spawn skill
Generates comprehensive, PhD-level expert agent prompt files in Markdown format for use with Claude Code.
- GitHub stars
- 81
- Files
- 4
- Last commit
- Nov 7, 2026
- License
- MIT
- Allowed tools
- 6
What does the spawn skill do?
spawn generates comprehensive, PhD-level expert agent prompt files in Markdown format for use with Claude Code.
Summary generated from the skill's SKILL.md.
About the spawn skill
Creating specialized, high-level expert personas for Claude Code is the primary function of this tool. It generates comprehensive Markdown files that serve as definitive domain references, designed to mimic the depth of a PhD-level practitioner. Developers use it to author new agent prompts rather than running them, producing files that include detailed patterns, configuration examples, and testing strategies.
Users can generate a single agent for a specific technology, create multiple agents in a batch from a list, or perform an architecture analysis to identify necessary experts for a given tech stack. The tool utilizes WebSearch and WebFetch to research official documentation, ensuring the generated content is accurate. It can save these files to a project-specific directory for team sharing or to a global user directory for use across all local projects. Each output includes YAML frontmatter and follows a strict ten-part structure to ensure consistency and depth.
What an agent can do with it
- 1Generate a single technology expertCreate a highly detailed Markdown prompt for a specific framework like Redis with custom focus areas.
- 2Batch create multiple agent filesProduce several expert agent prompts at once from a provided list of different technology platforms.
- 3Analyze architecture for required agentsProvide a description of a tech stack to automatically identify and suggest relevant expert agents to build.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the spawn skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the spawn skill in Plugin
/plugin marketplace add 0xDarkMatter/claude-mods /plugin install claude-mods@claude-mods
Install the spawn skill in Claude Code
~/.claude/skills/spawn/SKILL.md
$ npx degit 0xDarkMatter/claude-mods/skills/spawn ~/.claude/skills/spawnInstall the spawn skill in Claude Code (project)
.claude/skills/spawn/SKILL.md
$ npx degit 0xDarkMatter/claude-mods/skills/spawn .claude/skills/spawnInstall the spawn skill in Codex
~/.agents/skills/spawn/SKILL.md
$ npx degit 0xDarkMatter/claude-mods/skills/spawn ~/.agents/skills/spawnInstall the spawn skill in Gemini CLI
~/.gemini/skills/spawn/SKILL.md
$ npx degit 0xDarkMatter/claude-mods/skills/spawn ~/.gemini/skills/spawnInstall the spawn skill in Claude.ai
npx degit 0xDarkMatter/claude-mods/skills/spawn spawn && zip -r spawn.zip spawn # claude.ai → Customize → Skills → + → Create skill → Upload a skill → spawn.zip
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A skill needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachable0xdarkmatter/claude-mods/skills/spawn is public and reachablegithub.com/0xdarkmatter/claude-mods/tree/HEAD/skills/spawn ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-07github.com/0xdarkmatter/claude-mods/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/0xdarkmatter/claude-mods/blob/HEAD/skills/spawn/S ↗Pass
- Pre-approved tools are scopedBash lets the agent run any shell command without askinggithub.com/0xdarkmatter/claude-mods/blob/HEAD/skills/spawn/S ↗Finding
- SKILL.md follows the Agent Skills formatthe description does not say when to use the skillgithub.com/0xdarkmatter/claude-mods/blob/HEAD/skills/spawn/S ↗Finding
SKILL.md
View on GitHubSpawn - Expert Agent Generator
Generate world-class, comprehensive expert agent prompts for Claude Code. Each agent should be a definitive reference for its domain - the kind of guide a PhD-level practitioner would create.
Target quality: 500-1000 lines per agent with real code examples, complete configs, and detailed patterns.
Benchmark agents: firecrawl-expert.md (1026 lines), project-organizer.md (610 lines)
Usage Modes
Mode 1: Single Agent Generation
Generate one expert agent prompt for a specific technology platform.
Prompt for:
- Technology platform/framework name
- Scope (project-level or global/user-level)
- Focus areas (optional: specific features, patterns, use cases)
- Output format (markdown file or clipboard-ready text)
Mode 2: Batch Agent Generation
Create multiple agent prompts from a list of technology platforms.
