Claude Code Skills & Agents Factory
A set of skills, slash commands and agents for Claude Code that helps you build your own skills, agents, hooks, slash commands and prompts
- 899 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Generates and installs skills, hooks and slash commands that later run in the agent
- Copies files into configuration directories and runs generator scripts
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/claude-code-skills-agents-factoryDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Generates and installs skills, hooks and slash commands that later run in the agent
- Copies files into configuration directories and runs generator scripts
This is third-party code. Review the repository files before installing.
What it does
The set turns Claude Code into a workshop for building your own agent tooling. The factory-guide agent asks questions to understand the task and delegates to specialist guides, while slash commands like /build skill, /build agent and /build hook drive a step-by-step build. It ships ready-made skills: a prompt generator with 69 presets across domains, factories for hooks, agents and slash commands, and a bridge between Claude Code and Codex CLI. Output can be checked with /validate-output, packaged into a ZIP and installed via /install-skill or by copying folders into the skills directory.
Who it is for. For developers and tool authors who extend Claude Code with their own skills, agents and commands.
Good fit when
- You need to quickly build a new skill, agent or hook via guided questions
- You need a ready prompt generator with presets for different roles
- You need to validate, package and install your skill into Claude Code
Not a fit when
- You need a finished domain skill rather than a tool to create them
- You do not work in Claude Code: the slash commands and guide agents target it
Example request
Build a skill that checks my commits against our internal guideLimitations
The build commands and guide agents target Claude Code, and some generators produce Python files. Generated artifacts still need review before install. There is no plugin manifest in the repository; installation is by copying folders. The default branch is dev.
How to disable. Remove the copied skill folders from ~/.claude/skills/, and the .claude/commands and .claude/agents folders if you copied them into your project or home directory.
FAQ
Do I have to install the whole set?
No. You can copy only the folders you need, for example the ready prompt generator, and add the factories later.
What can be used outside Claude Code?
The slash commands and guide agents target Claude Code, while the skills they produce are plain SKILL.md skills that carry over to other runtimes.
Discussion
No questions or reviews yet.
Related
SkillsSkills, mods, subagents and hooks for Claude Code: the agent inspects your setup and installs what fits after your approval.
A Claude Code reference plus a collection of over 70 skills for development, security, data and docs, with agent configs
A learning kit for Claude Code: feature walkthroughs plus copy-paste templates for commands, skills, memory, hooks and subagents
A large kit for Claude Code: subagents, skills, commands, hooks, rules, templates and MCP configs in one plugin marketplace
A working folder for Claude Code where the agent asks questions and writes a new skill by Anthropic's guidance, not from memory.
A Claude Code plugin marketplace with ready sets of agents, slash commands, hooks and skills, plus a search site
README in short
The README describes the set as a workshop for building skills, agents, prompts, hooks and slash commands in Claude Code. It offers three quick paths: the interactive factory-guide agent, the /build family of slash commands and ready-made skills such as the prompt generator. It lists ten slash commands and five guide agents, plus factories for skills, agents, prompts, hooks and slash commands and a bridge to Codex CLI. Installation is by copying folders into the skills directory and via the /install-skill command, with output validation and ZIP packaging. MIT licensed.
README badge
Original SKILL.md
--- name: prompt-factory description: World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory, specialized-technical, research, creative-media), multiple output formats (XML/Claude/ChatGPT/Gemini), quality validation gates, and contextual best practices from OpenAI/Anthropic/Google. Supports both core and advanced modes with testing scenarios and prompt variations. --- # Prompt Factory A comprehensive system for generating production-ready prompts in one shot, reducing the need for iteration. ## Critical constraints This skill generates prompts only. It does not implement the work described in the prompt. What this skill does: - Generate a comprehensive prompt in the chosen format - Ask 5 to 7 questions to understand requirements - Validate prompt quality before delivery - Output a single prompt document with a token count What this skill does not do: - Implement the actual work (no code files, diagrams or APIs) - Create multiple files or deliverables - Execute the prompt after generating it