Learn how to create a compliant skill package
Scanned 9/1/2026
Install to Claude Code
npx -y skills add iflytek/skillhub --skill publishing --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Publishing?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/iflytek-publishing-skillhub)More formats (shields.io, HTML) on the badges page.
---
title: Create Skill Package
sidebar_position: 1
description: Learn how to create a compliant skill package
---
# Create Skill Package
## Skill Package Structure
A standard SkillHub skill package structure looks like this:
```
my-skill/
├── SKILL.md # Main entry file (required)
├── references/ # References (optional)
├── scripts/ # Scripts (optional)
└── assets/ # Static assets (optional)
```
## SKILL.md Format
SKILL.md is the main entry file of a skill package, using YAML frontmatter + Markdown body format:
```markdown
---
name: my-skill
description: One sentence describing what this skill is for
x-astron-category: code-review
---
# Skill Description
Detailed skill description goes here...
```
### Frontmatter Fields
| Field | Required | Description |
|-------|----------|-------------|
| `name` | Yes | Skill identifier, kebab-case format |
| `description` | Yes | Brief skill description |
| `x-astron-category` | No | Category tag |
| `x-astron-runtime` | No | Runtime requirement |
| `x-astron-min-version` | No | Minimum version requirement |
## File Limits
- Single file size: Max 1MB
- Total package size: Max 10MB
- File count: Max 100
- Allowed file types: `.md`, `.txt`, `.json`, `.yaml`, `.yml`, `.js`, `.ts`, `.py`, `.sh`, `.png`, `.jpg`, `.svg`
## Next Steps
- [Publish Workflow](./publish) - Publish skill package
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
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.