Accept:
- Multi-line list of technology platforms
- Scope (project-level or global/user-level)
- Common focus areas (optional)
- Output format (individual .md files or consolidated text)
Mode 3: Architecture Analysis
Analyze a tech stack or architecture description and suggest relevant agents.
Process:
- Read architecture description (from user input or file)
- Identify all technology platforms/services
- Ask for scope (project or global)
- Present checkbox selector for agent creation
- Generate selected agents
Agent File Format
All agents MUST be created as Markdown files with YAML frontmatter:
- Project-level:
.claude/agents/(current project only) - Global/User-level:
~/.claude/agents/orC:\Users\[username]\.claude\agents\(all projects)
File Structure:
---
name: technology-name-expert
description: When this agent should be used. Can include examples and use cases. No strict length limit - be clear and specific. Include "use PROACTIVELY" for automatic invocation.
model: inherit
color: blue
---
[Agent system prompt content here]
YAML Frontmatter Fields:
name(required): Unique identifier, lowercase-with-hyphens (e.g., "redis-expert")description(required): Clear, specific description of when to use this agent- No strict length limit - prioritize clarity over brevity
- Can include examples, use cases, and context
- Use "use PROACTIVELY" or "MUST BE USED" to encourage automatic invocation
- Multi-line YAML string format is fine for lengthy descriptions
tools(optional): Comma-separated list of allowed tools (e.g., "Read, Grep, Glob, Bash")- If omitted, agent inherits all tools from main session
- Best practice: Only grant tools necessary for the agent's purpose (improves security and focus)
model(optional): Specify model ("sonnet", "opus", "haiku", or "inherit" to use main session model)color(optional): Visual identifier in UI ("blue", "green", "purple", etc.)
File Creation: Agents can be created programmatically using the Write tool:
Project-level: .claude/agents/[platform]-expert.md
Global/User-level: ~/.claude/agents/[platform]-expert.md (or C:\Users\[username]\.claude\agents\ on Windows)
Choosing Scope:
- Project Agent (
.claude/agents/): Specific to the current project, can be version controlled and shared with team - Global Agent (
~/.claude/agents/): Available across all projects on your machine
After creation, Claude Code picks the file up within seconds and the agent is available
through the Agent tool (named Task before Claude Code 2.1.63; Task(...) still works as an
alias). The one exception: the first agent in an agents/ directory that did not exist when
the session started needs a session restart to load.
Claude Code Agent Documentation
Essential Reading:
- Subagents Overview: https://docs.claude.com/en/docs/claude-code/sub-agents
- Subagents in SDK: https://docs.claude.com/en/api/agent-sdk/subagents
- Agent SDK Overview: https://docs.claude.com/en/api/agent-sdk/overview
- Agent Skills Guide: https://docs.claude.com/en/docs/claude-code/skills
- Agent Skills in SDK: https://docs.claude.com/en/api/agent-sdk/skills
- Skill Authoring Best Practices: https://docs.claude.com/en/docs/agents-and-tools/agent-skills/best-practices
- Using Agent Skills with API: https://docs.claude.com/en/api/skills-guide
- Agent Skills Quickstart: https://docs.claude.com/en/docs/agents-and-tools/agent-skills/quickstart
- Claude Code Settings: https://docs.claude.com/en/docs/claude-code/settings
- Common Workflows: https://docs.claude.com/en/docs/claude-code/common-workflows
- Claude Code Overview: https://docs.claude.com/en/docs/claude-code/overview
- Plugins Reference: https://docs.claude.com/en/docs/claude-code/plugins-reference
Key Concepts from Documentation:
- Subagents operate in separate context windows with customized system prompts
- Each subagent can have restricted tool access for focused capabilities
- Multiple subagents can run concurrently for parallel processing
- User-level agents (
~/.claude/agents/) are available across all projects - Project-level agents (
.claude/agents/) are project-specific and shareable - Use
/agentscommand for the recommended UI to manage agents - Start with Claude-generated agents, then customize for best results
- Version control project-level subagents for team collaboration
Generation Requirements
For each agent, create a comprehensive expert prompt with:
Agent Content Structure (10-Part Template):
Every generated agent MUST follow this comprehensive 10-part structure:
- Part 1: Core Concepts - Fundamental principles, mental model, architecture overview
- Part 2: Essential Patterns (5-10 patterns) - Each with: when to use, full implementation (20-50 lines), variations, common mistakes
- Part 3: Advanced Techniques (3-5 techniques) - Deep dives with complete examples
- Part 4: Configuration - Complete dev config, complete prod config, environment variables table
- Part 5: Integration Patterns - Integration code for 2-3 common technologies
- Part 6: Testing Strategies - Unit tests with mocks, integration tests, test configuration
- Part 7: Error Handling - Custom exception hierarchy, retry/circuit breaker patterns, structured logging
- Part 8: Performance Optimization - Profiling techniques, optimization table, caching strategies
- Part 9: Security Considerations - Common vulnerabilities, security hardening checklist
- Part 10: Quick Reference - Common operations cheat sheet (20-30 snippets), CLI commands, troubleshooting table
Plus: Quality Checklist, Anti-Patterns (5-10 with bad/good code), Canonical Resources (10-15 URLs)
See firecrawl-expert.md and project-organizer.md in agents/ for reference implementations.
