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.
Triage and optionally address AI-generated GitHub PR review feedback from Copilot, CodeRabbit, or similar bots.
Install Gh AI Review Triage
$ npx skills add shm11C3/HardwareVisualizer --skill gh-ai-review-triage -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install shm11C3/HardwareVisualizer gh-ai-review-triage --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/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/gh-ai-review-triage .claude/skills/gh-ai-review-triage && 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 "gh-ai-review-triage" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/gh-ai-review-triage into .claude/skills/gh-ai-review-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gh-ai-review-triage", 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/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/gh-ai-review-triageType 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 shm11C3/HardwareVisualizer --skill gh-ai-review-triage -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install shm11C3/HardwareVisualizer gh-ai-review-triage --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/gh-ai-review-triage .agents/skills/gh-ai-review-triage && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "gh-ai-review-triage" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/gh-ai-review-triage into .agents/skills/gh-ai-review-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gh-ai-review-triage", 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 shm11C3/HardwareVisualizer --skill gh-ai-review-triage -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install shm11C3/HardwareVisualizer gh-ai-review-triage --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/gh-ai-review-triage .cursor/skills/gh-ai-review-triage && 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 "gh-ai-review-triage" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/gh-ai-review-triage into .cursor/skills/gh-ai-review-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gh-ai-review-triage", 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/shm11C3/HardwareVisualizer.git --path .agents/skills/gh-ai-review-triage--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 shm11C3/HardwareVisualizer --skill gh-ai-review-triage -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install shm11C3/HardwareVisualizer gh-ai-review-triage --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/gh-ai-review-triage .gemini/skills/gh-ai-review-triage && 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 "gh-ai-review-triage" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/gh-ai-review-triage into .gemini/skills/gh-ai-review-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gh-ai-review-triage", 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 shm11C3/HardwareVisualizer gh-ai-review-triageInstalls 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 shm11C3/HardwareVisualizer --skill gh-ai-review-triage -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/gh-ai-review-triage .github/skills/gh-ai-review-triage && 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 "gh-ai-review-triage" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/gh-ai-review-triage into .github/skills/gh-ai-review-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gh-ai-review-triage", 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 shm11C3/HardwareVisualizer --skill gh-ai-review-triage -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install shm11C3/HardwareVisualizer gh-ai-review-triage --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/gh-ai-review-triage .opencode/skills/gh-ai-review-triage && 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 "gh-ai-review-triage" agent skill from https://github.com/shm11C3/HardwareVisualizer/tree/develop/.agents/skills/gh-ai-review-triage into .opencode/skills/gh-ai-review-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gh-ai-review-triage", 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
gh-ai-review-triage- GitHub stars
- 183
- Token cost
- ~1.1k tokens
- SKILL.md length
- 556 words
- Files
- 4 (incl. references)
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
Triage and optionally address AI-generated GitHub PR review feedback from Copilot, CodeRabbit, or similar bots.
- Works in 5 steps: Resolve the target PR (user-given… → Extract binding constraints from the… → Classify each comment as Required /… → …
- The user asks to check AI review comments
- SKILL.md covers Workflow, Convergence, Sufficiency Judgment and Reviewer Commands, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Gh AI Review Triage is an agent skill from shm11C3/HardwareVisualizer. Triage and optionally address AI-generated GitHub PR review feedback from Copilot, CodeRabbit, or similar bots. Use when the user asks to check AI review comments, decide whether comments require action, ignore non-actionable suggestions, fix required/should-fix/worth-fixing feedback, or summarize bot review findings on a pull request.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/classification.md` and `references/retrieval.md`).
It sits in Development, covering Pull requests and Code review. It works with GitHub. The repository describes itself as: A cross-platform hardware monitor with real-time metrics, local history, and customizable dashboards. The licence is GPL-3.0.
When your agent uses it
- The user asks to check AI review comments
- Decide whether comments require action
- Ignore non-actionable suggestions
- Fix required/should-fix/worth-fixing feedback
Example prompts
- “/gh-ai-review-triage”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Resolve the target PR (user-given number/URL, else the current branch) and
- Extract binding constraints from the user request, maintainer corrections,
- Classify each comment as Required / Should Fix / Worth Fixing /
- Act: fix Required, Should Fix, and Worth Fixing by default ("only
- No GitHub writes — replies, thread resolution, review submission, issue
What it can do on your machine
Read from SKILL.md and the folder at commit b23baca. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Gh AI Review Triage loads about 1.1k tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 89 tokens; SKILL.md has 556 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 shm11C3/HardwareVisualizer at commit b23baca, republished under its GPL-3.0 licence (© shm11C3). 556 words, ~1,144 tokens.
