Pull Request (Vision-Agents)
SkillAI & modelsLets your agent create a draft pull request in the Vision-Agents repo using the gh CLI.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Pull Request (Vision-Agents) skill
About this capability
Create a draft pull request for the Vision-Agents repo using gh CLI.
What this skill tells your AI
The instructions your AI receives, as published by getstream/vision-agents in .claude/skills/pr/SKILL.md and read by ahel’s review.
Before creating
- Run
git log main..HEAD --oneline. If the branch contains more than one independent logical change, STOP and ask the user whether to split it before proceeding. - Run
uv run --no-sync dev.py check. Skip if the diff does not touch Python code (*.py) orpyproject.toml— e.g. docs-only,.gitignore,.github/, or.claude/changes. - Do not run integration tests locally, CI handles them.
- If the change is user-facing (public API break, new feature, bug fix), update
CHANGELOG.mdper the rules inCLAUDE.md.
Creating
- Always
gh pr create --draft. Push the branch first. - Follow
.github/pull_request_template.md. Read every commit on the branch, do not summarise from the latest commit alone. ## Whyis motivation + context.## Changes, if included, is high-level; never per-bullet justifications, those belong in## Why.- Link public GitHub issues inline within
## Why(e.g. "users reported X (#478)"), not as a trailingFixes #N. - Do not paste CI, lint, or tool output in the body.
- Do not hard-wrap paragraphs. GitHub renders each newline inside a paragraph as a visible line break, so a 72-column-wrapped paragraph becomes a staircase. Write each paragraph or bullet as one unbroken line; rely on the browser to soft-wrap. Only use newlines to separate paragraphs, list items, or block elements.
Signals
- GitHub stars
- 8k
- Forks
- 682
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
pr-getstream- Source
- github.com/getstream/vision-agents