Skills

A skill is instructions for one kind of task, loaded only when the agent needs it. It keeps the system prompt short and the cache warm.

Skills in the bootstrap

"skills": [
  { "name": "writing", "description": "How to word a message to the person.", "content": "Short sentences. Lead with the answer." }
]

newt adds an index of names and descriptions to the system prompt:

<skills>
Load a skill with load_skill before doing what it covers.
- writing: How to word a message to the person.
</skills>

and gives the agent a built-in load_skill tool. The index changes only with the bootstrap version, so it stays in the cached prefix. A loaded skill’s text stays in that turn’s scratch and never enters history.

Make a tool wait for a skill

Every tool call carries newt/skills_loaded, the skills the agent loaded this turn. A handler can refuse an action until the right skill was read, for example a refund tool that needs the refunds skill first.

Skills served over MCP

Experimental

This follows SEP-2640, a draft MCP extension.

An MCP server that declares io.modelcontextprotocol/skills can serve skills in the Agent Skills format instead of the bootstrap.

• newt lists them on connect and offers each as {server}/{skill path}: skill://acme/billing/refunds/SKILL.md on server app becomes app/acme/billing/refunds.
• Nothing is fetched until the model loads one. Then newt reads SKILL.md and checks its size, sha256 digest and frontmatter against the listing.
• A skill’s other files are readable through load_skill with file, each checked the same way.

A file that fails a check never reaches the model. Protocol 2.6 has the full rules.