-> extract the gist ID segment - A bare gist ID (hex string)
- A full URL like
-
Try
gh gist viewfirst (preferred):gh gist view <id> --rawIf the gist has multiple files, list them first with
gh gist view <id>(without--raw) to show filenames, then fetch with--rawor specify a filename with-f <filename>if the user asked for a specific file. -
Fallback to WebFetch only if
ghis not available or the command fails with an auth/install error:- Fetch
https://gist.githubusercontent.com/<user>/<id>/rawfor single-file gists - Or fetch the gist API endpoint
https://api.github.com/gists/<id>and extract file contents from the JSON response
- Fetch
-
Return the contents to the caller. If there are multiple files, show each file with its filename as a header.