Skip to main content

Documentation Index

Fetch the complete documentation index at: https://curia.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

Skills are the mechanism through which agents interact with external services and take action in the world. When Curia sends an email, searches the web, creates a calendar event, or looks up a contact, it is invoking a skill. Agents don’t call APIs directly — they invoke skills, which handle authentication, validation, and output sanitization on their behalf. The LLM never sees raw credentials.

​
Two types of skills

Curia supports two types of skills, and agents work with both using the same interface — they cannot tell the difference at runtime.
Local skills live in the skills/ directory as a folder containing a manifest and handler:
skills/
  email-send/
    skill.json      # manifest: name, inputs, outputs, permissions, sensitivity
    handler.ts      # implementation
    handler.test.ts # tests
The manifest declares everything the execution layer needs to validate, authorize, and invoke the skill. The handler implements the actual logic.

​
The skill manifest

Every local skill includes a skill.json manifest that the execution layer validates at startup. Here is a real example from the email-send skill: 
{
  "name": "email-send",
  "description": "Send a new email via the configured email account",
  "version": "1.0.0",
  "sensitivity": "normal",
  "action_risk": "medium",
  "inputs": {
    "to": "string",
    "cc": "string?",
    "subject": "string",
    "body": "string"
  },
  "outputs": {
    "message_id": "string",
    "to": "string",
    "subject": "string"
  },
  "permissions": [],
  "secrets": [],
  "timeout": 30000
}

​
Manifest fields

FieldDescription
nameUnique identifier used by agents and the skill registry
descriptionHuman-readable description — shown to the LLM and in the registry
sensitivitynormal or elevated — controls first-use approval behavior
action_riskRisk level used by the autonomy engine — see below
inputsInput schema — validated before the handler is called
outputsOutput schema — documents what the skill returns
permissionsDeclared capabilities, validated at load time
secretsEnv-var-backed secrets this skill may request via ctx.secret()
timeoutPer-invocation timeout in milliseconds (default: 30,000)

​
Action risk levels

Every skill declares an action_risk value that indicates its potential impact on the world. This field is required — Curia will not start if any skill manifest omits it.
LevelMin autonomy scoreCapability class
none0Read-only, no external effects (web search, summarization)
low60Internal state writes — memory, contacts
medium70Outbound communications — sending email or Signal messages
high80Calendar writes, commitments made on behalf of the CEO
critical90Financial, destructive, or irreversible actions
The autonomy engine uses these values to determine whether a given skill can run at the current autonomy score. See Autonomy engine for the full picture.

​
Sensitivity and first-use approval

The sensitivity field controls what happens the first time an agent tries to use a skill it was not explicitly configured with:
  • normal — the skill is auto-approved if the agent has allow_discovery: true
  • elevated — skills like payment processing or bulk deletion require your explicit approval the first time an agent requests them; once approved for that agent, they do not ask again
This means you review elevated-sensitivity skills once, not on every invocation.

​
Secrets: credentials the LLM never sees

Skills that need API keys, passwords, or tokens declare them in their secrets array. At runtime, the execution layer provides a scoped ctx.secret() accessor: 
// Inside a skill handler
const apiKey = ctx.secret("NYLAS_API_KEY");
The execution layer validates that the calling skill’s manifest declared the requested secret. If a skill tries to access a secret it did not declare, the call fails. Agents and LLMs never see secret values — only the skill handler does, and only through this scoped accessor. Every secret access is audit-logged (which skill, which task, when) — but values are never written to the log.

​
Output sanitization

Every skill result is sanitized before the LLM sees it. This prevents tool outputs from being used as injection vectors:
  • XML and HTML tags are stripped — they cannot be interpreted as system instructions
  • Outputs longer than 200,000 characters are truncated with a [truncated] marker
  • Patterns matching known secret formats (API keys, tokens, passwords) are redacted
  • Error strings are wrapped in a structured format that prevents them from being read as instructions
Nothing from the outside world reaches the LLM unfiltered.

​
Built-in skills

Curia ships with more than 50 built-in skills across several categories:
email-send, email-reply, email-list, email-get, email-archive, email-draft-save — send, reply, browse, and draft emails via the Nylas API across multiple configured accounts.
calendar-list-calendars, calendar-list-events, calendar-create-event, calendar-update-event, calendar-delete-event, calendar-find-free-time, calendar-check-conflicts, calendar-register — full calendar management via Nylas.
contact-create, contact-lookup, contact-list, contact-link-identity, contact-set-role, contact-merge, contact-find-duplicates, contact-grant-permission, contact-revoke-permission, contact-unlink-identity, contact-set-trust — manage contacts and their trust levels.
web-search, web-fetch, web-browser — search the web via Tavily, fetch static pages, or use a full Playwright-backed browser for JavaScript-rendered sites.
entity-context, context-for-email, knowledge-company-overview, knowledge-meeting-links, knowledge-travel-preferences, knowledge-loyalty-programs, query-relationships, delete-relationship, extract-facts, extract-relationships — query and extend the knowledge graph.
scheduler-create, scheduler-list, scheduler-cancel, scheduler-report — create and manage recurring or one-shot scheduled tasks.
template-meeting-request, template-reschedule, template-cancel, template-doc-request — structured outbound email templates for common executive workflows.
delegate, bullpen, skill-registry, held-messages-list, held-messages-process, signal-send — inter-agent delegation, the Bullpen discussion space, skill discovery, and held-message management.
get-autonomy, set-autonomy — read and update the global autonomy score. Pinned to the Coordinator only.
These MCP servers are not bundled with Curia but are documented as first-class integrations:
ServerPurpose
Google WorkspaceDrive, Docs, Sheets, Gmail read/search/write
FilesystemScoped local file access (read/write/search)
GitHubRepository management, issues, pull requests
Brave SearchAdditional web search for research agents
FetchWeb fetching with robots.txt compliance
To connect any MCP server, add it to config/skills.yaml using the mcp_servers block shown above. Curia will discover and register its tools automatically at startup.

Building custom skills

Build a local skill from scratch with a manifest and handler.

Autonomy

See how action_risk values gate skill execution by autonomy score.