PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Fetches GitHub Copilot review feedback from inline threads and review bodies, checks each finding against the code and fixes the valid ones.
Install Address PR Feedback
$ npx skills add keybase/client --skill address-pr-feedback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install keybase/client address-pr-feedback --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/keybase/client.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill/address-pr-feedback .claude/skills/address-pr-feedback && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "address-pr-feedback" agent skill from https://github.com/keybase/client/tree/master/skill/address-pr-feedback into .claude/skills/address-pr-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "address-pr-feedback", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/keybase/client/tree/master/skill/address-pr-feedbackType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add keybase/client --skill address-pr-feedback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install keybase/client address-pr-feedback --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/keybase/client.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skill/address-pr-feedback .agents/skills/address-pr-feedback && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "address-pr-feedback" agent skill from https://github.com/keybase/client/tree/master/skill/address-pr-feedback into .agents/skills/address-pr-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "address-pr-feedback", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add keybase/client --skill address-pr-feedback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install keybase/client address-pr-feedback --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/keybase/client.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skill/address-pr-feedback .cursor/skills/address-pr-feedback && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "address-pr-feedback" agent skill from https://github.com/keybase/client/tree/master/skill/address-pr-feedback into .cursor/skills/address-pr-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "address-pr-feedback", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/keybase/client.git --path skill/address-pr-feedback--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add keybase/client --skill address-pr-feedback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install keybase/client address-pr-feedback --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/keybase/client.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skill/address-pr-feedback .gemini/skills/address-pr-feedback && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "address-pr-feedback" agent skill from https://github.com/keybase/client/tree/master/skill/address-pr-feedback into .gemini/skills/address-pr-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "address-pr-feedback", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install keybase/client address-pr-feedbackInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add keybase/client --skill address-pr-feedback -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/keybase/client.git skills-src && mkdir -p .github/skills && cp -r skills-src/skill/address-pr-feedback .github/skills/address-pr-feedback && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "address-pr-feedback" agent skill from https://github.com/keybase/client/tree/master/skill/address-pr-feedback into .github/skills/address-pr-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "address-pr-feedback", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add keybase/client --skill address-pr-feedback -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install keybase/client address-pr-feedback --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/keybase/client.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skill/address-pr-feedback .opencode/skills/address-pr-feedback && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "address-pr-feedback" agent skill from https://github.com/keybase/client/tree/master/skill/address-pr-feedback into .opencode/skills/address-pr-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "address-pr-feedback", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
address-pr-feedback- GitHub stars
- 9.3k
- Token cost
- ~657 tokens
- SKILL.md length
- 354 words
- Files
- 2
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- BSD-3-Clause
At a glance
Fetches GitHub Copilot review feedback from inline threads and review bodies, checks each finding against the code and fixes the valid ones.
- Works in 2 steps: Fetch Copilot feedback → Evaluate each comment
- Addressing Copilot review comments on a pull request
- SKILL.md covers Step 1 — Fetch Copilot feedback, Step 2 — Evaluate each comment and Hidden = ignored
- Runs Shell scripts from its folder; calls gh
What it does
This skill handles feedback that GitHub Copilot leaves on a pull request. A bundled script, get-copilot-feedback.sh, takes an optional PR number, defaulting to the current branch's PR, and reads Copilot findings from both places they appear: inline review threads, and the review body, where newer reviews put findings under a Suppressed comments heading. Resolved or minimized threads are skipped, while outdated threads are kept and tagged OUTDATED.
An empty inline section is never read as a clean review, since a thread-only query can miss findings filed in the body; if both sections are empty the agent checks whether Copilot reviewed at all with gh pr view. The script drops Copilot's per-file summary table. For each finding the agent verifies the issue still exists in the current file, re-locating older line references by symbol, judges whether it is correct for this codebase and pushes back with reasoning when it is not, then fixes the valid ones and mutation-checks any test it adds. It does not post replies to GitHub threads and only changes the code.
