pr-feedback-classifier
Fetches and classifies PR review feedback with context isolation. Returns structured JSON with thread IDs for deterministic resolution. Use when analyzing PR comments before addressing them.
npx skills add majiayu000/claude-skill-registry --skill pr-feedback-classifier-dagster-io-erk-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# PR Feedback Classifier Fetch and classify all PR review feedback for the current branch's PR. ## Arguments - `--pr <number>`: Target a specific PR by number (default: current branch's PR) - `--include-resolved`: Include resolved threads (for reference) Check `$ARGUMENTS` for flags. ## Steps 1. **Get current branch and PR info:** - **If `--pr <number>` specified in `$ARGUMENTS`**: ```bash gh pr view <number> --json number,title,url -q '{number: .number, title: .title, url: .url}' ``` - **If `--pr` not specified** (use current branch): ```bash git rev-parse --abbrev-ref HEAD gh pr view --json number,title,url -q '{number: .number, title: .title, url: .url}' ``` 2. **Fetch all comments:** ```bash # If --include-resolved in $ARGUMENTS: erk exec get-pr-review-comments [--pr <number>] --include-resolved # Otherwise: erk exec get-pr-review-comments [--pr <number>] erk exec get-pr-discussion-comments [--pr <number>] ``` Note: Pass `--pr <number>` to both exec commands when specified in `$ARGUMENTS`. 3. **Classify each comment** using the Comment Classification Model below. 4. **Group into batches** by complexity. 5. **Output structured JSON** (schema below). ## Comment Classification Mod
- Arguments
- Steps
- Comment Classification Model
- Actionability
- Complexity (for actionable items)
- Batch Ordering
- Output Format
- Error Case
- No Comments Case
gh pr view <number> --json number,title,url -q '{number: .number, title: .title, url: .url}'
git rev-parse --abbrev-ref HEAD
gh pr view --json number,title,url -q '{number: .number, title: .title, url: .url}'
erk exec get-pr-review-comments [--pr <number>] --include-resolved
erk exec get-pr-review-comments [--pr <number>]
erk exec get-pr-discussion-comments [--pr <number>]What does the pr-feedback-classifier skill do?
Fetches and classifies PR review feedback with context isolation. Returns structured JSON with thread IDs for deterministic resolution. Use when analyzing PR comments before addressing them.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill pr-feedback-classifier-dagster-io-erk-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.