Menu
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Scaffold new JS/TS projects from curated starter templates pre-configured with Biome, TypeScript strict mode, GitHub Actions CI, VS Code settings, and AI agent skills. Use when user wants to create a new project, scaffold an app from a template, or mentions "create-xtarter-app", "npx create-xtarter-app", "scaffold", "starter template", or a template name like "next-tailwind", "vite-chakra", "vite-tailwind", "vite-hero", or "next-chakra".
Apply production-grade conformance configurations (linting, type checking, CI, editor settings, AI skills, release tooling) to JS/TS projects. Scans package.json and config files to auto-detect framework, bundler, and styling, then resolves applicable tasks. Use when user mentions "xtarterize", "conformance", "setup linting", "add CI", "configure project", "init xtarterize", or any task name like "lint/biome", "ts/strict", or "ci/workflow".
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for", "read the source of", "how does X work internally", "get the implementation of", "opensrc path", or any task requiring access to dependency source code beyond types and docs.
Compact the current conversation into a handoff document for another agent to pick up.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
| name | write-a-skill |
| description | Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill. |
| metadata | {"internal":true} |
Gather requirements - ask user about:
Draft the skill - create:
Review with user - present draft and ask:
skill-name/
├── SKILL.md # Main instructions (required)
├── REFERENCE.md # Detailed docs (if needed)
├── EXAMPLES.md # Usage examples (if needed)
└── scripts/ # Utility scripts (if needed)
└── helper.js
---
name: skill-name
description: Brief description of capability. Use when [specific triggers].
---
# Skill Name
## Quick start
[Minimal working example]
## Workflows
[Step-by-step processes with checklists for complex tasks]
## Advanced features
[Link to separate files: See [REFERENCE.md](REFERENCE.md)]
The description is the only thing your agent sees when deciding which skill to load. It's surfaced in the system prompt alongside all other installed skills. Your agent reads these descriptions and picks the relevant skill based on the user's request.
Goal: Give your agent just enough info to know:
Format:
Good example:
Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction.
Bad example:
Helps with documents.
The bad example gives your agent no way to distinguish this from other document skills.
Add utility scripts when:
Scripts save tokens and improve reliability vs generated code.
Split into separate files when:
After drafting, verify: