branch-review
Review any branch — check diff, analyze code against standards, provide recommendations
Skill by dagda1
Chalk Labs
Need help deploying branch-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/dagda1-branch-review-d12998
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
branch-review- Description
- Review any branch — check diff, analyze code against standards, provide recommendations
- License
- unknown
- Instructions
- 201 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from dagda1/claude
- 0.559score
m
dagda1
Teach maths one concept at a time, checking each with a question.
SkillAFreshness: AClaude Code +9 - 0.556score
spec
dagda1
Agree a spec for a piece of work and write its failing acceptance tests, ready for /build.
SkillAFreshness: AClaude Code +9 - 0.556score
build
dagda1
Build an approved spec with no conversation — make every check pass, run up to three review rounds, and write a summary the user audits afterwards.
SkillAFreshness: AClaude Code +9 - 0.556score
retro
dagda1
After you have audited a finished task, find what the harness got wrong and propose at most one change to a skill or check so it does not happen again.
SkillAFreshness: AClaude Code +9 - 0.556score
assistant-communication
dagda1
Communication style for the assistant — no follow-up nudges, one direct question when unsure, no hedging, no padding patterns, claims labelled with their…
SkillAFreshness: AClaude Code +9 - 0.549score
branch-review
dagda1
Review any branch — check diff, analyze code against standards, provide recommendations
SkillAFreshness: AClaude Code +9 - 0.534score
grilling
dagda1
Grill the user relentlessly about a plan, decision, or idea.
SkillAFreshness: AClaude Code +9 - 0.519score
code-no-defensive-fallbacks
dagda1
Do not paper over missing values with `??
SkillBFreshness: BClaude Code +9 - 0.469score
code-test-colocation
dagda1
Test files live next to source — `foo.ts` → `foo.test.ts`, `Bar.tsx` → `Bar.test.tsx`.
SkillCFreshness: CClaude Code +9 - 0.469score
cdk-stateful-resources
dagda1
Safe handling of stateful AWS resources in CDK — explicit removal policies, deletion protection, backup retention, snapshot-on-delete.
SkillCFreshness: CClaude Code +9 - 0.469score
code-trust-the-types
dagda1
TypeScript discipline — trust the types, no defensive runtime checks for things the compiler already guarantees.
SkillCFreshness: CClaude Code +9 - 0.469score
code-style-defaults
dagda1
Generic code style defaults — no comments, no single-character variables, braces on all if statements, blank lines between logical sections, prefer existing…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/dagda1/claude
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from dagda1
- 0.559score
m
dagda1
Teach maths one concept at a time, checking each with a question.
SkillAFreshness: AClaude Code +9 - 0.556score
retro
dagda1
After you have audited a finished task, find what the harness got wrong and propose at most one change to a skill or check so it does not happen again.
SkillAFreshness: AClaude Code +9 - 0.556score
assistant-communication
dagda1
Communication style for the assistant — no follow-up nudges, one direct question when unsure, no hedging, no padding patterns, claims labelled with their…
SkillAFreshness: AClaude Code +9 - 0.556score
build
dagda1
Build an approved spec with no conversation — make every check pass, run up to three review rounds, and write a summary the user audits afterwards.
SkillAFreshness: AClaude Code +9 - 0.556score
spec
dagda1
Agree a spec for a piece of work and write its failing acceptance tests, ready for /build.
SkillAFreshness: AClaude Code +9 - 0.549score
branch-review
dagda1
Review any branch — check diff, analyze code against standards, provide recommendations
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 branch-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
branch-review skill. Agent Mart. https://agentmart.dev/skills/dagda1-branch-review-d12998 (last updated 2026-10-24)