Delegate independent tasks to specialized agents working concurrently with isolated context.
Init Agents Config
init-agents-config
Generate .agents.yml config from user answers. Provides tech stack templates for Rails, Python, Node, and Generic projects.
SKILL.md
Full skill instructions
Init Agents Config
Assemble .agents.yml from collected user answers during /majestic:init.
Resources
| Resource | Purpose |
|---|---|
CONFIG_VERSION | Current .agents.yml schema version |
resources/rails.yaml | Rails config template |
resources/python.yaml | Python config template |
resources/node.yaml | Node config template |
resources/generic.yaml | Generic config template |
resources/agents-md-template.md | AGENTS.md best practices |
resources/local-config-template.yaml | Local overrides template |
Template Selection by Tech Stack
| Tech Stack | Template |
|---|---|
| Rails | resources/rails.yaml |
| Python | resources/python.yaml |
| Node | resources/node.yaml |
| Generic | resources/generic.yaml |
Assembly Instructions
- Read the appropriate template based on detected
tech_stack - Replace placeholders with collected answers:
{{config_version}}- Read fromCONFIG_VERSIONfile{{default_branch}}- From git detection or user answer{{owner_level}}- beginner, intermediate, senior, expert{{task_management}}- github, linear, beads, file, none- Stack-specific fields from user answers
- Conditionally include/exclude sections:
- Remove
extras:section if no Solid gems selected (Rails) - Remove
toolbox.build_task.design_system_pathif no design system detected - Comment out
browser:section unless user selected non-Chrome browser
- Remove
- Write to
.agents.yml
Conditional Sections
Quality Gate Reviewers
Each stack has default reviewers. Include optional reviewers only if user enables them:
dhh-code-reviewer- Rails strict styledata-integrity-reviewer- Migration safetycodex-reviewer/gemini-reviewer- External LLM
Browser Config
Default is commented out (uses Chrome). Uncomment only if user selects Brave or Edge.
Extras (Rails only)
Include only Solid gems the user selected:
solid_cachesolid_queuesolid_cable
Output
Write generated config to .agents.yml in project root.
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
