New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Update PR Review

by warpdotdev in warpdotdev/oz-for-oss

Update the repo-local review-pr-local and review-spec-local companion skills using human feedback left on pull request conversations.

MITAuto-check passedDevelopment

Install Update PR Review

skills CLI
$ npx skills add warpdotdev/oz-for-oss --skill update-pr-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install warpdotdev/oz-for-oss update-pr-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/warpdotdev/oz-for-oss.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/update-pr-review .claude/skills/update-pr-review && rm -rf skills-src

Use ~/.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/

Facts

Skill name
update-pr-review
GitHub stars
313
Token cost
~1.6k tokens
SKILL.md length
813 words
Files
2 (incl. scripts)
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

Update the repo-local review-pr-local and review-spec-local companion skills using human feedback left on pull request conversations.

  • Works in 2 steps: Verify GitHub CLI auth → Aggregate the feedback for pull requests…
  • Aggregating replies to agent-authored PR review comments
  • SKILL.md covers Write surface, Inputs, Workflow and Evidence Rules, plus 2 more sections
  • Runs Python scripts from its folder; calls gh, python3 and git

What it does

Update PR Review is an agent skill from warpdotdev/oz-for-oss. Update the repo-local review-pr-local and review-spec-local companion skills using human feedback left on pull request conversations. Use when aggregating replies to agent-authored PR review comments, incorporating broader human review comments, extracting repeated reviewer feedback, and refining .agents/skills/review-pr-local/SKILL.md and .agents/skills/review-spec-local/SKILL.md with evidence-backed adjustments.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/aggregate_review_feedback.py`).

It sits in Development, covering Pull requests. It works with GitHub. The repository describes itself as: Workflows and skills to help people and agents collaborate on open-source software with the power of Oz! The licence is MIT.

When your agent uses it

  • Aggregating replies to agent-authored PR review comments
  • Incorporating broader human review comments
  • Extracting repeated reviewer feedback
  • Refining .agents/skills/review-pr-local/SKILL.md and .agents/skills/review-spec-local/SKILL.md with evidence-backed adjustments

Example prompts

  • “/update-pr-review”

Requirements

  • Python 3

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Verify GitHub CLI auth
  2. Aggregate the feedback for pull requests updated over the last week with the bundled script

What it can do on your machine

Read from SKILL.md and the folder at commit a2bb45f. 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 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • gh
    • python3
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh and git, 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

Update PR Review loads about 1.6k tokens when it runs. Until then it costs about 109 tokens; SKILL.md has 813 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~109
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from warpdotdev/oz-for-oss at commit a2bb45f, republished under its MIT licence (© warpdotdev). 813 words, ~1,585 tokens.

Download SKILL.mdSave it as .claude/skills/update-pr-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
update-pr-review
description
Update the repo-local review-pr-local and review-spec-local companion skills using human feedback left on pull request conversations. Use when aggregating replies to agent-authored PR review comments, incorporating broader human review comments, extracting repeated reviewer feedback, and refining .agents/skills/review-pr-local/SKILL.md and .agents/skills/review-spec-local/SKILL.md with evidence-backed adjustments.

Update PR Review

Use this skill to improve the repo-local review companions .agents/skills/review-pr-local/SKILL.md and .agents/skills/review-spec-local/SKILL.md from real reviewer feedback. The shared review-pr skill and the repo-local core .agents/skills/review-spec/SKILL.md are the cross-repo contracts and are read-only from this loop.

The repository uses two separate review skills: review-pr for code pull requests and review-spec for spec-only pull requests (PRs where every changed file lives under specs/). Feedback from each category of PR should be routed to the corresponding repo-local companion.

Write surface

This self-improvement loop may only write to:

  • .agents/skills/review-pr-local/ (and SKILL.md inside it)
  • .agents/skills/review-spec-local/ (and SKILL.md inside it)

It must NOT touch:

  • the shared review-pr skill
  • .agents/skills/review-spec/SKILL.md (the core contract)
  • any file under .github/issue-triage/ (that taxonomy is owned by the update-triage loop)
  • any other core skill

The self-improvement runner enforces this via a git diff check against allowed prefixes before pushing. A violation aborts the run.

