Create new Claude Code skills with best practices and proper directory structure
From lpclaude-confignpx claudepluginhub lpasqualis/lpclaude --plugin lpclaude-config[description of what the skill should do] (skill name optional - can be embedded in description or will be generated)skills//createCreates a new beads issue interactively or via title, type (bug/feature/task/epic/chore/decision), and priority args. Uses beads MCP create tool, shows ID/details, offers linking.
/createLaunches Socratic subagent to create orchestration workflows interactively from natural language descriptions. Accepts optional initial description. Deprecated.
/createCreates a new scaffold template in .scaffold/<name> with scaffold.yaml config, Go template files for project or template scaffolds, and validates via lint and dry-run generation.
/createCreates a workspace directory with git worktrees for multi-repository development. Parses description for GitHub PRs, JIRA keys, and repos; sets up feature branches or PR checkouts.
/createAnalyzes project state (git, Node.js, Python, Rust, Go) and creates 9 baseline Markdown context files in .claude/context/ for structure, tech, progress, vision, and more.
/createCreates a new NotebookLM notebook via CLI with given title and optional sources (URLs, files, YouTube, PDFs, etc.). Reports notebook ID and added sources.
Parse the user's input to extract:
.claude/skills/) unless "global", "personal", or "all projects" mentionedFrom the description, determine:
allowed-tools)reference.mdexamples.mdscripts/ directory with placeholdertemplates/ directory with placeholderSkills are directories containing a SKILL.md file plus optional supporting resources:
skill-name/
|-- SKILL.md (required - main instructions)
|-- reference.md (optional - detailed documentation)
|-- examples.md (optional - usage examples)
|-- scripts/ (optional - utility scripts)
| |-- README.md (placeholder explaining purpose)
|-- templates/ (optional - reusable templates)
|-- README.md (placeholder explaining purpose)
---
name: skill-name
description: What it does AND when Claude should use it (critical for discovery)
allowed-tools: Tool1, Tool2 # Optional - only include if restrictions needed
---
# Skill Name
## Overview
Brief explanation of the skill's purpose and value.
## Instructions
Step-by-step guidance for Claude when this skill is active.
## When to Use
Specific triggers and contexts where this skill applies.
## References
Links to supporting files if they exist.
The description field is critical for Claude's automatic discovery. A good description:
Includes WHAT the skill does:
Includes WHEN to use it:
Bad examples (too vague):
Only add allowed-tools when the skill should be limited:
Read-only skills:
allowed-tools: Read, Grep, Glob
Analysis skills (no file modification):
allowed-tools: Read, Grep, Glob, Bash(git log:*), Bash(git diff:*)
Omit allowed-tools for skills that need full capabilities - Claude will ask for permission as normal.
mkdir -p [scope]/skills/[skill-name]
# [Skill Name] Reference
## Detailed Documentation
[Add comprehensive reference material here]
## API/Tool Reference
[Add relevant API documentation or tool references]
## Best Practices
[Add domain-specific best practices]
# [Skill Name] Examples
## Basic Usage
[Add simple examples]
## Advanced Usage
[Add complex examples with explanations]
## Common Patterns
[Add frequently used patterns]
# Scripts
This directory contains utility scripts for the [skill-name] skill.
## Available Scripts
- Add your scripts here
## Usage
Describe how Claude should use these scripts.
# Templates
This directory contains reusable templates for the [skill-name] skill.
## Available Templates
- Add your templates here
## Usage
Describe how Claude should use these templates.
After creating the skill, remind the user:
$ARGUMENTS