Add Agent Skills system - #56
Conversation
Implements an agent-skill management system, allowing AI coding agents to learn how to use md2png effectively. Adds `install`, `update`, `remove`, `list`, `inspect`, and `doctor` subcommands. Includes a builtin operational skill and supports downloading from local paths and remote GitHub repositories. Co-authored-by: arran4 <[email protected]>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Documentation previewsThe rendered README and example images are available as workflow artifacts.
|
1 participant
Adds the
skillsubcommand group for managing AI agent skills.Features:
skill install <source> [name]skill update [name](or--all)skill remove <name>skill listskill inspect <name>skill doctorSupports user and project scopes. Includes a comprehensive remote fetcher (GitHub zips), safe file extraction with path traversal guards, and local modification detection via content hashing.
Includes an official embedded skill providing guidance for AI agents.
PR created automatically by Jules for task 6506677532724437030 started by @arran4