Stats
Actions
Tags
From feedbacks
Protocol for @feedback annotations in source code. Use when user mentions @feedback, address feedbacks, inline feedback, or when encountering @feedback markers during any task.
How this skill is triggered — by the user, by Claude, or both
Slash command
/feedbacks:feedback-protocolThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
`@feedback` annotations are inline source code comments that describe desired changes. They use the file's native comment style (`//`, `#`, `--`, `/* */`, `<!-- -->`).
@feedback annotations are inline source code comments that describe desired changes. They use the file's native comment style (//, #, --, /* */, <!-- -->).
// @feedback: <desired change>
// @agent-response: <what was done>
The @agent-response line is added directly below the @feedback line using the same comment style after implementing the change.
@feedback with no @agent-response below it@feedback followed by @agent-response on the next line@feedback in source files, exclude non-source dirs@agent-response: <summary> — max 300 characters. If unable: @agent-response: skipped - <reason>When encountering @feedback while working on other tasks: note them to the user and offer to address if related. Do not address silently.
For comment style details and edge cases (multi-line blocks, inline placement, nested comments): see references/comment-patterns.md.
npx claudepluginhub obsfx/cc-feedback --plugin feedbacksProcesses external code review feedback from LLMs, humans, or CI tools by verifying claims with tools, evaluating via decision matrix, and executing implement/reject/defer with tracked disposition.
Use when processing code review feedback before making changes, particularly when suggestions are ambiguous, technically suspect, or span multiple interdependent items - demands verification and technical rigor over compliance theater
Guides receiving code review feedback with a structured pattern: read, understand, verify, evaluate, implement. Especially useful when feedback is unclear, risky, or disputed.