Requirements:
- YAML frontmatter at top with required fields (name, description)
- Concise, actionable system prompt (not verbose)
- Minimum 10 official/authoritative URLs
- Include real, production-ready code examples (10+ code blocks)
- Include complete configuration files (dev + prod)
- Include testing patterns with actual test code
- Focus on patterns, best practices, architecture
- Include canonical references for expansion
- Markdown formatted for direct use
- Description field can be lengthy with examples if needed for clarity
Output Options
Ask user to choose scope:
- Project Agent - Save to
.claude/agents/(project-specific, version controlled) - Global Agent - Save to
~/.claude/agents/orC:\Users\[username]\.claude\agents\(all projects)
Ask user to choose format:
- Clipboard-ready - Output complete markdown (with YAML frontmatter) in code block
- File creation - Use Write tool to save to appropriate agents directory based on scope
- Both - Create file using Write tool AND show complete content in chat for review
File Creation Process: When creating files programmatically:
- Generate complete agent content with YAML frontmatter
- Determine path based on scope selection:
- Project:
.claude/agents/[platform-name]-expert.md - Global:
~/.claude/agents/[platform-name]-expert.md(or Windows equivalent)
- Project:
- Use Write tool with appropriate path
- Verify file was created successfully
- Agent is immediately available for use
Examples
Example 1: Single Agent
User: /spawn
Agent: [Shows multi-tab AskUserQuestion with 5 tabs]
Tab 1 (Mode): Single Agent / Batch Generation / Architecture Analysis
Tab 2 (Scope): Project Agent / Global Agent
Tab 3 (Output): Create File / Show in Chat / Both
Tab 4 (Platform): Custom Platform / [or popular options]
Tab 5 (Focus): [Multi-select] General Coverage / Caching Patterns / Pub/Sub / etc.
User: [Selects all answers and submits once]
Mode: Single Agent
Scope: Global Agent
Output: Both
Platform: Redis (via Other field)
Focus: General Coverage, Caching Patterns, Pub/Sub
Agent: [Generates Redis expert prompt and saves to ~/.claude/agents/redis-expert.md]
Example 2: Batch Generation
User: /spawn
Agent: [Shows multi-tab AskUserQuestion with 3 tabs]
Tab 1 (Mode): Single Agent / Batch Generation / Architecture Analysis
Tab 2 (Scope): Project Agent / Global Agent
Tab 3 (Output): Create Files / Show in Chat / Both
User: [Submits]
Mode: Batch Generation
Scope: Project Agent
Output: Create Files
Agent: Please provide platforms (one per line):
User: PostgreSQL
Redis
RabbitMQ
Agent: [Creates 3 .md files in .claude/agents/ (project directory)]
Example 3: Architecture Analysis
User: /spawn
Agent: [Shows multi-tab AskUserQuestion with 3 tabs]
Tab 1 (Mode): Single Agent / Batch Generation / Architecture Analysis
Tab 2 (Scope): Project Agent / Global Agent
Tab 3 (Output): Create Files / Show in Chat / Both
User: [Submits]
Mode: Architecture Analysis
Scope: Global Agent
Output: Both
Agent: Describe your architecture or provide file path:
User: E-commerce platform: Next.js frontend, Node.js API, PostgreSQL, Redis cache, Stripe payments, AWS S3 storage, SendGrid emails
Agent: Found platforms: Next.js, Node.js, PostgreSQL, Redis, Stripe, AWS S3, SendGrid
[Shows multi-select AskUserQuestion]
User: [Selects: nextjs-expert, redis-expert, stripe-expert, sendgrid-expert]
Agent: [Generates 4 selected agents in ~/.claude/agents/]
Implementation Steps
-
Ask All Questions at Once using a single multi-question AskUserQuestion call:
- Question 1 (header: "Mode"): Single Agent / Batch Generation / Architecture Analysis
- Question 2 (header: "Scope"): Project Agent (this project only) / Global Agent (all projects)
- Question 3 (header: "Output"): Create File / Show in Chat / Both
For Single Mode, also ask in the same call:
- Question 4 (header: "Platform"): Offer "Custom Platform" option (user types in Other field)
- Question 5 (header: "Focus", multiSelect: true): General Coverage / [2-3 common focus areas for that tech]
-
For Single Mode:
