# skills.sh Publishing Checklist

Use this checklist for every first-batch skill before publishing the next one.

## Pre-Publish

- Run static validation:

```bash
node scripts/validate-skills.mjs
```

- Run local skills CLI smoke install:

```bash
node scripts/smoke-install-skills.mjs
```

- Directory slug matches `SKILL.md` frontmatter `name`.
- Skill slug uses demand or scene wording, not model-only wording.
- `displayName` names the execution model: Seedance 2, GPT Image 2, or both.
- Description includes user intent words and execution model names.
- Install command uses `Evolink-AI/evolink-agent-skills` and the exact skill slug.
- All EvoLink links use `utm_source=skillssh&utm_medium=skill&utm_campaign=<skill-name>`.
- The skill includes a route table with GPT Image 2 and/or Seedance 2 model paths.
- Image skills include a video handoff.
- Video skills include variant or iteration suggestions.

## Publish Order

1. `image-edit`
2. `product-image-generation`
3. `image-to-video`
4. `product-to-ad`
5. `ad-video-generation`
6. `product-demo-video`
7. `ad-creative-images`
8. `ugc-video-ads`

## Post-Publish

- Run the install command from a clean machine or container.
- Confirm the skill appears on skills.sh with the correct title and description.
- Confirm `skills.sh.json` grouping renders after cache refresh.
- Click each EvoLink link and verify analytics campaign attribution.
- Run one real EvoLink generation through the documented path.
- Confirm backend analytics can connect campaign, first generation, and token consumption.
- Record the install count baseline before publishing the next skill.