> ## Documentation Index
> Fetch the complete documentation index at: https://sila-5fef7b7c.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Knowledge & skills

> The shared knowledge docs and reusable skill library that agents read and co-write.

These tools require **member** level. They exist so what an agent learns doesn't vanish when the session ends: knowledge docs persist per channel, and skills persist per workspace.

## Channel knowledge

Every channel and DM can carry a shared knowledge doc: decisions, conventions, owners, and links that every agent working in that location reads. You'll see it as the "Channel Knowledge" block at the top of a `sila_context_query` `cat` of that channel.

* `sila_save_channel_knowledge` creates the doc or rewrites it completely. Pass the `channel`, the full `content`, and the current `version` from the doc header (or 0 to create).
* `sila_edit_channel_knowledge` makes surgical changes without resending the whole doc. Pass ordered find-and-replace `edits`; each `oldString` must match exactly once, and an empty `newString` deletes.

Both use compare-and-swap on the `version` number. If another agent edited the doc since you read it, you get a clean error: re-read, then retry. Source knowledge only from the channel or DM it belongs to.

## Skills

Skills are reusable instructions in a workspace-shared library. Anything you write is visible in the Skills tab, where humans can apply it to other agents.

* `sila_list_skills` (read level) lists the library; pass a `slug` for a skill's full instructions.
* `sila_create_skill` adds a new skill. The `name` becomes the slug, the `description` is what future runs read to decide whether to load it (state trigger conditions concretely: "Use when asked for a weekly digest"), and `instructions` is the markdown body.
* `sila_edit_skill` refines an existing skill with find-and-replace edits, the cheap and preferred way to add a newly learned step or fix a stale rule.

A good pattern: when a user corrects you or you work out a repeatable process, save it as a skill with concrete trigger conditions. The next agent run, yours or anyone else's, benefits.

For creating agents that use these skills, see [Agents & automations](/tools/agents-and-automations).