Skip to main content

How to Use Agent Skills

๐Ÿ”ง Tools ยท ๐Ÿ“‹ Prompt

Skills are markdown documents that teach the agent how to handle specific tasks. You write a skill, drop it in a directory (or save it as a tag-note in the platform), and the agent discovers it automatically. No Python, no deployment for tag-note skills.

How Skills Workโ€‹

At startup, the agent loads only each skill's name and description (~100 tokens each). When a user request matches a skill, the agent calls use_skill to load the full instructions and follows them for that task.

Three progressive levels:

  1. Catalog - skill name + description (always loaded at startup)
  2. Instructions - full step-by-step guidance (loaded on demand via use_skill)
  3. Resources - companion files like templates or examples (loaded on demand via read_skill_resource)

List and Enable Sourcesโ€‹

za agents capabilities skills-sources list
za agents capabilities skills-sources configure <source-name>

Configure Provider Settingsโ€‹

za agents capabilities skills-sources settings
SettingTypeDefaultDescription
injection_mode"prompt" | "tools" | "both""both"How skills surface to the agent. prompt = catalog in system prompt, tools = use_skill tool only, both = both channels
prompt_format"text" | "xml""text"Formatting of skill catalog. xml recommended for Anthropic/Claude models
include_location_in_promptboolfalseInclude file paths in the prompt (useful for debugging)
writable_sourcestr or nullnullWhich source receives skills created via create_skill at runtime

Skill Sourcesโ€‹

SourceCLI nameDefaultDescription
Disk SkillsdiskdisabledMarkdown skill files on the file system
In-Memory Skillsin-memory-skillsdisabledSkills defined inline in JSON configuration
Platform Docs Skillsplatform-docs-skillsdisabledBuilt-in skills covering Zeta Alpha platform features
Tag Notestag-notesdisabledSkills stored as tag-notes in the platform UI
Skill Notesskill-notesdisabledPlatform-managed skill notes with scope filtering
Skill Creation Skillsskill-creation-skillsdisabledMeta-skills that teach the agent how to author new skills
Image Search Skillsimage-search-skillsdisabledSkills for image-based search workflows

Disk Skillsโ€‹

Loads skill files from directories on the file system. Each skill lives in its own subdirectory with a SKILL.md file and optional companion resources.

za agents capabilities skills-sources configure disk

Configurationโ€‹

SettingTypeDefaultDescription
skills_directorieslist[str][]Directories to scan for skill subdirectories

Directory Structureโ€‹

<agents project>/
โ”œโ”€โ”€ agent_setups.json
โ””โ”€โ”€ skills/
โ”œโ”€โ”€ summarize-document/
โ”‚ โ””โ”€โ”€ SKILL.md
โ””โ”€โ”€ compare-papers/
โ”œโ”€โ”€ SKILL.md
โ””โ”€โ”€ comparison-template.md โ† companion resource

Companion files in the skill directory are accessible to the agent via read_skill_resource.


In-Memory Skillsโ€‹

Skills defined entirely in JSON configuration โ€” no files needed. Useful for simple skills or skills managed through tenant configuration.

za agents capabilities skills-sources configure in-memory-skills

Configurationโ€‹

SettingTypeDefaultDescription
skillslist[{name, description, body}][]List of skill definitions
{
"in_memory_skills_source_configuration": {
"enabled": true,
"skills": [
{
"name": "executive-summary",
"description": "Write an executive summary. Use when asked for 'executive summary' or 'brief for leadership'.",
"body": "## Steps\n\n1. Identify the key findings\n2. Write a 3-paragraph summary\n3. Keep under 300 words"
}
]
}
}

In-memory skills do not support companion resources (read_skill_resource returns an error). For skills that need templates, use disk skills.


Platform Docs Skillsโ€‹

Curated skills covering the Zeta Alpha platform features โ€” search, tags, documents, chat, data analysis, chemistry tools, memory, and notes.

za agents capabilities skills-sources configure platform-docs-skills

Configurationโ€‹

SettingTypeDefaultDescription
skill_overridesdict[str, str] or nullnullOverride individual skill bodies by name

Registers 8 built-in skills:

SkillCoverage
platform-searchKeyword search, filters, search tabs, QA widget, federated web search
platform-tagsCreate, organize, share document collections
platform-documentsUpload, manage, read, and chat with private documents
platform-chatConversational AI, agents, context, deep research, scheduled agents
platform-data-analysisSpreadsheets, CSV/Excel, SQL, statistics, charting
platform-chemistryMolecular tools, SMILES, PubChem, drug-likeness
platform-skills-and-memoryPersistent memory, custom skill authoring
platform-notesCreate, manage, and find notes and annotations

Tag Notesโ€‹

Skills stored as tag-notes in the platform UI โ€” no file system access or deployment needed. Anyone with access to a tag can author and share skills.

za agents capabilities skills-sources configure tag-notes

Configurationโ€‹

SettingTypeDefaultDescription
tag_idslist[str][]Tags to load skills from
include_favoritesboolfalseAlso load skills from the user's favorites tag

Skill Notesโ€‹

Platform-managed skill notes with scope-based access control.

za agents capabilities skills-sources configure skill-notes

Configurationโ€‹

SettingTypeDefaultDescription
include_scopeslist[str]["own"]Which scopes to read from (e.g. ["own"], ["own", "shared"])
allowed_skill_note_idslist[str] or nullnullRestrict to specific skill note IDs; null loads all

Skill Creation Skillsโ€‹

Meta-skills that teach the agent how to author new skills through conversation. When a user asks the agent to remember a workflow or encode a process, the agent follows these meta-skills to write proper SKILL.md files with frontmatter, trigger phrases, and step-by-step instructions.

za agents capabilities skills-sources configure skill-creation-skills

No additional configuration beyond enabled.


Image Search Skillsโ€‹

Skills for image-based search workflows.

za agents capabilities skills-sources configure image-search-skills

No additional configuration beyond enabled.


Writing a Skillโ€‹

Create a SKILL.md file:

---
name: summarize-document
description: 'Summarize a document. Use when asked to "summarize", "give me a summary", or "what is this paper about".'
allowed_tools:
- read_document
- retrieve_metadata
---

## Steps

1. Use the document context to get the document ID, or ask the user which document to summarize
2. Call `retrieve_metadata` to get the title, source, and abstract
3. Call `read_document` to fetch the full content
4. Produce a structured summary:
- **Key findings** - the main claims or results
- **Methodology** - how the work was done
- **Conclusions** - implications and takeaways
5. Cite specific sections using the document URL

The description field is the discovery surface โ€” write it with trigger phrases so the agent knows when to activate the skill. The allowed_tools field tells the agent which tools it's expected to use.

Managing Skills via the CLIโ€‹

Add a Skillโ€‹

za agents skill add [NAME] [-d "description"] [--no-generate]

By default, this runs the agent headlessly to generate the skill content using its built-in create_skill capability. The agent writes a complete Skill.md with proper frontmatter and step-by-step instructions based on your description.

Use --no-generate to create an empty template instead:

za agents skill add "summarize-document" -d "Summarize a document" --no-generate

This creates:

skills/
summarize-document/
Skill.md

If you omit the name or description, the CLI prompts for them interactively.

List Skillsโ€‹

za agents skill list

Remove a Skillโ€‹

za agents skill remove [NAME]
info

For more on the Agent Skills protocol, see agentskills.io.