Download SKILL.mdSave it as
.claude/skills/gh-ai-review-triage/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- gh-ai-review-triage
- description
- Triage and optionally address AI-generated GitHub PR review feedback from Copilot, CodeRabbit, or similar bots. Use when the user asks to check AI review comments, decide whether comments require action, ignore non-actionable suggestions, fix required/should-fix/worth-fixing feedback, or summarize bot review findings on a pull request.
GitHub AI Review Triage
Separate AI review noise from useful feedback, and end the review with an explicit shippability verdict rather than with silence.
Workflow
- Resolve the target PR (user-given number/URL, else the current branch) and collect threads, comments, and review submissions — see references/retrieval.md.
- Extract binding constraints from the user request, maintainer corrections, and canonical decisions; they are the classification boundary, not inputs equal to bot feedback.
- Classify each comment as
Required/Should Fix/Worth Fixing/Optional/Ignore, verifying before classifying — definitions and verification rules in references/classification.md. - Act: fix
Required,Should Fix, andWorth Fixingby default ("only required" from the user narrows this); leaveOptional/Ignorealone. A "needs verification" tag excludes a finding from default fixing — never edit code on an unverified claim; take it to the maintainer instead. Keep fixes scoped to the comment; run the smallest relevant checks first. - No GitHub writes — replies, thread resolution, review submission, issue filing — without the user's explicit request.
Convergence
Bot reviewers are generators, not gates: they can always produce another
finding, so "respond until silent" never terminates (see lesson
bound-bot-review-loops).
- Split findings by evidence class. Reproducible (code, tests, types, CI, deterministic guidance checks): fix what reproduces — defects are finite. Subjective (wording, naming, structure): fix only self-contradictions and factual errors; decline the rest once, with reasoning.
- Do not restructure to satisfy a subjective finding — file an issue or ask
the maintainer. A verified
Requireddefect needing structural repair is fixed, in any round. - A finding that targets the previous response: verify it first (responses can introduce real regressions); if it does not reproduce, stop forward-fixing — revert the accumulated response-structure or freeze.
- Stop-loss backstop: after two response rounds, stop editing for subjective findings; summarize the remainder as declined-with-evidence or filed issues and hand the trade-off to the maintainer.
Show full SKILL.md (252 more words)Show less
Sufficiency Judgment
Processing a round means deciding fix / decline / file-an-issue for each valid finding, with reasoning — processing is not fixing. Then judge the change as a whole:
| Verdict | Meaning |
|---|---|
SUFFICIENT | purpose achieved; nothing remaining justifies blocking the merge |
INSUFFICIENT | a correctness, safety, or acceptance-criteria problem remains |
UNCERTAIN | agent-available evidence cannot settle it; a human decides |
Sufficient does not mean zero findings: purpose and acceptance criteria met, no credible correctness/security/regression concern, required verification passing, and no remaining finding worth fixing in this PR rather than filing.
Before the verdict, answer: purpose met? credible defect open? CI green?
must any remainder land in this PR? is a proposed addition a fix or taste?
and — the loop-ender — what concretely breaks if this merges now? A
finding that cannot answer the last question does not block, however
reasonable it sounds. SUFFICIENT: end the iteration, state the rationale.
INSUFFICIENT: fix and re-judge. UNCERTAIN: ask the maintainer.
Reviewer Commands
@coderabbitai reviewis not a routine step: it starts a full re-review over unchanged code — fuel for the loop. Reserve it for a push that genuinely changes direction or scope.- After
SUFFICIENT, clear a staleCHANGES_REQUESTEDwith@coderabbitai approve(explicit write authorization as always). Approval is the outcome of the judgment, never the goal; do not use it to bypassINSUFFICIENT.
Output
Report per class: addressed, declined and why, filed issues, validation results, whether GitHub writes were performed — and the sufficiency verdict with its rationale, anchored on what would concretely break by merging now. Respond in the user's language.
© shm11C3, GPL-3.0. 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 3 other files (references) in .agents/skills/gh-ai-review-triage of shm11C3/HardwareVisualizer.
