Skills

Build once. Reuse everywhere.

Skills are the atomic capabilities every AI employee draws from — search a wiki, open a ticket, provision an account, refund an invoice. One catalogue, one identity model, one audit trail. 48+ shipped, and one open SDK to write your own.

Catalogue

Six kinds of skill.

Every skill in the catalogue falls into one of six intents. Read down the group titles and you get the platform's working vocabulary in a glance.

Search & Retrieve

Grounded lookups against your corpus, your warehouse, and your systems of record.

Search DocumentationQuery WarehouseFetch Ticket ContextRead Salesforce RecordRead HRIS ProfileRead GitHub IssueFetch Meeting NotesRead Slack Thread
Communicate

Deliver the answer, the update, or the request — through whatever channel the reader lives in.

Send Slack MessageReply on ZendeskSend EmailPost to ConfluenceUpdate Notion PagePost to TeamsReply on IntercomSend SMS (out-of-band)
Provision & Grant

The write-side skills that turn a request into a state change — always through the approval matrix.

Provision Okta UserReset PasswordGrant Access (JIT)Revoke AccessAdd to GroupAssign SaaS LicenceCreate Google Workspace AccountApprove Request
Create & Update

Structured writes into your systems of record — CRM, ITSM, docs, code.

Create Jira TicketUpdate Salesforce DealUpdate HubSpot ContactCreate GitHub IssueOpen PR (draft)Log Time Off (HRIS)File Expense (Concur)Schedule Meeting
Analyze & Draft

Reasoning-heavy skills that read many sources and produce one output.

Analyze ContractDraft Security QuestionnaireGenerate ReportProcess InvoiceCategorise ExpenseSummarise ThreadExtract EntitiesScore Deal
Control & Escalate

Operational skills for the reviewer, not the requester — approvals, escalations, incident coordination.

Route to ApproverStep-up MFA ChallengeEscalate to On-CallOpen Incident (Jira)Page PagerDutyFreeze AccountTrigger RollbackNotify Manager
Shared by design

One skill. Every agent that needs it.

A skill is not agent-specific. Ivy calls `provision-okta-user` for a new hire; Sig calls the same skill during a step-up review; a custom automation agent calls it on a schedule. Guardrails, permissions, and evaluation travel with the skill — not with each caller.

  • One implementation · many callers · one audit trail
  • Guardrails and PII rules live with the skill
  • Skills call other skills — no reinvention
  • Versioning + deprecation windows on the contract
Written by the people who ship them

Skills are how your platform team makes the AI workforce yours.

Every organisation has one or two capabilities no vendor ships — a bespoke ticket-triage rule, an ERP-specific write, a compliance skill the auditors know by name. The SDK is designed so those skills feel like first-class citizens beside the ones we ship, not bolt-ons around them.

See the developer platform
Developer writing typed skill code at a monitor
Anatomy

Eight parts. One contract.

Every skill in the catalogue is composed of the same eight primitives. Change any one and the skill's behaviour changes — versioned, evaluated, and rolled forward through the same control plane.

Instructions

The system prompt that shapes voice, refusal behaviour, and when to escalate.

Tools

The APIs, MCP servers, or database queries this skill can call.

Knowledge

The corpora this skill reads from when the answer needs grounding.

Inputs

Typed inputs — email, ticket ID, entity path. Identity fields are injected, not model-supplied.

Outputs

Typed outputs — the shape callers depend on. Versioned; breaking changes are opt-in.

Permissions

Scoped access — a skill inherits the employee's ceiling and can narrow further.

Guardrails

Input and output filters — PII masking, prompt-injection screens, banned-content checks.

Validation

Golden-set evaluation that runs before promotion. Accuracy, tool-success, hallucination rate.

Every skill carries

The guarantees that make a skill safe to reuse

Typed inputs
OpenAPI-style schemas
Typed outputs
versioned contract
Identity injection
email never model-supplied
Permission ceiling
inherits from employee
Guardrails
input + output filters
Idempotency
safe to retry
Audit event
every call logged
Rollback path
reversible writes
Cost + latency
measured per call
Evaluation
golden set before ship
Versioning
semver, deprecation window
Rate limits
per employee, per skill
Custom skills

Write your own. In an afternoon.

The SDK ships the same primitives the built-in skills use — typed inputs, typed outputs, permission scoping, guardrails, evaluation. Write a skill in TypeScript, ship it via the CLI, roll it out by percent or cohort. Or expose your internal tool as an MCP server and every agent in your workspace can call it.

  • Typed schemas — no untyped tool calls
  • Test locally with `bq skill run`
  • Golden-set evals gate promotion
  • MCP bridge — expose any tool to any agent
Governance

Every skill carries a risk tier.

Read-only skills default to autopilot. Reversible writes route through the approval matrix. Destructive writes add step-up MFA on the reviewer before execution. The tier is a property of the skill, not the caller — Ivy or a custom agent, same gate.

Read

Search, fetch, summarise — auto-run.

Reversible

Update fields, create tickets, add-to-group — routed for approval.

Destructive

Revoke, delete, transfer, refund — step-up MFA on the reviewer.

Skills your workforce actually runs on.

Book a demo and browse the catalogue on your own systems. First custom skill live in an afternoon.