Inputs

  • Optional repository override if you are not running from the target checkout.
  • Optional time window override when you need something other than the default seven-day lookback.
  • Optional agent-login override if the review comments were not authored by the default bot identities.

Workflow

  1. Verify GitHub CLI auth:
bash
gh auth status
  1. Aggregate the feedback for pull requests updated over the last week with the bundled script:
bash
python3 .agents/skills/update-pr-review/scripts/aggregate_review_feedback.py

By default this targets the current repo, looks back 7 days, and analyzes review comments authored by the bot identities used by the PR review workflow (warp-dev-github-integration[bot]). It also collects broader human review comments from those PRs so the skill can learn from reviewer norms even when they were not replying directly to the bot. The script writes structured JSON to a temporary file and prints the temp-file path. Treat that file as scratch state for this skill, not as a user-facing deliverable or final output. If you need a repository other than the current checkout, pass --repo owner/name. If you need a different author identity, pass --agent-login <login> one or more times.

Each pull request in the output includes a review_type field that is either "spec" (all changed files under specs/) or "code" (any non-spec file changed). Use this field to route feedback to the correct skill.

  1. Read the generated JSON and look for repeated reviewer signals, especially:
  • replies that say the agent's feedback was wrong, invalid, not applicable, or based on a bad assumption
  • signals that the agent had the right instinct but the wrong severity, scope, line targeting, or proposed fix
  • feedback that the comment was not actionable enough, including requests for clearer concrete changes
  • recurring cases where humans override the bot because repository or product context changes the right call
  • review patterns from human-only threads that show what experienced reviewers in this repo consistently care about
  • explicit reviewer guidance about what belongs inline, what belongs in the summary, and when the bot should stay uncertain
  1. Partition the feedback by review_type:
  • Feedback from "code" PRs applies to .agents/skills/review-pr-local/SKILL.md.
  • Feedback from "spec" PRs applies to .agents/skills/review-spec-local/SKILL.md.
  • Update each companion skill independently with the smallest rule change that explains the feedback for that category.
  • If feedback for one category is empty, skip that companion.
  1. Keep the core review contract stable — never edit the shared review-pr skill or .agents/skills/review-spec/SKILL.md. Only the -local companions evolve from feedback.
Show full SKILL.md (275 more words)Show less

Evidence Rules

  • Prefer patterns backed by multiple threads or a strong explicit maintainer statement.
  • Do not weaken correctness, security, or data-loss checks because of a single disagreement.
  • Separate feedback about review quality from feedback about repository-specific preferences.
  • Avoid encoding one-off reviewer preferences as universal rules.
  • If the feedback points to missing repository context, add that context only if it improves review precision.
  • Do not mix code-review feedback into the spec skill, or spec-review feedback into the code skill.

Intermediary State

The script builds structured JSON that captures:

  • pull request metadata for the recent PR window, including review_type classification
  • agent-authored review comments that received human replies
  • human-authored review comments from the same PRs, even when they were not replying to the bot
  • thread metadata like file path, line, resolution, and outdated state
  • normalized agent-comment fields such as severity label and whether a suggestion block was present
  • the full set of human replies for each agent comment
  • top-level PR issue comments for broader review context

Use that temporary data as evidence when refining the skills, then remove it before finishing if you wrote it to disk explicitly.

Final Checks

  • Re-read the updated review-pr-local and/or review-spec-local companion skills and confirm any new rules are explicit.
  • Keep each companion concise; do not turn them into long style guides.
  • Commit any changes on a local branch named oz-agent/update-pr-review. Do NOT push the branch; the Python entrypoint will run a write-surface guard and push only when the guard passes.
  • If the updates warrant a PR, it will be opened from the pushed branch. Tag @captainsafia as a reviewer on that PR.
  • Validate any temporary JSON with jq before relying on it.

© warpdotdev, MIT. 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 (scripts) in .agents/skills/update-pr-review of warpdotdev/oz-for-oss.

  • SKILL.md
  • scripts/aggregate_review_feedback.py

Open the folder on GitHubat commit a2bb45f

Compare with similar skills

Update PR Review 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.

