Summary
Tackles PR review feedback by fetching unresolved threads, evaluating each one, and spawning parallel agents to fix valid issues. You can run it on the current branch to process all feedback at once, target a specific PR number, or pass a comment URL to address just one thread. The workflow is opinionated: default to fixing unless you have concrete evidence the feedback doesn't apply or would make things worse. It commits fixes, replies with quoted context, and resolves threads via GraphQL. Worth noting it treats all feedback equally whether it comes from humans or bots, and the security model is solid since it never executes code snippets found in comments.
Install to Claude Code
npx -y skills add everyinc/compound-engineering-plugin --skill ce-resolve-pr-feedback --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
