factory-code

factory-code

Use when users ask about Factory Code features, setup, configuration, troubleshooting, slash commands, MCP servers, Agent Skills, hooks, plugins, CI/CD integration, or enterprise deployment. Activate for questions like 'How do I use Factory Code?', 'What slash commands are available?', 'How to set up MCP?', 'Create a skill', 'Fix Factory Code issues', or 'Deploy Factory Code in enterprise'. | Dùng khi hỏi về Factory Code, lệnh slash, hook, plugin, skill, cấu hình, cài đặt.

2étoiles
0forks
Mis à jour 1/11/2026
SKILL.md
readonlyread-only
name
factory-code
description

Use when users ask about Factory Code features, setup, configuration, troubleshooting, slash commands, MCP servers, Agent Skills, hooks, plugins, CI/CD integration, or enterprise deployment. Activate for questions like 'How do I use Factory Code?', 'What slash commands are available?', 'How to set up MCP?', 'Create a skill', 'Fix Factory Code issues', or 'Deploy Factory Code in enterprise'. | Dùng khi hỏi về Factory Code, lệnh slash, hook, plugin, skill, cấu hình, cài đặt.

Factory Code Expert

Factory Code is Anthropic's agentic coding tool that lives in the terminal and helps turn ideas into code faster. It combines autonomous planning, execution, and validation with extensibility through skills, plugins, MCP servers, and hooks.

When to Use This Skill

Use when users need help with:

  • Understanding Factory Code features and capabilities
  • Installation, setup, and authentication
  • Using slash commands for development workflows
  • Creating or managing Agent Skills
  • Configuring MCP servers for external tool integration
  • Setting up hooks and plugins
  • Troubleshooting Factory Code issues
  • Enterprise deployment (SSO, sandboxing, monitoring)
  • IDE integration (VS Code, JetBrains)
  • CI/CD integration (GitHub Actions, GitLab)
  • Advanced features (extended thinking, caching, checkpointing)
  • Cost tracking and optimization

Activation examples:

  • "How do I use Factory Code?"
  • "What slash commands are available?"
  • "How to set up MCP servers?"
  • "Create a new skill for X"
  • "Fix Factory Code authentication issues"
  • "Deploy Factory Code in enterprise environment"

Core Architecture

Subagents: Specialized AI agents (planner, code-reviewer, tester, debugger, docs-manager, ui-ux-designer, database-admin, etc.)

Agent Skills: Modular capabilities with instructions, metadata, and resources that Factory uses automatically

Slash Commands: User-defined operations in .factory/commands/ that expand to prompts

Hooks: Shell commands executing in response to events (pre/post-tool, user-prompt-submit)

MCP Servers: Model Context Protocol integrations connecting external tools and services

Plugins: Packaged collections of commands, skills, hooks, and MCP servers

Quick Reference

Load these references when needed for detailed guidance:

Getting Started

  • Installation & Setup: references/getting-started.md
    • Prerequisites, installation methods, authentication, first run

Development Workflows

  • Slash Commands: references/slash-commands.md

    • Complete command catalog: /cook, /plan, /debug, /test, /fix:, /docs:, /git:, /design:, /content:*
  • Agent Skills: references/agent-skills.md

    • Creating skills, skill.json format, best practices, API usage

Integration & Extension

  • MCP Integration: references/mcp-integration.md

    • Configuration, common servers, remote servers
  • Hooks & Plugins: references/hooks-and-plugins.md

    • Hook types, configuration, environment variables, plugin structure, installation

Configuration & Settings

  • Configuration: references/configuration.md
    • Settings hierarchy, key settings, model configuration, output styles

Enterprise & Production

  • Enterprise Features: references/enterprise-features.md

    • IAM, SSO, RBAC, sandboxing, audit logging, deployment options, monitoring
  • IDE Integration: references/ide-integration.md

    • VS Code extension, JetBrains plugin setup and features
  • CI/CD Integration: references/cicd-integration.md

    • GitHub Actions, GitLab CI/CD workflow examples

Advanced Usage

  • Advanced Features: references/advanced-features.md

    • Extended thinking, prompt caching, checkpointing, memory management
  • Troubleshooting: references/troubleshooting.md

    • Common issues, authentication failures, MCP problems, performance, debug mode
  • API Reference: references/api-reference.md

    • Admin API, Messages API, Files API, Models API, Skills API
  • Best Practices: references/best-practices.md

    • Project organization, security, performance, team collaboration, cost management

Common Workflows

Feature Implementation

/cook implement user authentication with JWT
# Or plan first
/plan implement payment integration with Stripe

Bug Fixing

/fix:fast the login button is not working
/debug the API returns 500 errors intermittently
/fix:types  # Fix TypeScript errors

Code Review & Testing

Factory "review my latest commit"
/test
/fix:test the user service tests are failing

Documentation

/docs:init      # Create initial documentation
/docs:update    # Update existing docs
/docs:summarize # Summarize changes

Git Operations

/git:cm                    # Stage and commit
/git:cp                    # Stage, commit, and push
/git:pr feature-branch main  # Create pull request

Design & Content

/design:fast create landing page for SaaS product
/content:good write product description for new feature

Instructions for Factory

When responding to Factory Code questions:

  1. Identify the topic from the user's question
  2. Load relevant references from the Quick Reference section above
  3. Provide specific guidance using information from loaded references
  4. Include examples when helpful

Loading references:

  • Read reference files only when needed for the specific question
  • Multiple references can be loaded for complex queries
  • Use grep patterns if searching within references

For setup/installation questions: Load references/getting-started.md

For slash command questions: Load references/slash-commands.md

For skill creation: Load references/agent-skills.md

For MCP questions: Load references/mcp-integration.md

For hooks/plugins: Load references/hooks-and-plugins.md

For configuration: Load references/configuration.md

For enterprise deployment: Load references/enterprise-features.md

For IDE integration: Load references/ide-integration.md

For CI/CD: Load references/cicd-integration.md

For advanced features: Load references/advanced-features.md

For troubleshooting: Load references/troubleshooting.md

For API usage: Load references/api-reference.md

For best practices: Load references/best-practices.md

Documentation links:

Provide accurate, actionable guidance based on the loaded references and official documentation.

You Might Also Like

Related Skills

mcporter

mcporter

179Kdev-mcp

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

openclaw avataropenclaw
Obtenir
model-usage

model-usage

88Kdev-mcp

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

moltbot avatarmoltbot
Obtenir

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

affaan-m avataraffaan-m
Obtenir

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

davila7 avatardavila7
Obtenir

Claude Code 高级开发指南 - 全面的中文教程,涵盖工具使用、REPL 环境、开发工作流、MCP 集成、高级模式和最佳实践。适合学习 Claude Code 的高级功能和开发技巧。

2025Emma avatar2025Emma
Obtenir

This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.

muratcankoylan avatarmuratcankoylan
Obtenir