review-branch
Review all changes on the current branch against main for quality, security and maintainability, and print the review without posting it anywhere.
Skill by crcatala
Chalk Labs
Need help deploying review-branch?
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/crcatala-review-branch
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
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/review-branch
What's inside
- Skill name
review-branch- Description
- Review all changes on the current branch against main for quality, security and maintainability, and print the review without posting it anywhere.
- License
- MIT
- Instructions
- 7 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
If your harness provides a code-review subagent, delegate this task to it; otherwise do it yourself: Review all changes on the current branch compared to main. Use `git diff main...HEAD` to get the diff. Focus on code quality, security, and maintainability. Do NOT post to GitHub, just output the review. Any additional text supplied when this skill was invoked (a trailing `ARGUMENTS:` line, or a user message following these instructions) is extra context or instructions for this task; apply it.
From crcatala/skills, MIT.
More from crcatala/skills
- 0.570score
anatomy
crcatala
Build crafted, highly detailed, interactive isometric SVG figures that explain a technical idea as a real physical object (a test rig, a dial gauge, a cabinet…
SkillAFreshness: AClaude Code +9 - 0.565score
image-gen
crcatala
Generate or edit images with OpenAI GPT Image (gpt-image-2.5-flare, default) or xAI Grok Imagine (grok-imagine-image-2.0).
SkillAFreshness: AClaude Code +9 - 0.565score
github-pr-screenshots
crcatala
Upload local screenshots or captures (PNG, SVG, other image files) to a GitHub pull request with gh-attach and embed the returned markdown in the requested PR…
SkillAFreshness: AClaude Code +9 - 0.565score
grok-research
crcatala
Deep research via Grok 4.6 — agentic web + X (Twitter) search.
SkillAFreshness: AClaude Code +9 - 0.563score
repo-icons
crcatala
Wizard that finds your recently active GitHub repositories without a usable icon, generates icon concepts in a choice of styles, lets you pick them on a…
SkillAFreshness: AClaude Code +9 - 0.561score
ralph
crcatala
Use Ralph for autonomous, ticket-native campaign delivery: ordered tk tickets, one PR per ticket, committed recipes and prompts, checks, merge, status, logs…
SkillAFreshness: AClaude Code +9 - 0.561score
brave-web
crcatala
Fast web search and safe URL extraction through Brave Search.
SkillAFreshness: AClaude Code +9 - 0.561score
evaluate-competing-prs
crcatala
Compare multiple PRs from different agents that implement the same task, with scoring and a recommendation saved to docs/evaluations/.
SkillAFreshness: AClaude Code +9 - 0.561score
exa-code
crcatala
Search for code documentation, examples, and API references using Exa AI.
SkillAFreshness: AClaude Code +9 - 0.561score
review-and-fix-pr
crcatala
Review the PR for this branch (Good/Bad/Ugly), comment the assessment on the PR, fix the issues worth addressing, then commit and push.
SkillAFreshness: AClaude Code +9 - 0.561score
agent-browser
crcatala
Browser automation via Vercel's agent-browser CLI.
SkillAFreshness: AClaude Code +9 - 0.561score
review-pr-good-bad-ugly
crcatala
Read the PR for this branch in full (description, comments, commits, linked issues, diff) and produce a structured Good/Bad/Ugly review.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 1, 2026 (29 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/crcatala/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from crcatala
- 0.570score
anatomy
crcatala
Build crafted, highly detailed, interactive isometric SVG figures that explain a technical idea as a real physical object (a test rig, a dial gauge, a cabinet…
SkillAFreshness: AClaude Code +9 - 0.565score
image-gen
crcatala
Generate or edit images with OpenAI GPT Image (gpt-image-2.5-flare, default) or xAI Grok Imagine (grok-imagine-image-2.0).
SkillAFreshness: AClaude Code +9 - 0.565score
grok-research
crcatala
Deep research via Grok 4.6 — agentic web + X (Twitter) search.
SkillAFreshness: AClaude Code +9 - 0.565score
github-pr-screenshots
crcatala
Upload local screenshots or captures (PNG, SVG, other image files) to a GitHub pull request with gh-attach and embed the returned markdown in the requested PR…
SkillAFreshness: AClaude Code +9 - 0.563score
repo-icons
crcatala
Wizard that finds your recently active GitHub repositories without a usable icon, generates icon concepts in a choice of styles, lets you pick them on a…
SkillAFreshness: AClaude Code +9 - 0.561score
evaluate-competing-prs
crcatala
Compare multiple PRs from different agents that implement the same task, with scoring and a recommendation saved to docs/evaluations/.
SkillAFreshness: AClaude Code +9
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 review-branch 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
review-branch skill. Agent Mart. https://agentmart.dev/skills/crcatala-review-branch (last updated 2026-10-24)