Create new skill scaffold with required structure. Use when starting a new skill from scratch or need proper YAML frontmatter template.
Scanned 6/7/2026
Install via CLI
openskills install melodic-software/claude-code-plugins---
name: create-skill
allowed-tools: Write, Bash(mkdir:*), Skill
argument-hint: [skill-name]
description: Create new skill scaffold with required structure. Use when starting a new skill from scratch or need proper YAML frontmatter template.
---
# Create Skill
Create a new skill scaffold with required structure.
## Skill Name
$ARGUMENTS
## Prerequisites
- Skill name should use kebab-case (e.g., `my-new-skill`)
- Skill names should be noun-phrases describing capability (e.g., `docs-management`, not `manage-docs`)
## Instructions
### Step 1: Validate Input
If `$ARGUMENTS` is empty or invalid:
- Prompt the user for a skill name
- Validate it follows kebab-case convention
### Step 2: Load Skill Development Guidance
Invoke the `claude-ecosystem:skill-development` skill to get:
- Skill naming conventions
- Required YAML frontmatter fields
- Directory structure requirements
- Best practices for skill content
### Step 3: Create Skill Scaffold
Create the directory and SKILL.md:
```bash
mkdir -p .claude/skills/$ARGUMENTS
```
Create `.claude/skills/$ARGUMENTS/SKILL.md` with:
```yaml
---
description: [Brief description of what this skill does]
allowed-tools: [Comma-separated list of tools needed]
---
# [Skill Name]
[Skill content following patterns from skill-development guidance]
```
### Step 4: Follow Established Patterns
Reference existing skills in this repo for:
- Content organization
- Progressive disclosure patterns
- Reference file usage
## Example Usage
```text
/create-skill api-integration
```
Creates:
- `.claude/skills/api-integration/SKILL.md` with proper frontmatter
- Ready for customization with skill-specific content
## Fallback
If `skill-development` skill is unavailable, use these minimum requirements:
**Required frontmatter:**
- `description`: Brief description (required)
- `allowed-tools`: Comma-separated tool list (optional)
**Content structure:**
- H1 title matching skill name
- Overview section
- Instructions or guidance
- Examples where applicable
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.