Update PR Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Update PR Review this skillwarpdotdev/oz-for-oss313—~1.6kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Pull Request Title and Body Writeropeninterpreter/openinterpreter69k2 repos~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • 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.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed

  • Contributor-First PR Merge

    HKUDS/OpenHarness

    Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed

  • Create Pull Request

    cline/cline

    Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed

  • Pull Request Title and Body Writer

    openinterpreter/openinterpreter

    Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.

    69k GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check passed

  • GitHub Review Iteration

    prisma/orm

    Official

    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.

    48k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed

More from warpdotdev/oz-for-oss

All 17 skills in this repo

  • Update Dedupe

    warpdotdev/oz-for-oss

    Update the repo-local dedupe-issue-local companion skill using closed-as-duplicate signals.

    313 GitHub stars~927 tokensUpdated 20 days ago
    Auto-check passed

  • Bootstrap Issue Config

    warpdotdev/oz-for-oss

    Bootstrap the issue triage configuration for a repository by analyzing existing issues, labels, and contributors to generate .github/issue-triage/config.json and .github/STAKEHOLDERS.

    313 GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

  • Update Triage

    warpdotdev/oz-for-oss

    Update the repo-local triage-issue-local companion skill using signals from recently triaged issues (maintainer re-labels, re-opens, follow-up comments).

    313 GitHub stars~1k tokensUpdated 20 days ago
    Auto-check passed

  • Implement Issue

    warpdotdev/oz-for-oss

    Implement a GitHub issue in this repository by applying the shared implement-specs workflow with Oz-specific issue, spec-context, and summary-file handling.

    313 GitHub stars~2k tokensUpdated 20 days ago
    Auto-check passed

  • Review Spec

    warpdotdev/oz-for-oss

    Review a spec/plan pull request diff and write structured feedback to review.json for the workflow to publish.

    313 GitHub stars~1.9k tokensUpdated 20 days ago
    Auto-check passed

  • Create Product Spec

    warpdotdev/oz-for-oss

    Create a product spec from a GitHub issue in this repository by applying the shared write-product-spec workflow with Oz-specific issue context and output paths.

    313 GitHub stars~1.2k tokensUpdated 20 days ago
    Auto-check passed

Works with

Categories

Questions about Update PR Review

What does Update PR Review do?

Update the repo-local review-pr-local and review-spec-local companion skills using human feedback left on pull request conversations. Update PR Review is an agent skill from warpdotdev/oz-for-oss. Update the repo-local review-pr-local and review-spec-local companion skills using human feedback left on pull request conversations.

When should I use Update PR Review?

Update PR Review fits situations like: aggregating replies to agent-authored PR review comments; incorporating broader human review comments; extracting repeated reviewer feedback; refining .agents/skills/review-pr-local/SKILL.md and .agents/skills/review-spec-local/SKILL.md with evidence-backed adjustments.

How do I install Update PR Review in Claude Code?

Run `npx skills add warpdotdev/oz-for-oss --skill update-pr-review -a claude-code`. Or copy the skill folder (.agents/skills/update-pr-review in warpdotdev/oz-for-oss) into .claude/skills/update-pr-review in your project. Claude Code loads it when a task matches its description.

How do I install Update PR Review in Codex?

Run `npx skills add warpdotdev/oz-for-oss --skill update-pr-review -a codex`. Or copy the skill folder (.agents/skills/update-pr-review in warpdotdev/oz-for-oss) into .agents/skills/update-pr-review in your project. Codex loads it when a task matches its description.

Can I use Update PR Review 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 warpdotdev/oz-for-oss --skill update-pr-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-pr-review, .gemini/skills/update-pr-review, .github/skills/update-pr-review and .opencode/skills/update-pr-review in your project.

What does Update PR Review need to run?

Going by SKILL.md and its folder, Update PR Review needs Python for the scripts in its folder and the command-line tools its instructions call (gh, python3 and git). Our summary lists: Python 3.

Does Update PR Review access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Update PR Review 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Update PR Review use?

Update PR Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Update PR Review use?

About 1.6k tokens (SKILL.md is roughly 6.3k 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 Update PR Review?

Skills that share tags, products or a category with Update PR Review: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update PR Review?

warpdotdev (a GitHub organization) maintains it in warpdotdev/oz-for-oss, which has 313 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on September 17, 2026.

Source: warpdotdev/oz-for-oss on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.