When your agent uses it
- Addressing Copilot review comments on a pull request
- Checking whether an apparently clean Copilot review hid findings in the review body
- Triaging outdated review threads against the current code
Example prompts
- “Look at the Copilot feedback on this PR and fix whatever is valid.”
- “Address the review comments on PR 5 but do not reply on GitHub.”
- “Copilot's review looks empty, so check the review body for suppressed comments before we call it clean.”
Requirements
- GitHub CLI (gh) authenticated for the repository
- A pull request that Copilot has reviewed
Workflow steps
2 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 81e93d6. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Shell), which the agent can run.
Shell commands in SKILL.md call:
gh
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Address PR Feedback loads about 657 tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 354 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from keybase/client at commit 81e93d6, republished under its BSD-3-Clause licence (© keybase). 354 words, ~657 tokens.
Download SKILL.mdSave it as
.claude/skills/address-pr-feedback/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- address-pr-feedback
- description
- Use when asked to look at or address feedback on a PR. Fetches Copilot feedback from both inline threads and review bodies, skips hidden comments, then evaluates and fixes the valid ones.
Address PR Feedback
Step 1 — Fetch Copilot feedback
./.claude/skills/address-pr-feedback/get-copilot-feedback.sh [pr-number]If no PR number is given, it uses the current branch's PR.
Copilot reports findings in two different places, and the script reads both:
- Inline review threads — the classic form. Hidden comments (resolved threads, minimized
comments) are skipped automatically. Outdated threads are still shown, tagged
[OUTDATED]. - Review bodies — as of 2026-09 Copilot frequently posts
Comments generated: 0and puts its real findings in the review body instead, under### Suppressed comments. These never appear as threads.
An empty "Inline review threads" section does NOT mean the review was clean. That is the
trap this skill exists to avoid: a thread-only query returns nothing and the PR looks unreviewed
when Copilot in fact filed a finding in the body. Always read both sections before concluding
there is no feedback. If both are empty, check that Copilot has actually reviewed
(gh pr view <n> --json reviews) rather than assuming it found nothing.
The script deliberately strips Copilot's per-file summary table — it restates the diff and carries no findings. It keeps the headline verdict, the one-line concern beneath it, and the suppressed-comments block.
Show full SKILL.md (165 more words)Show less
Step 2 — Evaluate each comment
For each finding:
- Verify — read the current file and confirm the issue actually exists. Comments may already
be fixed by later commits. For
[OUTDATED]ones this matters most: the diff position moved, but the underlying issue often still exists — find the corresponding spot and evaluate there. A body finding citespath:linefrom an older push; re-locate it by symbol, not line number. - Assess — is it technically correct for this codebase? Push back with reasoning if not. Copilot's verdict line ("Needs a closer look") is not itself a finding; the substance is in the concern sentence and the suppressed comments.
- Fix — edit the file if the feedback is valid, and mutation-check any test you add.
Do not post replies to GitHub comment threads. Just fix the code.
Hidden = ignored
A comment is hidden only when its thread is resolved or minimized on GitHub. Those are skipped automatically and need no action. Outdated is not hidden — evaluate those normally.
© keybase, BSD-3-Clause. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skill/address-pr-feedback of keybase/client.
- SKILL.md
- get-copilot-feedback.sh
Open the folder on GitHubat commit 81e93d6
Compare with similar skills
Address PR Feedback next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Address PR Feedback this skillkeybase/client | 9.3k | — | ~657 | Automated safety check: Pass | BSD-3-Clause | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| GitHub Review Iterationprisma/orm | 48k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| PR Finalize Reviewmicrosoft/garnet | 12k | — | ~3.1k | Automated safety check: Pass | MIT | |
| PR Review State Fetchprisma/orm | 48k | — | ~767 | Automated safety check: Pass | Apache-2.0 | |
| Fastlane Pull Request Reviewfastlane/fastlane | 42k | — | ~550 | Automated safety check: Pass | MIT |
Similar skills
- Official
GitHub Review Iteration
prisma/orm
Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.
- Official
PR Finalize Review
microsoft/garnet
Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.