- SKILL.md
- agents/openai.yaml
- references/classification.md
- references/retrieval.md
Open the folder on GitHubat commit b23baca
Compare with similar skills
Gh AI Review Triage 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 |
|---|---|---|---|---|---|---|
| Gh AI Review Triage this skillshm11C3/HardwareVisualizer | 183 | — | ~1.1k | Automated safety check: Pass | GPL-3.0 | |
| 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 Review State Fetchprisma/orm | 48k | — | ~767 | Automated safety check: Pass | Apache-2.0 | |
| PR Finalize Reviewmicrosoft/garnet | 12k | — | ~3.1k | Automated safety check: Pass | MIT | |
| 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 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.
- 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.
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 Babysitter
thedotmack/claude-mem
Keeps watching a pull request, fixing real review and CI problems and resolving stale threads, until it is clean and ready to merge.
More from shm11C3/HardwareVisualizer
Capture Project Learning
shm11C3/HardwareVisualizer
Turn a HardwareVisualizer maintainer correction, repeated failure, surprising invariant, or costly investigation into an evidence-backed learning record and the right durable guardrail.
Change Kind Naming
shm11C3/HardwareVisualizer
Decide the correct change kind and semantically align branch names, PR titles, commit prefixes, and PR template types.
Deliver Pull Request
shm11C3/HardwareVisualizer
Deliver a focused HardwareVisualizer change as a pull request, then address its CI and review feedback to completion.
Hardwarevisualizer Design Review
shm11C3/HardwareVisualizer
Review or shape HardwareVisualizer product and architecture changes against the maintainer's design principles.
Verify Identity Contracts
shm11C3/HardwareVisualizer
Verify the id/key contract between backend producers and frontend consumers before implementing any change that joins, selects, persists, or attributes entities keyed by backend-produced ids (GPUs…
Related
Works with
Categories
Questions about Gh AI Review Triage
What does Gh AI Review Triage do?
Triage and optionally address AI-generated GitHub PR review feedback from Copilot, CodeRabbit, or similar bots. Gh AI Review Triage is an agent skill from shm11C3/HardwareVisualizer. Triage and optionally address AI-generated GitHub PR review feedback from Copilot, CodeRabbit, or similar bots.
When should I use Gh AI Review Triage?
Gh AI Review Triage fits situations like: the user asks to check AI review comments; decide whether comments require action; ignore non-actionable suggestions; fix required/should-fix/worth-fixing feedback.
How do I install Gh AI Review Triage in Claude Code?
Run `npx skills add shm11C3/HardwareVisualizer --skill gh-ai-review-triage -a claude-code`. Or copy the skill folder (.agents/skills/gh-ai-review-triage in shm11C3/HardwareVisualizer) into .claude/skills/gh-ai-review-triage in your project. Claude Code loads it when a task matches its description.
How do I install Gh AI Review Triage in Codex?
Run `npx skills add shm11C3/HardwareVisualizer --skill gh-ai-review-triage -a codex`. Or copy the skill folder (.agents/skills/gh-ai-review-triage in shm11C3/HardwareVisualizer) into .agents/skills/gh-ai-review-triage in your project. Codex loads it when a task matches its description.
Can I use Gh AI Review Triage 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 shm11C3/HardwareVisualizer --skill gh-ai-review-triage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gh-ai-review-triage, .gemini/skills/gh-ai-review-triage, .github/skills/gh-ai-review-triage and .opencode/skills/gh-ai-review-triage in your project.
What does Gh AI Review Triage need to run?
SKILL.md names no scripts, command-line tools or credentials: Gh AI Review Triage is instructions for the agent only.
Does Gh AI Review Triage access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Gh AI Review Triage 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 Gh AI Review Triage use?
Gh AI Review Triage is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Gh AI Review Triage use?
About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 758 tokens, read only when the agent opens those files.
What are the alternatives to Gh AI Review Triage?
Skills that share tags, products or a category with Gh AI Review Triage: PR Babysitter (openinterpreter/openinterpreter, 69k stars), GitHub Review Iteration (prisma/orm, 48k stars), PR Review State Fetch (prisma/orm, 48k stars) and PR Finalize Review (microsoft/garnet, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Gh AI Review Triage?
shm11C3 (a GitHub user) maintains it in shm11C3/HardwareVisualizer, which has 183 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 11, 2026.
Source: shm11C3/HardwareVisualizer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.