Review Recaps
SkillAI & modelsThis plan Claude skill lets your agent build before/after visual recaps posted automatically on every pull request.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Review Recaps skill
About this skill
The `columns` before/after comparison primitive and the PR Visual Recap GitHub Action (agent/model env vars, required tokens, sticky comment, informational scope). Use when building a recap, configuring recap CI, or explaining a Visual Recap check or comment.
What this skill tells your AI
The instructions your AI receives, as published by builderio/agent-native in templates/plan/.agents/skills/plan-review-recaps/SKILL.md and read by ahel’s review.
columnsis the generic before/after layout primitive for structured comparisons. Use it for side-by-side schema, API, prose, and model blocks.- The PR Visual Recap GitHub Action runs the
visual-recapskill on each PR via an LLM coding agent (Claude Code or Codex, chosen withVISUAL_RECAP_AGENT; model and reasoning depth viaVISUAL_RECAP_MODEL/VISUAL_RECAP_REASONING) whenPLAN_RECAP_TOKENand the backend's API key are configured, shows a non-requiredVisual Recapcheck while it runs, then posts a sticky comment with an inline screenshot. The recap is informational and must not imply the diff has been reviewed.
Related Skills
- visual-recap — how to generate the recap content itself.
- plan-authoring-flow — when
/visual-recapis the right command.
Signals
- GitHub stars
- 7k
- Forks
- 613
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
plan-review-recaps- Source
- github.com/builderio/agent-native