fetch-pr-feedback
Fetch review comments from a PR and evaluate with receive-feedback skill
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/anderskev/fetch-pr-feedbackWhat This Skill Does
The fetch-pr-feedback skill is a powerful automation utility for OpenClaw that streamlines the code review process by aggregating feedback from GitHub pull requests. Instead of manually parsing through fragmented review comments, discussions, and line-specific suggestions, this skill automatically retrieves all relevant feedback from your PR. It filters out noise—such as the PR author’s own updates or the current user’s contributions—to provide a clean, actionable summary of what needs to be addressed. By leveraging the receive-feedback skill, it transforms raw GitHub comments into a structured analysis, allowing you to focus on resolving issues rather than hunting for them in the UI.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/anderskev/fetch-pr-feedback
Ensure that you have the GitHub CLI (gh) configured and authenticated on your system, as this skill relies on the local environment to handle API interactions securely.
Use Cases
- Automated PR Summaries: Quickly generate a concise digest of reviewer suggestions before you begin your coding session.
- Feedback Synthesis: Evaluate complex, multi-reviewer threads to identify consensus or conflicting suggestions.
- Reviewer Accountability: Easily separate feedback from core maintainers versus casual observers to prioritize your response strategy.
- Context Restoration: If you are returning to an old PR, use this skill to instantly parse and understand pending feedback without re-reading the entire history.
Example Prompts
- "@openclaw fetch-pr-feedback for PR #42 and summarize the main blockers."
- "Please run fetch-pr-feedback on this branch, including comments from the author, so I can review my own context too."
- "Fetch PR feedback for the current branch and pass it to receive-feedback so I can create a follow-up task list."
Tips & Limitations
- Filtering: The skill intelligently ignores common noise patterns, such as auto-generated AI analysis chains and standardized tips, ensuring you see only human-authored feedback.
- Truncation: To prevent overwhelming the AI context window, comments exceeding 4,000 characters are automatically truncated, appended with a truncation notice.
- Permissions: Ensure your GitHub CLI token has
reposcope permissions to fetch comments successfully. If you encounter issues, try runninggh auth statusto confirm your authentication state. - Dependencies: This skill works best when paired with the
receive-feedbackskill to interpret the resulting data.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-anderskev-fetch-pr-feedback": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-read, external-api
Related Skills
explanation-docs
Explanation documentation patterns for understanding-oriented content - conceptual guides that explain why things work the way they do
tutorial-docs
Tutorial patterns for documentation - learning-oriented guides that teach through guided doing
pytest-code-review
Reviews pytest test code for async patterns, fixtures, parametrize, and mocking. Use when reviewing test_*.py files, checking async test functions, fixture usage, or mock patterns.
reference-docs
Reference documentation patterns for API and symbol documentation. Use when writing reference docs, API docs, parameter tables, or technical specifications. Triggers on reference docs, API reference, function reference, parameters table, symbol documentation.
serde-code-review
Reviews serde serialization code for derive patterns, enum representations, custom implementations, and common serialization bugs. Use when reviewing Rust code that uses serde, serde_json, toml, or any serde-based serialization format. Covers attribute macros, field renaming, and format-specific pitfalls.