- If user selected "Custom Platform", prompt for the platform name in chat
- Generate comprehensive prompt based on answers
- Create file and/or display based on output preference
-
For Batch Mode:
- Ask user to provide multi-line platform list in chat
- For each platform:
- Generate expert prompt
- Save to
.claude/agents/[platform]-expert.md
- Report completion with file paths
-
For Architecture Analysis:
- Ask user for architecture description in chat
- Parse and identify technologies
- Present checkbox selector using AskUserQuestion (multiSelect: true)
- Generate selected agents
- Save to files based on output preference
-
Generate Each Agent Prompt:
- Research official docs (WebSearch or WebFetch)
- Find 10+ authoritative URLs
- Structure according to template above
- Focus on patterns and best practices
- Target 500-1000 lines with comprehensive patterns
- Markdown formatted
-
Output:
- Determine file path based on Scope selection:
- Project Agent:
.claude/agents/[platform]-expert.md - Global Agent:
~/.claude/agents/[platform]-expert.md(Unix/Mac) orC:\Users\[username]\.claude\agents\[platform]-expert.md(Windows)
- Project Agent:
- If "Create File" or "Both": Use Write tool with appropriate path and complete YAML frontmatter + system prompt
- If "Show in Chat" or "Both": Display complete markdown (including frontmatter) in code block
- Confirm creation with full file path
- Remind user the agent is available via the Agent tool within seconds (restart first if
this created the
agents/directory)
- Determine file path based on Scope selection:
Important: Always use a single AskUserQuestion call with multiple questions (2-4) to create the multi-tab interface. Never ask questions sequentially one at a time.
Quality Checklist
Before outputting each agent prompt, verify:
- YAML frontmatter present with required fields (name, description)
- Name uses lowercase-with-hyphens format
- Description is clear and specific (length is flexible)
- Tools field specified if restricting access (best practice: limit to necessary tools)
- 10+ authoritative URLs included in system prompt
- 10+ production-ready code examples included
- Complete dev and prod configuration files
- Testing patterns with actual test code
- Error handling patterns and exception hierarchy
- 5+ anti-patterns with bad/good code comparison
- Concise and scannable system prompt
- Clear use cases defined
- Integration points identified
- Common patterns referenced
- Anti-patterns listed
- Proper markdown formatting throughout
- Filename matches name field:
[name].md - Follows Claude Code subagent best practices (see documentation links above)
Post-Generation
After creating agents, remind user:
- Review generated prompts
- Test agent with sample questions
- Refine based on actual usage
- Add to version control if satisfied
- Consult Claude Code documentation links above for advanced features and best practices
Additional Resources:
- Use
/agentscommand to view and manage all available agents - Refer to https://docs.claude.com/en/docs/claude-code/sub-agents for detailed subagent documentation
- Check https://docs.claude.com/en/docs/agents-and-tools/agent-skills/best-practices for authoring guidelines
Files in this skill
4spawn skill questions
How do I install the spawn skill in Claude Code?
Run npx degit 0xDarkMatter/claude-mods/skills/spawn ~/.claude/skills/spawn. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the spawn skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
Can I use this tool to run parallel workers?
No, this tool is for authoring agent prompts, not for runtime execution. For spawning parallel runtime workers, you should use fleet-worker/fleetflow via parallel-ops.
What information is included in a generated agent file?
Each agent follows a 10-part structure including core concepts, essential patterns, advanced techniques, configuration, integration patterns, testing strategies, error handling, performance optimization, security considerations, and a quick reference.