397fa2aa5d
* Fix SEO skill 34 bugs, Korean labels, and transition Ahrefs refs to our-seo-agent P0: Fix report_aggregator.py — wrong SKILL_REGISTRY[33] mapping, missing CATEGORY_WEIGHTS for 7 categories, and break bug in health score parsing that exited loop even on parse failure. P1: Remove VIEW tab references from skill 20, expand skill 32 docs, replace Ahrefs MCP references across all 16 skills (19-28, 31-34) with our-seo-agent CLI data source references. P2: Fix Korean labels in executive_report.py and dashboard_generator.py, add tenacity to base requirements, sync skill 34 base_client.py with canonical version from skill 12. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add Claude Code slash commands for SEO skills 19-34 and fix stale paths Create 14 new slash command files for skills 19-28, 31-34 so they appear as /seo-* commands in Claude Code. Also fix stale directory paths in 8 existing commands (skills 12-18, 29-30) that referenced pre-renumbering skill directories. Update .gitignore to track .claude/commands/ while keeping other .claude/ files ignored. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add 8 slash commands, enhance reference-curator with depth/output options - Add slash commands: ourdigital-brand-guide, notion-writer, notebooklm-agent, notebooklm-automation, notebooklm-studio, notebooklm-research, reference-curator, multi-agent-guide - Add --depth (light/standard/deep/full) with Firecrawl parameter mapping - Add --output with ~/Documents/reference-library/ default and user confirmation - Increase --max-sources default from 10 to 100 - Rename /reference-curator-pipeline to /reference-curator - Simplify web-crawler-orchestrator label to web-crawler in docs Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2.2 KiB
2.2 KiB
description: Set up multi-agent collaboration framework (Claude, Gemini, Codex) with guardrails
argument-hint: [--quick] [--full]
Multi-Agent Guide
Set up multi-agent collaboration framework for projects where multiple AI agents work together.
Triggers
- "set up multi-agent", "agent guardrails", "multi-agent collaboration"
Quick Setup (Recommended)
Rapid deployment with minimal questions:
- Assess project structure
- Ask which agents participate (Claude/Gemini/Codex/Human)
- Create framework files
- Customize ownership matrix
Files Created
your-project/
├── .agent-state/
│ ├── tasks.yaml # Task registry
│ └── locks.yaml # Lock registry
├── tools/
│ └── check-ownership.py # Ownership verification
├── MULTI_AGENT_FRAMEWORK.md # Consolidated rules
├── GEMINI.md # Sub-agent directive (if selected)
└── CODEX.md # Sub-agent directive (if selected)
Agent Hierarchy
┌─────────────────┐
│ Claude Code │
│ (Lead Agent) │
└────────┬────────┘
│
┌──────────────┼──────────────┐
v v v
┌──────────┐ ┌──────────┐ ┌──────────┐
│ Gemini │ │ Codex │ │ Human │
│(Research)│ │ (Speed) │ │ (Review) │
└──────────┘ └──────────┘ └──────────┘
Commit Message Format
[Agent] type(scope): description
Examples:
[Claude] feat(core): implement new feature
[Gemini] docs(api): update API documentation
[Codex] test(models): add unit tests
Post-Setup
- Set agent identity:
export AGENT_AUTHOR=claude - Review ownership matrix in
MULTI_AGENT_FRAMEWORK.md - Install pre-commit hooks:
pre-commit install(optional)
Source
Full details: custom-skills/91-multi-agent-guide/README.md
Related commands: custom-skills/91-multi-agent-guide/commands/