- Official
PR Review State Fetch
prisma/orm
Fetches a pull request's canonical review state as JSON, validates it, and renders markdown, a text summary and triage target files from it using bundled scripts.
Fastlane Pull Request Review
fastlane/fastlane
Reviews a fastlane pull request against its linked issue and the project guides, separating blocking from non-blocking findings and handling vulnerabilities privately.
Pull Request Reviewer for daisyUI
saadeghi/daisyui
Reviews open pull requests in the daisyUI repository using read-only GitHub data and isolated base-versus-PR checks, then writes a merge verdict report.
More from keybase/client
All 14 skills in this repoElectron Heap Snapshot Analysis
keybase/client
Analyzes V8, Chrome and Electron .heapsnapshot files with Node scripts to find memory leaks, detached DOM nodes and the retainer paths that keep objects alive.
Electron DevTools Trace Analysis
keybase/client
Analyzes Chrome or Electron DevTools Performance trace exports with Python scripts to find where render time actually goes, without opening DevTools.
Keybase RPC Log Analysis
keybase/client
Captures a clean Keybase service log and analyzes it for redundant, duplicated or looping RPCs, then checks whether a caching fix reduced the calls.
React DevTools Profile Analyzer
keybase/client
Parses a React DevTools Profiler JSON export with Python scripts to find re-render storms, commit fan-out and why a component rendered, without opening the DevTools UI.
Electron App Screenshot
keybase/client
Takes a screenshot of a running Electron desktop app through playwright-cli over remote debugging, shrinks it and shows it so you can check the UI visually.
Keybase E2E Flow Tests
keybase/client
Guides writing and fixing end-to-end flow tests for the Keybase app on desktop with Playwright and on iOS with Appium and WebdriverIO, sharing one testID registry.
Related
Works with
Categories
Questions about Address PR Feedback
What does Address PR Feedback do?
Fetches GitHub Copilot review feedback from inline threads and review bodies, checks each finding against the code and fixes the valid ones. This skill handles feedback that GitHub Copilot leaves on a pull request.sh, takes an optional PR number, defaulting to the current branch's PR, and reads Copilot findings from both places they appear: inline review threads, and the review body, where newer reviews put findings under a Suppressed comments heading.
When should I use Address PR Feedback?
Address PR Feedback fits situations like: addressing Copilot review comments on a pull request; checking whether an apparently clean Copilot review hid findings in the review body; triaging outdated review threads against the current code.
How do I install Address PR Feedback in Claude Code?
Run `npx skills add keybase/client --skill address-pr-feedback -a claude-code`. Or copy the skill folder (skill/address-pr-feedback in keybase/client) into .claude/skills/address-pr-feedback in your project. Claude Code loads it when a task matches its description.
How do I install Address PR Feedback in Codex?
Run `npx skills add keybase/client --skill address-pr-feedback -a codex`. Or copy the skill folder (skill/address-pr-feedback in keybase/client) into .agents/skills/address-pr-feedback in your project. Codex loads it when a task matches its description.
Can I use Address PR Feedback in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add keybase/client --skill address-pr-feedback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/address-pr-feedback, .gemini/skills/address-pr-feedback, .github/skills/address-pr-feedback and .opencode/skills/address-pr-feedback in your project.
What does Address PR Feedback need to run?
Going by SKILL.md and its folder, Address PR Feedback needs a shell for the scripts in its folder and the command-line tools its instructions call (gh). Our summary lists: GitHub CLI (gh) authenticated for the repository; A pull request that Copilot has reviewed.
Does Address PR Feedback access the network?
SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Address PR Feedback safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Address PR Feedback use?
Address PR Feedback is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Address PR Feedback use?
About 657 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Address PR Feedback?
Skills that share tags, products or a category with Address PR Feedback: PR Babysitter (openinterpreter/openinterpreter, 69k stars), GitHub Review Iteration (prisma/orm, 48k stars), PR Finalize Review (microsoft/garnet, 12k stars) and PR Review State Fetch (prisma/orm, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Address PR Feedback?
keybase (a GitHub organization) maintains it in keybase/client, which has 9,257 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.
Source: keybase/client on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.