AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MPL-2.0 Self-run

Skill Development

skill-rooftop-owl-skill-factory-skill-development · by rooftop-Owl

Use when creating new agent skills, improving skill descriptions, structuring skill directories, or authoring SKILL.md files. Covers the agentskills.io specification, frontmatter format, trigger phrase design, and publishing workflow.

— No reviews yet
0 installs
33 views
0.0% view→install

Install

$ agentstack add skill-rooftop-owl-skill-factory-skill-development

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-rooftop-owl-skill-factory-skill-development)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Skill Development? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Skill Development

Guide for authoring high-quality, cross-platform agent skills.

SKILL.md Format

Every skill is a markdown file with YAML frontmatter:

---
name: my-skill-name
description: Use when the user asks to "do X", "perform Y", or needs help with Z. Provides step-by-step procedures for accomplishing the task.
---

# My Skill Name

## Purpose
What this skill enables the agent to do.

## Procedures
Step-by-step instructions the agent follows.

## When to Load
- Load when: [trigger conditions]
- Not needed when: [exclusion conditions]

Frontmatter Spec (agentskills.io)

Required Fields

| Field | Rules | Example | |-------|-------|---------| | name | ^[a-z0-9]+(-[a-z0-9]+)*$, max 64 chars | react-best-practices | | description | Max 1024 chars, should start with "Use when..." | Use when building React components... |

Optional Fields

| Field | Purpose | Example | |-------|---------|---------| | license | SPDX identifier | MPL-2.0 | | metadata.triggers | Pipe-delimited trigger phrases | "react hooks \| useState \| components" | | metadata.domains | Pipe-delimited domain tags | "frontend \| react" | | metadata.version | Semver string | "1.0.0" |

Name Rules

  • Lowercase letters, digits, hyphens only
  • Cannot start or end with a hyphen
  • Max 64 characters
  • Must match the parent directory name exactly

Directory Structure

skill-name/
├── SKILL.md              # Required: main skill file
├── references/           # Optional: supporting documents
│   ├── api-patterns.md
│   └── common-errors.md
└── examples/             # Optional: usage examples
    └── basic-setup.md

Reference files enable progressive disclosure — the main SKILL.md stays concise while references/ holds deep-dive content the agent loads on demand.

See handbook/agentskills-io-spec.md for the full specification reference.

Description Best Practices

The description field is the primary trigger mechanism. Agents load skills based on keyword matching against descriptions.

DO

  • Start with "Use when..." or "This skill should be used when..."
  • Include quoted trigger phrases: "deploy to production", "fix auth bug"
  • List concrete user prompts that should activate it
  • Include negative triggers: "Not needed when..."

DON'T

  • Write vague descriptions: "Helps with development"
  • Omit trigger phrases — the skill won't be discoverable
  • Make descriptions longer than 1024 characters
  • Duplicate another skill's trigger phrases

Example (good)

description: Use when the user asks to "set up authentication", "add login", "implement JWT", "secure API endpoints", or needs guidance on session management, OAuth flows, or password hashing. Not needed for basic CRUD operations or frontend styling.

Example (bad)

description: Authentication skill for web applications.

Testing a Skill Locally

Before publishing, verify your skill works:

  1. Place it: Copy skill-name/SKILL.md to .claude/skills/skill-name/SKILL.md
  2. Validate frontmatter:

``bash python3 -c " import yaml content = open('.claude/skills/skill-name/SKILL.md').read() fm = yaml.safe_load(content.split('---', 2)[1]) assert fm.get('name') == 'skill-name', 'Name mismatch' assert fm.get('description'), 'Missing description' print('PASS') " ``

  1. Test trigger: Start a new session and type a prompt that should activate the skill
  2. Verify loading: The agent should load and follow the skill's procedures

Publishing

See handbook/publishing-skills.md for the full publishing guide. Quick version:

  1. Create a public GitHub repo
  2. Place skills in skills//SKILL.md
  3. Push — skills.sh auto-indexes it
  4. Verify: npx skills find

When to Load This Skill

Load skill-development when:

  • Creating a new skill from scratch
  • Improving a skill's description or trigger phrases
  • Structuring a skill directory with references and examples
  • Validating frontmatter format
  • Preparing a skill for publishing

Not needed when:

  • Installing existing skills (use skill-management)
  • Searching for skills (use /skills-search)
  • Removing skills (use skill-management)

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.