Attach skills to your inference.sh agents so they can load context on demand.
From the Registry
The fastest way to add a skill:
- Open your agent's settings → Prompt tab
- Scroll to the Skills section
- Click Browse to open the skill browser
- Search and select a skill
The skill's name, description, and URL are filled in automatically.
By URL
Point to any skill hosted anywhere:
- In the skills section, click + URL
- Fill in:
| Field | Value |
|---|---|
| Name | Identifier the agent uses (e.g. api-docs) |
| Description | When to load this skill — the agent sees this |
| URL | Where to fetch the content |
1name: api-docs2description: REST API documentation for the payment service3url: https://api.inference.sh/skills/yourteam/api-docs/contentThe URL can point to:
- A skill on inference.sh (
https://api.inference.sh/skills/{ns}/{name}/content) - A raw file on GitHub (
https://raw.githubusercontent.com/...) - Any HTTPS URL that returns text/markdown
Inline
Write skill content directly in the agent config:
- Click + Text
- Fill in name, description, and the content itself
Good for short, agent-specific instructions that don't need to be shared:
1name: response-style2description: guidelines for tone and formatting3content: |4 Always respond in lowercase.5 Use bullet points for lists.6 Keep responses under 200 words unless asked for detail.How skill_get Works at Runtime
When your agent runs, the skills you've added appear in the skill_get tool:
1skill_get: Retrieves skill content.23Available skills:4- code-review: guidelines for reviewing pull requests5- api-docs: REST API documentation for the payment service67Parameters:8 skill: the name of the skill to retrieve9 path: optional path to a supporting file (e.g. references/api-docs.md)The agent decides when to call skill_get based on the conversation. Typical flow:
- User asks something related to a skill's description
- Agent calls
skill_get(skill="code-review")→ gets the main instructions - If the instructions reference supporting files, agent calls
skill_get(skill="code-review", path="references/checklist.md")→ gets the specific file - Agent uses the loaded context to respond
Content is cached per session — loading the same skill twice doesn't re-fetch.
How Many Skills?
There's no hard limit, but keep descriptions concise. Every skill adds a line to the tool description. 5-15 well-described skills is a good range — enough to cover the domain without overwhelming the agent's context.
If you find yourself adding 20+ skills, consider whether some should be supporting files within a parent skill rather than separate skills.
Next
- Creating skills — build your own skills
- Using with other agents — install skills to Claude Code, Cursor, and more
- Skills overview — how skills work