Claude Code Extensions
Skill authoring skill, available on Zeplik
Claude Code Extensions is a ready-to-run skill authoring skill on Zeplik. Authoring Claude Code extensions — subagents, hooks, slash commands, MCP server config, output styles, status lines, and skill authoring. Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
The Claude Code Extensions skill loads automatically when your request matches it, or you can invoke it directly by typing /claude-code-extensions in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.
What the Claude Code Extensions skill can do
- Identify which Claude Code extension type a request needs
- Generate subagent, hook, and slash command configs with correct file placement
- Scaffold MCP server configs, output styles, and status lines
- Author and refactor skills, plugins, and agent instruction files
Try these prompts on Zeplik
Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.
How the Claude Code Extensions skill works
/claude-code-extensions
Umbrella for building Claude Code extensions. The user wants to customize Claude Code; identify the extension type (subagent, hook, slash command, MCP server, output style, status line, skill) and deliver the config or code plus where it lives. For questions about using Claude Code itself, answer directly from the claude-code guide.
Dispatch table
Pick the reference file(s) that match the request, read them, then answer. Read at most 2-3 files per turn.
| Topic | Read |
|---|---|
| This skill should be used when the user asks to "create an agent", "add an agent", "wri… | references/agent-development.md |
| Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow pro… | references/agent-md-refactor.md |
| Development skill from everything-claude-code | references/cc-skill-continuous-learning.md |
| Project Guidelines Skill (Example) | references/cc-skill-project-guidelines-example.md |
| Development skill from everything-claude-code | references/cc-skill-strategic-compact.md |
| This skill should be used when the user asks to "create a slash command", "add a comman… | references/command-development.md |
| This skill should be used when creating a Claude Code slash command. | references/command-creator.md |
| This skill should be used when the user asks to "create a hook", "add a PreToolUse/Post… | references/hook-development.md |
| This skill should be used when the user asks about "plugin settings", "store plugin con… | references/plugin-settings.md |
| This skill should be used when the user asks to "create a plugin", "scaffold a plugin",… | references/plugin-structure.md |
| Create and manage Claude Code plugins with proper structure, manifests, and marketplace… | references/plugin-forge.md |
| Guide for creating effective skills. | references/skill-creation-guide.md |
| Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. | references/skill-installer.md |
| Use when starting any conversation - establishes how to find and use skills, requiring… | references/using-superpowers.md |
How to work
- Identify which leaf topic the request maps to from the dispatch table above; establish the concrete inputs (language, dataset, framework, file format) and the goal. Ask for a missing detail rather than guessing.
- Read the matching reference file(s) before answering. Read at most 2-3 per turn.
- Deliver runnable artifacts — code, configs, specs — with a short rationale, matching the user's existing conventions when they paste code.
- Confirm any decision the source flags (versions, thresholds, tradeoffs) with the user instead of guessing.
Usage
/claude-code-extensions $ARGUMENTS
How to use the Claude Code Extensions skill
Sign in to Zeplik
Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Claude Code Extensions skill right away.
Describe your skill authoring task
Ask in plain language, or type /claude-code-extensions to invoke the skill directly. Zeplik recognizes the Claude Code Extensions skill and applies its method.
Review and refine the result
Zeplik returns a clear, structured answer. Ask follow-ups in the same chat to refine it or take the next step.
Source and credit
- Author
- davila7 (D7 umbrella-consolidation)
- License
- MIT
Adapted from the open-source davila7/claude-code-templates project and tuned to run natively on Zeplik. View source on GitHub.
Frequently asked questions
- What is the Claude Code Extensions skill?
- Claude Code Extensions is a ready-to-run skill authoring skill on Zeplik. Authoring Claude Code extensions — subagents, hooks, slash commands, MCP server config, output styles, status lines, and skill authoring. Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
- How do I use Claude Code Extensions on Zeplik?
- Sign in to Zeplik and ask in plain language, or type /claude-code-extensions in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
- Which AI model does the Claude Code Extensions skill use?
- Any model you choose. Zeplik works across every model in one chat, so the Claude Code Extensions skill runs on your preferred model for the task.
- Where does the Claude Code Extensions skill come from?
- The Claude Code Extensions skill is adapted from the open-source davila7/claude-code-templates project (MIT) and tuned to run natively on Zeplik. The original source is linked on this page.
- How much does the Claude Code Extensions skill cost?
- Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.
Related skill authoring skills
- Evaluation MethodologyUse when designing eval suites for agent skills or plugins -- fixtures, graders, pass bars, dimensions. Not for judging one skill draft (use skill-judge) or LLM app evals (use llm-evaluation).
- Skill CreatorGuide the user through creating a personal skill: interview briefly, draft the name, description, and body, get approval, then persist it with the skill_manage tool. Use when the user wants to create, design, or improve a custom skill, or says things like "make me a skill for X" or "turn this into a skill". Not for merely using an existing skill.
- Skill JudgeUse when evaluating a pasted skill definition against a quality rubric -- knowledge delta, triggers, anti-patterns -- with scores and top fixes. Not for authoring new skills (use skill-creator).
- Skill Self-ImprovementCapture a hard-won, reusable procedure from the current conversation as a personal skill via skill_manage, so the next occurrence is solved in one step. Use after a non-obvious multi-step problem is solved through iteration and is likely to recur, or when the user says "save this as a skill" or "remember how we did this". Not for one-off facts or things plain documentation already covers.
- Skill Writing GuideUse when writing or editing the content of a skill file so it actually triggers and works: "improve this skill description", "why doesn't my skill fire", testing skills with subagents, skill structure, naming, and token efficiency. Not for scaffolding a brand-new skill file (use skill-creator).
More on Zeplik
Try Claude Code Extensions on Zeplik
Every model, one chat. Bring the Claude Code Extensions skill into your next conversation and let the assistant do the work.