Skills reference

A skill is any markdown file. Hiveloom reads the file verbatim and appends it to the agent’s system prompt whenever the agent is invoked.

File format

There is no required structure, but these conventions help the agent:

# Skill name
 
Short description of when this skill applies.
 
## Instructions
 
Specific directives to the agent: how to behave, what to emphasise, what to
avoid.
 
## Examples (optional)
 
Concrete input → output pairs that the agent uses as few-shot grounding.

Frontmatter is not parsed by Hiveloom — everything becomes prompt text.

Discovery

Skills are registered explicitly via hiveloom capability add; Hiveloom does not scan a folder. This means:

• You can store skill files anywhere (git repo, shared drive, /etc/hiveloom/skills).
• hiveloom capability add ... --from-file PATH imports the file’s contents into the tenant store. Moving or deleting the source file after import has no effect on the installed skill.
• To re-sync after editing the source file, use hiveloom capability edit <agent> <name> --from-file PATH.

Lifecycle

Size and performance

Skills are cheap: they’re just text. But they count against the model’s context window every turn, so keep each one focused. If you have many skills, consider consolidating related ones into a single file. Very long skills (>2000 tokens each) will reduce the amount of conversation history the model can attend to — see Operations for how Hiveloom manages this.

What skills are not

• Skills are not tools. They don’t invoke external APIs. They only shape what the agent says. For tool-calling, see the capability add --cap-endpoint URL path in the CLI reference.
• Skills are not fine-tuning. They’re per-request prompt injection. If you uninstall one, the effect disappears on the next turn.
• Skills are not tenant-global. They’re attached to a specific agent. Cloning a skill to another agent means running capability add again.

Next

Examples — three annotated worked skills you can adapt.