Claude MarketplacesSubmit
dimillian avatar

Review Swarm

dimillian/skills

Four read-only sub-agents review your git diff in parallel, each hunting a different class of problem: regressions against intent, security and privacy risks, performance and reliability issues, and contract or test coverage gaps. The main agent then filters out the noise and gives you a prioritized fix path without touching any files. Use it when you want a second set of eyes before merge and the diff is big enough that parallel review saves time. The strictly read-only design means you get findings and recommendations, not automatic edits, which is the right call when you're looking for issues you might have missed rather than a bot rewriting your code.

skills.sh installs
789
GitHub stars
4K
last updated
Aug 21, 2026
View on GitHub

Install

$ npx -y skills add dimillian/skills --skill review-swarm --agent claude-code

Installs into .claude/skills of the current project.

Files

Review Swarm

Review a diff with four read-only sub-agents in parallel, then have the main agent filter, order, and summarize only the issues that matter. This skill is review-only: sub-agents do not edit files, and the main agent does not apply fixes as part of this workflow.

Step 1: Determine Scope and Intent

Prefer this scope order:

  1. Files or paths explicitly named by the user
  2. Current git changes
  3. An explicit branch, commit, or PR diff requested by the user
  4. Most recently modified tracked files, only if the user asked for a review and there is no clearer diff

If there is no clear review scope, stop and say so briefly.

When using git changes, choose the smallest correct diff command:

  • unstaged work: git diff
  • staged work: git diff --cached
  • mixed staged and unstaged work: review both
  • explicit branch or commit comparison: use exactly what the user requested

Before launching reviewers, read the closest local instructions and any relevant project docs for the touched area, such as:

  • AGENTS.md
  • repo workflow docs
  • architecture or contract docs for the touched module

Build a short intent packet for the reviewers:

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/dimillian/skills
Categories
Testing & QA, Security, Git & Pull Requests, Code Review & Quality, AI & Agent Building, Debugging, Automation & Workflows
First seen
Jun 3, 2026

More from dimillian/skills

All 17

Recommended

More Testing & QA
1github avatarsalesforce-component-standardsgithub/awesome-copilotQuality standards for Salesforce Lightning Web Components (LWC), Aura components, and Visualforce pages. Covers SLDS 2 compliance, accessibility (WCAG 2.1 AA), 770skills.sh installs
2davila7 avatarbrowser-automationdavila7/claude-code-templatesBrowser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understand753skills.sh installs
3github avatarreact18-enzyme-to-rtlgithub/awesome-copilotProvides exact Enzyme → React Testing Library migration patterns for React 18 upgrades. Use this skill whenever Enzyme tests need to be rewritten - shallow, mou742skills.sh installs
4mindrally avatarrspecmindrally/skillsRSpec testing best practices for Ruby and Rails applications, covering test organization, data management, and isolation patterns.734skills.sh installs
5ruvnet avatarsparc-refineruvnet/rufloRun the SPARC Refinement and Completion phases — review code, improve test coverage, validate against specification, and generate documentation730skills.sh installs
6hamelsmu avatargenerate-synthetic-datahamelsmu/evals-skillsCreate diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user 723skills.sh installs