manuelmauro/arkouda/use-skilo
Claude Code and agent skill by manuelmauro/arkouda
- community
Checking that the SKILL.md file is still in the repository.
Creates, installs, validates, and formats Agent Skills. Use when developing skills from templates, installing skills from git repositories, linting against the specification, or managing skills across AI coding agents.
Install
npx vskill@latest install manuelmauro/arkouda/use-skiloSKILL.md
Use Skilo
Skilo is a CLI tool for developing Agent Skills.
Installation
Quick Start
Run skilo -h for all commands and options.
ALWAYS Validate Skills
Run `skilo lint` and `skilo fmt` before committing any skill changes. These commands enforce the Agent Skills Specification and catch common issues.
Skill Structure
Frontmatter Requirements
Required Fields
`name` (1-64 characters)
- Lowercase alphanumeric and hyphens only (
a-z,0-9,-) - Must NOT start/end with
-or contain-- - Must match parent directory name
`description` (1-1024 characters)
- Describe WHAT the skill does AND WHEN to use it
- Include keywords that help agents match user requests
Optional Fields
- `license` - Keep short, reference LICENSE file for details
- `compatibility` (max 500 chars) - Environment requirements (e.g.,
Requires git, docker) - `metadata` - Key-value pairs for custom properties
- `allowed-tools` - Space-delimited list of pre-approved tools (experimental)
Best Practices
Write Effective Descriptions
The description is how agents decide when to activate your skill. Be specific.
Keep Body Content Concise
The entire SKILL.md body loads when the skill activates. Keep it under 500 lines.
- Include step-by-step instructions
- Add examples of inputs and outputs
- Cover common edge cases
- Move detailed material to
references/
Use Progressive Disclosure
Structure skills to minimize context usage:
- Metadata (~100 tokens) -
name+descriptionloaded at startup for all skills - Instructions (<5000 tokens) - Full body loaded when skill activates
- Resources (on-demand) -
scripts/,references/,assets/loaded only when needed
Write Self-Contained Scripts
Scripts in scripts/ should:
- Be self-contained or clearly document dependencies
- Include helpful error messages
- Handle edge cases gracefully
Organize References Effectively
Files in references/ are loaded on-demand:
- Keep files focused (one file = one concept)
- Use relative paths from skill root
- Avoid deeply nested reference chains
Lint Rules
Skilo enforces these rules (configure in .skilorc.toml):
| Code | Rule | Default | |
|---|---|---|---|
| E001 | name_format | enabled | |
| E002 | name_length | 64 chars | |
| E003 | name_directory | enabled | |
| E004 | description_required | enabled | |
| E005 | description_length | 1024 chars | |
| E006 | compatibility_length | 500 chars | |
| E009 | references_exist | enabled | |
| W001 | body_length | 500 lines | |
| W002 | script_executable | enabled | |
| W003 | script_shebang | enabled |
CI Integration
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/use-skilo/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/manuelmauro/arkouda/use-skilo)