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

Skill Creator

skill-shaunandrews-agent-skills-skill-creator · by shaunandrews

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

No reviews yet
0 installs
9 views
0.0% view→install

Install

$ agentstack add skill-shaunandrews-agent-skills-skill-creator

✓ 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-shaunandrews-agent-skills-skill-creator)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5mo 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 Creator? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Skill Creator Skill

Use this skill when creating a new agent skill. Skills provide specialized instructions for specific tasks.

When to Use

  • Creating a new skill for the agent-skills repo
  • User asks to "create a skill" or "add a new skill"
  • Documenting a repeatable workflow as a skill

Skill Location

All skills live in: ~/Developer/Projects/agent-skills/skills/{skill-name}/

Use kebab-case for skill names (e.g., wordpress-mockups, project-setup).

Skill Structure

Minimal skill:

{skill-name}/
└── SKILL.md              # Required: main skill file

Complex skill with assets:

{skill-name}/
├── SKILL.md              # Required: main skill file
├── docs/                 # Optional: detailed documentation
│   └── {topic}.md
├── templates/            # Optional: file templates
│   └── {template-file}
├── examples/             # Optional: example files
│   └── {example-file}
└── assets/               # Optional: images, icons, etc.
    └── {asset-file}

SKILL.md Template

# {Skill Name} Skill

{One-line description of what this skill does}

## When to Use

- {Trigger condition 1}
- {Trigger condition 2}
- {Trigger condition 3}

## Prerequisites

{Tools, CLIs, access, or setup required — or "None" if self-contained}

## Workflow

### Step 1: {First Step}

{Instructions}

### Step 2: {Second Step}

{Instructions}

{Continue with more steps as needed}

## Commands Reference

{If the skill involves CLI tools, list key commands}

```bash
# Example command
command --flag value

Templates

{If the skill includes templates, document them here}

Examples

{Show example usage or link to examples/ folder}

Troubleshooting

{Common issues and solutions}

Related Skills

  • {Link to related skills if applicable}

## Writing Good Skills

### Be Specific
- Describe exact conditions when to use the skill
- Include concrete examples, not abstract principles

### Be Procedural
- Break down workflows into clear steps
- Use numbered lists for sequences
- Use code blocks for commands and file contents

### Be Complete
- Include all necessary context
- Don't assume the agent remembers prior conversations
- Reference file paths explicitly

### Be Practical
- Focus on what the agent needs to DO, not background theory
- Include templates and examples
- Anticipate common variations

## Creation Procedure

1. **Identify the skill need**
   - What task keeps coming up?
   - What workflow should be standardized?

2. **Create skill directory**
   ```bash
   mkdir -p ~/Developer/Projects/agent-skills/skills/{skill-name}
   ```

3. **Write SKILL.md**
   - Use template above
   - Be thorough — this is the agent's only reference

4. **Add supporting files** (if needed)
   - Templates in `templates/`
   - Examples in `examples/`
   - Documentation in `docs/`

5. **Test the skill**
   - Symlink to workspace: 
     ```bash
     ln -s ~/Developer/Projects/agent-skills/skills/{skill-name} ~/.openclaw/workspace/skills/{skill-name}
     ```
   - Try using it in a conversation
   - Refine based on results

6. **Commit to agent-skills repo**
   ```bash
   cd ~/Developer/Projects/agent-skills
   git add skills/{skill-name}
   git commit -m "Add {skill-name} skill"
   git push
   ```

## Symlinking Skills

To make a skill available to the agent:

```bash
# Create symlink
ln -s ~/Developer/Projects/agent-skills/skills/{skill-name} ~/.openclaw/workspace/skills/{skill-name}

# Verify
ls -la ~/.openclaw/workspace/skills/{skill-name}

To remove a skill:

rm ~/.openclaw/workspace/skills/{skill-name}  # Removes symlink only, not source

Skill Naming Conventions

| Pattern | Use For | Examples | |---------|---------|----------| | {tool}-{action} | Tool-specific skills | gh-issues, wp-deploy | | {domain}-{topic} | Domain skills | wordpress-blocks, design-mockups | | {verb}-{noun} | Action skills | project-setup, skill-creator |

Quality Checklist

Before committing a new skill:

  • [ ] SKILL.md has clear "When to Use" section
  • [ ] All file paths are explicit (no assumptions)
  • [ ] Commands include expected output or success criteria
  • [ ] Templates are complete and copy-pasteable
  • [ ] Tested with actual usage
  • [ ] Committed to agent-skills repo

Existing Skills Reference

Check existing skills for patterns:

ls ~/.openclaw/workspace/skills/

Read a skill to understand structure:

cat ~/.openclaw/workspace/skills/{skill-name}/SKILL.md

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.