KS
Killer-Skills

git-routing — how to use git-routing how to use git-routing, git-routing setup guide, git-routing alternative, git-routing vs conventional commits, git-routing install, what is git-routing, git-routing for AI agents, standardized commit messages, git-routing best practices

v1.0.0
GitHub

About this Skill

Perfect for Multi-Agent Project Managers needing standardized commit message formatting. git-routing is a commit message formatting standard for AI agent projects, using a specific header format with required fields.

Features

Enforces a specific commit message header format with required fields
Supports multiple agent values, including claude, cursor, lovable, and kimi
Requires a short description under 72 characters
Allows for an optional body with details
Uses a standardized format for task IDs and actions

# Core Topics

AgentArtel AgentArtel
[0]
[0]
Updated: 3/6/2026

Quality Score

Top 5%
57
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add AgentArtel/Open-RPG/git-routing

Agent Capability Analysis

The git-routing MCP Server by AgentArtel is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use git-routing, git-routing setup guide, git-routing alternative.

Ideal Agent Persona

Perfect for Multi-Agent Project Managers needing standardized commit message formatting.

Core Value

Empowers agents to maintain consistent commit history using a standardized header format, including AGENT, ACTION, and TASK fields, ensuring clarity and readability in git repositories, with support for agents like Claude Code, Cursor, and Lovable.

Capabilities Granted for git-routing MCP Server

Standardizing commit messages for multi-agent projects
Automating commit message formatting for consistent clarity
Debugging commit history using standardized TASK and ACTION fields

! Prerequisites & Limits

  • Requires adherence to the specified commit message header format
  • Limited to the defined set of valid AGENT values, including 'claude', 'cursor', and 'lovable'
Project
SKILL.md
4.0 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Commit Message Format

Every commit in a multi-agent project uses this header format:

[AGENT:agent] [ACTION:action] [TASK:task-id] Short description

Optional body with details.

All three header fields are required. The short description should be under 72 characters.

Valid AGENT Values

ValueAgentRole
claudeClaude CodeOrchestrator
cursorCursorImplementation Specialist
lovableLovableUI/UX Specialist
kimiKimi CodeProject Overseer

Valid ACTION Values

ValueMeaningWho Uses It
submitWork completed, ready for reviewAny agent submitting work
reviewReview in progressReviewer (Kimi or Claude Code)
approveWork approvedReviewer
rejectWork needs changes, feedback providedReviewer
updateProgress update (not a submission)Any agent
reportSprint or status reportKimi or Claude Code
delegateAssigning work to another agentKimi or Claude Code
mergeMerging approved work to target branchKimi or Claude Code

Valid TASK Values

PatternWhen to UseExample
Task IDStandard task workTASK-001, TASK-P4-01
Sprint IDSprint-level workSPRINT-3, SPRINT-4
CategoryNon-task workINFRA, DOCS, CLEANUP

Routing Table

This table defines what should happen after each commit pattern:

Commit PatternWhat Happens Next
[AGENT:cursor] [ACTION:submit] [TASK:X]Kimi or Claude Code reviews cursor's work
[AGENT:lovable] [ACTION:submit] [TASK:X]Kimi or Claude Code reviews lovable's work
[AGENT:claude] [ACTION:submit] [TASK:X]Kimi reviews claude's work
[AGENT:kimi] [ACTION:approve] [TASK:X]Work merged to pre-mortal, next task assigned
[AGENT:kimi] [ACTION:reject] [TASK:X]Agent addresses feedback, re-submits
[AGENT:kimi] [ACTION:delegate] [TASK:X]Target agent picks up assignment
[AGENT:kimi] [ACTION:report] [SPRINT:X]Human PM reviews sprint summary
[AGENT:kimi] [ACTION:merge] [TASK:X]Branch merged to pre-mortal
[AGENT:claude] [ACTION:delegate] [TASK:X]Target agent picks up assignment
[AGENT:*] [ACTION:update] [TASK:X]Status tracking only, no action triggered

Branch Rules

  • Agents commit to their own branch: <agent>/<task-id>-<description>
  • Submit commits are made on the agent's branch
  • Approve and merge commits are made on pre-mortal
  • Report commits can be made on any branch

Examples

Agent submitting work

[AGENT:cursor] [ACTION:submit] [TASK:TASK-P4-01] Implement gateway API client hook

Added WebSocket JSON-RPC client with reconnection logic.
Files: src/hooks/use-gateway-api.ts, src/services/openclaw-client.ts

Reviewer approving work

[AGENT:kimi] [ACTION:approve] [TASK:TASK-P4-01] Gateway API client approved

All acceptance criteria met. Merging to pre-mortal.
Unblocks: TASK-P4-02, TASK-P4-03

Reviewer requesting changes

[AGENT:kimi] [ACTION:reject] [TASK:TASK-P4-01] Error handling needs improvement

Missing timeout handling on WebSocket reconnection.
See .ai/reviews/TASK-P4-01-review.md for details.

Progress update

[AGENT:claude] [ACTION:update] [TASK:TASK-002] Enrich ideas with research findings

Updated 18 idea files with feasibility ratings and roadmap phases.

Sprint report

[AGENT:kimi] [ACTION:report] [SPRINT:3] Sprint 3 complete — 8 tasks done

See .ai/reports/sprint-3-summary.md for full details.

Delegating work

[AGENT:kimi] [ACTION:delegate] [TASK:TASK-P4-02] Assign agent CRUD sync to Cursor

See .ai/instructions/cursor-TASK-P4-02.md for assignment details.

Merging approved work

[AGENT:kimi] [ACTION:merge] [TASK:TASK-P4-01] Merge gateway client to pre-mortal

Approved in .ai/reviews/TASK-P4-01-review.md

Reference

Full routing specification with additional details: .ai/templates/commit-message.md

Related Skills

Looking for an alternative to git-routing or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication