Skills

A skill is a short markdown primer the assistant loads on demand. Skills solve a specific problem: tool descriptions can't be long enough to teach the model your workspace conventions, but you don't want a 50-page system prompt on every turn either. Instead, the assistant browses a list of skills, decides "I'll need the data_python primer for this question", and pulls it in only for the turn that needs it.

The three scopes

Every skill lives in exactly one of three scopes, with the higher scope taking precedence on a name collision:

Built-in (global)

Ships in the platform. Maintained by the Dalea team. Every workspace sees the same set; cannot be edited or shadowed.

Workspace

Authored by workspace admins (anyone with the MANAGE_AI_SKILLS permission). Visible to every member of the workspace.

Personal

Authored by you, visible only to you. Use for personal shorthand, draft skills, or one-off domain notes that don't belong to the team yet.

The built-in skills

Three primers ship with the platform out of the box:

editing_dalea_documents

Authoring and editing documents — when to read a document outline vs the full content, how custom block fences work, how to safely round-trip grid blocks and registration tables.

writing_python_in_dalea

Writing Python in a document's embedded Pyodide block — the globals (get_block, get_sheet, get_cell), what the sandbox does and doesn't allow (no filesystem, no network).

designing_data_environments

Designing a data environment — entity tables vs result tables, the ten column types and their typeConfig shapes, displayPattern IDs, references, and atomic entity-row registration via bulk tools or registrationTable blocks.

The assistant pulls these in by name as it works; you don't usually need to do anything. Built-in skills are always enabled unless you explicitly turn one off.

Activating, deactivating, authoring

Settings → AI Skills shows every skill visible to you (built-in + workspace

• personal) with a toggle for each, and is where you author personal skills. Workspace skills are authored from Settings → Workspaces → <workspace> → AI Skills (requires the MANAGE_AI_SKILLS permission). Deactivating a skill in the settings removes the capability for an agent (in-platform or through MCP) to read the skill.

The editor enforces the same limits as the API:

Name

Lowercase, starts with a letter, 2-64 chars, may include digits and underscores. Pattern: ^[a-z][a-z0-9_]{1,63}$

Description

1-200 characters, single line (no newlines). This is what the assistant sees when deciding whether to load the skill — make it descriptive.

Body

Markdown, 1-20,480 characters (≈ 5,000 tokens, or roughly 500 lines of prose). This is the content the assistant pulls in once it decides to load the skill. The cap targets Anthropic's Agent Skills guidance — the body is returned as a tool-call payload that persists in the conversation, so big skills crowd context and disrupt prompt-cache reuse. If you need more, split into multiple skills the assistant can load on demand rather than one giant body.

You cannot publish a workspace or personal skill that shadows a built-in name — the API rejects it at write time.

Permissions

How the assistant uses them

On every turn, the assistant sees the list of activated skills with their names and descriptions in its tool catalogue. When a skill looks relevant, it calls load_skill(name) to pull the body into context for that turn. The body is not held across turns — the assistant re-loads any skill it still needs on the next turn, which keeps idle context small.

This means a high-quality description matters more than you'd think: it's how the assistant decides whether to look in the first place. "Authoring ELISA result protocols including dilution and curve-fit conventions" beats "ELISA things".

What's next