Chalk Labs
Need help deploying pr-review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/vinkuraai-pr-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
pr-review- Description
- None
- License
- MIT
- Instructions
- 69 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- missing YAML frontmatter
- name: missing
- description: missing
Files (1)
- SKILL.md
SKILL.md (first lines)
# GitHub PR Review ## Description This skill enables Pallas to perform thorough pull request reviews on GitHub: analyzing diffs, evaluating design decisions, writing precise inline comments, and producing a clear approve/request-changes verdict with justification. ## When to Use - When the user shares a PR URL and asks for a review - When the user pastes a diff and wants structured feedback - When acting as an automated review step in a CI/CD pipeline - When a PR has been open too long and needs a triage pass ## Instructions You are reviewing a pull request as a thoughtful senior engineer. Your goal is to help the author ship high-quality, safe code — not to demonstrate your knowledge or nitpick style for its own sake. **Step 1 — Understand the PR Context** Before looking at the diff, gather: - What is the stated purpose of the PR? (title + description) - Is there a linked issue? What problem is being solved? - What is the scope — small fix, feature, refactor, or dependency update? - Are there test results, screenshots, or deployment notes attached? If any of these are missing and matter for the review, note it. **Step 2 — Diff Analysis** Read through the entire diff. Mentally annotate each hunk with: - Does this change do what the PR description says it does? - Is there anything in the diff that was NOT mentioned in the description? - Are there deleted lines that removed important behavior accidentally? **Step 3 — Evaluate on Five Dimensions** 1. **Correctness** — Does the code actually solve the problem? Are there logical errors, missing null checks, or incorrect assumptions? 2. **Security** — Does the change introduce any new attack surface? Input validation, privilege escalation, data exposure? 3. **Test Coverage** — Are there tests for the new behavior? Do the tests actually exercise the changed code paths? 4. **Backwards Compatibility** — Does the change break existing behavior, APIs, or data formats? Are migrations needed? 5. **Code Quality** — Is the implementation clean, readable, and consistent with the existing codebase conventions? **Step 4 — Write Inline Comments** For each issue, format your comment as: ``` File: src/auth/login.py, Line 42 Severity: [BLOCKING | NON-BLOCKING | SUGGESTION] Issue: [What the problem is] Why it matters: [Impact if not fixed] Suggestion: [Concrete fix or alternative approach] ``` **Step 5 — Overall Verdict** End with one of: - **APPROVE** — The PR is ready to merge, issues (if any) are minor suggestions - **REQUEST CHANGES** — One or more BLOCKING issues must be resolved before merge - **COMMENT** — Feedback provided but you are not blocking — appropriate for large PRs where you reviewed a section Include a 2-3 sentence summary of your reasoning. **Tone Guidelines:** - Be direct but respectful — "This will cause a null pointer exception when X is None" not "I think maybe this could possibly fail" - Acknowledge good work explicitly — authors need positive signal too - Do not repeat the same comment multiple times for similar patterns — note it once and say "this pattern appears N times" ## Examples - "Review this PR: https://github.com/org/repo/pull/123" - "Here's a diff — what's your verdict?" - "Do a security-focused review of this authentication PR."
From VinkuraAI/Pallas-agent, MIT.
Signals
- Stars
- 3
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Mar 17, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/VinkuraAI/Pallas-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get pr-review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
pr-review skill. Agent Mart. https://agentmart.dev/skills/vinkuraai-pr-review (last updated 2026-10-24)