Multipov Code — AI skill for Claude Code
Run a multi-agent code review on $ARGUMENTS (default: current branch changes) via the multipov.ai MCP server.
How to install Multipov Code
Installs to ~/.claude/skills/capitalthought-multipov-docs-multipov-code/SKILL.md
mkdir -p ~/.claude/skills/capitalthought-multipov-docs-multipov-code && curl -fsSL https://raw.githubusercontent.com/capitalthought/multipov-docs/HEAD/skills/multipov-code.md -o ~/.claude/skills/capitalthought-multipov-docs-multipov-code/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Multipov Code does
Run a multi-agent code review on `$ARGUMENTS` (default: current branch changes) via the multipov.ai MCP server.
Determine the diff range from arguments: `--staged`, `--unstaged`, or a ref range like `main..HEAD` (default).
Fallback: Review Last Committed Work
Before proceeding, check whether the determined diff range contains changes:
DIFF_OUTPUT=$(git diff --stat $DIFF_RANGE 2>/dev/null)
If `$DIFF_OUTPUT` is empty AND there are no staged or unstaged changes:
- Fall back to
Alternatives in AI
- Rmslop — Remove AI code slop from current branch 508 ★
- Add New Provider — Add a new AI provider "$ARGUMENTS" to the OpenUsage TUI dashboard 180 ★
- Comfy Generate 3D — Generate a 3D model using Comfy Cloud based on the user's description: $ARGUMENTS 178 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Multipov Performance
Run a multi-agent performance-focused code review on $ARGUMENTS (default: current branch changes) via the mult
Multipov Reliability
Run a multi-agent reliability-focused code review on $ARGUMENTS (default: current branch changes) via the mult
Review PR Comments
Triage and resolve AI or human GitHub PR review comments for the current branch.
Review Slop
Review the current branch diff against main for AI-generated code slop — unnecessary or stylistically inconsis
Aigate AI Git Workflow Guard CLI
Pre-push Git safety CLI for AI-assisted coding: catch risky changes, possible secrets, weak PR readiness, and
Lad MCP Server
Lad MCP Server: Autonomous code & system design review for AI coding agents (Claude Code, Cursor, Codex, etc.)
Related Agents
Failure Diagnostician
Use when a check is red or a run crashed and the cause is not obvious, or to reproduce a claimed defect/histor
Code Reviewer Compatibility
Use this agent for backwards compatibility analysis of code changes. Focuses exclusively on breaking changes t
Reviewer Compatibility
Compatibility specialist reviewer. Focuses on breaking changes to code already shipped in the default branch: