> ## Documentation Index > Fetch the complete documentation index at: https://docs.teamfollowup.ai/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Use the public API base URL: https://api.teamfollowup.ai/api. > Authenticate public API requests with Authorization: Bearer YOUR_API_KEY. > Use product-owned terms: agents, calls, campaigns, contacts, phone numbers, billing, and configuration. # Replace all agent skills > Replace the entire skills list. Any existing skill omitted from the request is deleted. expectedVersion is required, and an empty list also requires confirmClear: true. Prefer single-skill operations unless you intentionally own the full list. Required API key scope: `agents:write`. ## OpenAPI ````yaml /openapi.yaml put /api/agent-builder/agents/{id}/skills openapi: 3.1.0 info: title: TFUAI Server API version: 1.0.0 description: >- API reference for the TFUAI SaaS server. All published endpoints are mounted under `/api`. Responses use a standard envelope: `{ "success": true, ... }` on success and `{ "success": false, "error": "..." }` on failure. Product API modules are being launched module by module. This spec currently exposes only contracted public modules. Authenticate public API requests with an API key in the `Authorization` header: `Authorization: Bearer YOUR_API_KEY`. servers: - url: https://api.teamfollowup.ai description: Production API origin. Public API paths are under /api. - url: https://devapi.teamfollowup.ai description: Development API origin. Public API paths are under /api. security: [] tags: - name: Agents description: Manage voice agents, campaigns, workflows, and outcomes. - name: Analytics description: >- Minimal, non-billing performance summary: volume, conversion, and pickup metrics. - name: Calls description: Review calls, test runs, and execution history. - name: Campaign Workflows description: >- What runs after a call lands: for each outcome (booked, opted out, asked for a callback…), an ordered chain of actions — tag the contact, move a pipeline stage, send an SMS, book an appointment. Stored as a graph: `nodes` are the actions, `edges` say what follows what, and `dispositionEntries` maps each outcome to the node its chain starts at. **Pick the narrowest endpoint that does the job.** | To | Call | | | --- | --- | --- | | See what fires per outcome | `GET .../workflow/digest` | Reads as plain text, no graph walking | | Add steps to an outcome | `POST .../outcomes/{outcome}/nodes` | Server derives node ids, edge ids, handles, layout | | Change a message, tag or setting | `PATCH .../workflow` | Merges; carries no graph, so it cannot damage one | | Remove one step | `DELETE .../nodes/{nodeId}` | Also re-links the chain around it | | Author or replace the whole graph | `PUT .../workflow` | Replaces everything you send | `PUT` is the only one that can re-wire, position nodes, build an `if`, save an unconfigured draft, or copy a whole workflow — and the only one that can overwrite a change someone else made after you read it. Use it when you are genuinely authoring the graph, and send `expectedVersion` when you do. For everything else the narrower endpoints are both easier and safer. - name: Contacts description: Contact list, filters, contact call history, and do-not-call actions. - name: GHL description: CRM variables and contact helpers used by agent and campaign setup flows. - name: Phone Numbers description: >- Caller ID pool, number search, assignment, movement, and release endpoints. - name: Power Dialer description: >- Power Dialer queue, lead cadence, callback, parked lead, and campaign schedule endpoints. - name: Projects description: >- Project management endpoints: list, update, disconnect, configure project campaigns, and validate setup. - name: Skills and Tools description: Manage reusable agent behaviors and in-call tool descriptions. - name: Voices description: Voice catalogue endpoints for choosing the voice used by an agent. paths: /api/agent-builder/agents/{id}/skills: put: tags: - Skills and Tools summary: Replace all agent skills description: >- Replace the entire skills list. Any existing skill omitted from the request is deleted. expectedVersion is required, and an empty list also requires confirmClear: true. Prefer single-skill operations unless you intentionally own the full list. Required API key scope: `agents:write`. operationId: put-agent-builder-agents-by-id-skills parameters: - name: id in: path required: true schema: type: string minLength: 1 description: Agent id. example: agent_01J2ABCDEF1234567890 requestBody: required: true content: application/json: schema: type: object additionalProperties: false properties: skills: type: array maxItems: 40 items: $ref: '#/components/schemas/SkillsSkill' expectedVersion: type: integer minimum: 0 confirmClear: type: boolean description: Must be true when skills is empty. required: - skills - expectedVersion examples: default: value: skills: - id: pricing_objections type: instructions name: Pricing objections whenToUse: The caller says the service costs too much. enabled: true instructions: >- Acknowledge the concern, explain the value, and never invent a discount. expectedVersion: 4 responses: '200': description: Skills replaced. content: application/json: schema: $ref: '#/components/schemas/SkillsReplaceResponse' examples: default: value: success: true skills: - id: pricing_objections type: instructions name: Pricing objections whenToUse: The caller says the service costs too much. enabled: true instructions: >- Acknowledge the concern, explain the value, and never invent a discount. version: 5 '400': $ref: '#/components/responses/ValidationError' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '404': $ref: '#/components/responses/NotFound' '409': description: The supplied version is stale. Read the latest skills and retry. content: application/json: schema: $ref: '#/components/schemas/ApiError' examples: default: value: success: false error: CONFLICT message: >- This agent’s skills changed since you read them. Re-read and reapply your change. '429': $ref: '#/components/responses/RateLimited' '500': $ref: '#/components/responses/ServerError' security: - ApiKeyAuth: [] x-codeSamples: - lang: bash label: cURL source: |- curl --request PUT \ --url https://api.teamfollowup.ai/api/agent-builder/agents/{id}/skills \ --header 'Authorization: Bearer YOUR_API_KEY' \ --header 'Content-Type: application/json' \ --data '{ "skills": [ { "id": "pricing_objections", "type": "instructions", "name": "Pricing objections", "whenToUse": "The caller says the service costs too much.", "enabled": true, "instructions": "Acknowledge the concern, explain the value, and never invent a discount." } ], "expectedVersion": 4 }' components: schemas: SkillsSkill: oneOf: - $ref: '#/components/schemas/SkillsInstructionsSkill' - $ref: '#/components/schemas/SkillsServiceAreaSkill' - $ref: '#/components/schemas/SkillsLiveTransferSkill' - $ref: '#/components/schemas/SkillsAddTagSkill' - $ref: '#/components/schemas/SkillsCheckTagSkill' - $ref: '#/components/schemas/SkillsAppointmentBookingSkill' discriminator: propertyName: type SkillsReplaceResponse: type: object additionalProperties: false properties: success: type: boolean const: true version: type: integer minimum: 0 partialFailures: type: array items: type: string description: >- Background synchronization work that did not finish. The skill change was still saved. skills: type: array items: $ref: '#/components/schemas/SkillsSkill' required: - success - skills - version ApiError: type: object description: Standard error envelope returned by the API. properties: success: type: boolean example: false error: type: string description: Short machine-readable error code. example: Unauthorized message: type: string description: Human-readable explanation of the error. example: Authentication required. required: - success - error SkillsInstructionsSkill: title: Custom instruction skill description: >- A plain-English playbook that teaches the agent when and how to handle a use case. type: object additionalProperties: {} properties: id: type: string minLength: 1 description: Stable skill id. Generated when omitted during creation. type: type: string const: instructions name: type: string minLength: 1 maxLength: 120 pattern: \S description: >- Human-readable name for the skill. Longer input is truncated to 120 characters and saved, not rejected. Whitespace is trimmed first, so a whitespace-only name is rejected as empty. whenToUse: type: string maxLength: 300 default: '' description: >- Plain-English trigger: when the agent should reach for this. Longer input is truncated to 300 characters and saved, not rejected. enabled: type: boolean default: true description: >- Whether the skill is active on the agent. A disabled skill is kept but its tool is not installed. instructions: type: string minLength: 1 maxLength: 12000 pattern: \S description: >- The playbook the agent follows once the trigger lands. Longer input is truncated to this length and saved; it is not rejected. Leading and trailing whitespace is stripped before validation, so a value that is only whitespace counts as empty. required: - type - name - instructions SkillsServiceAreaSkill: title: Service area check description: A deterministic ZIP coverage check the agent can use during a call. type: object additionalProperties: {} properties: id: type: string minLength: 1 description: Stable skill id. Generated when omitted during creation. type: type: string const: smart_service_area name: type: string minLength: 1 maxLength: 120 pattern: \S description: >- Human-readable name for the skill. Longer input is truncated to 120 characters and saved, not rejected. Whitespace is trimmed first, so a whitespace-only name is rejected as empty. whenToUse: type: string maxLength: 300 default: '' description: >- Plain-English trigger: when the agent should reach for this. Longer input is truncated to 300 characters and saved, not rejected. enabled: type: boolean default: true description: >- Whether the skill is active on the agent. A disabled skill is kept but its tool is not installed. zips: type: string minLength: 1 maxLength: 4000 pattern: \d{5} description: >- Coverage list, separated by commas or line breaks. Only five-digit US ZIP codes are recognised: the server extracts every run of five digits and ignores the rest, so a list of non-US postcodes parses to nothing and is rejected. Longer input is truncated to this length and saved; it is not rejected. outOfAreaResponse: type: string maxLength: 400 default: '' description: >- What the agent should do when the caller's ZIP is outside the list. Longer input is truncated to this length and saved; it is not rejected. required: - type - name - zips SkillsLiveTransferSkill: title: Live transfer description: A configured human transfer destination the agent can use during a call. type: object additionalProperties: {} properties: id: type: string minLength: 1 description: Stable skill id. Generated when omitted during creation. type: type: string const: live_transfer name: type: string minLength: 1 maxLength: 120 pattern: \S description: >- Human-readable name for the skill. Longer input is truncated to 120 characters and saved, not rejected. Whitespace is trimmed first, so a whitespace-only name is rejected as empty. whenToUse: type: string maxLength: 300 default: '' description: >- Plain-English trigger: when the agent should reach for this. Longer input is truncated to 300 characters and saved, not rejected. enabled: type: boolean default: true description: >- Whether the skill is active on the agent. A disabled skill is kept but its tool is not installed. transferNumber: type: string maxLength: 40 pattern: ^$|^\+[1-9]\d{6,14}$ description: >- Destination phone number in E.164 format, for example `+14155550100`. A national or formatted number such as `(415) 555-0100` is rejected. May be omitted or left empty to save the skill as a draft; the campaign cannot go live until a destination is set. example: '+14155550100' required: - type - name SkillsAddTagSkill: title: Add a tag description: >- A CRM action that lets the agent add one of the configured tags during a call. type: object additionalProperties: {} properties: id: type: string minLength: 1 description: Stable skill id. Generated when omitted during creation. type: type: string const: add_tag name: type: string minLength: 1 maxLength: 120 pattern: \S description: >- Human-readable name for the skill. Longer input is truncated to 120 characters and saved, not rejected. Whitespace is trimmed first, so a whitespace-only name is rejected as empty. whenToUse: type: string maxLength: 300 default: '' description: >- Plain-English trigger: when the agent should reach for this. Longer input is truncated to 300 characters and saved, not rejected. enabled: type: boolean default: true description: >- Whether the skill is active on the agent. A disabled skill is kept but its tool is not installed. tags: type: string maxLength: 1500 description: >- Tags the agent may apply, separated by commas or line breaks. Case is kept as typed; duplicates are removed case-insensitively. Up to 30 tags, each truncated to 100 characters. May be omitted or left empty to save the skill as a draft, in which case the tool is installed in a fail-closed state that applies nothing until at least one tag is set. Longer input is truncated to this length and saved; it is not rejected. example: qualified_lead, hot required: - type - name SkillsCheckTagSkill: title: Check a tag description: >- A CRM lookup that lets the agent check for one of the configured tags during a call. type: object additionalProperties: {} properties: id: type: string minLength: 1 description: Stable skill id. Generated when omitted during creation. type: type: string const: check_tag name: type: string minLength: 1 maxLength: 120 pattern: \S description: >- Human-readable name for the skill. Longer input is truncated to 120 characters and saved, not rejected. Whitespace is trimmed first, so a whitespace-only name is rejected as empty. whenToUse: type: string maxLength: 300 default: '' description: >- Plain-English trigger: when the agent should reach for this. Longer input is truncated to 300 characters and saved, not rejected. enabled: type: boolean default: true description: >- Whether the skill is active on the agent. A disabled skill is kept but its tool is not installed. tags: type: string maxLength: 1500 pattern: ^\s*[^,\n]+\s*,?\s*$ description: >- The single tag to check for. Unlike Add a Tag, this takes EXACTLY ONE tag: supplying two or more is rejected with "can only check one tag", and supplying none is rejected too. There is no draft state for this skill. example: existing_customer checkingMessage: type: string maxLength: 200 default: '' description: >- What the agent says while the lookup runs. Longer input is truncated to this length and saved; it is not rejected. required: - type - name - tags SkillsAppointmentBookingSkill: title: Appointment booking description: >- Lets the agent offer real calendar availability and book the time the lead accepts. It carries no settings of its own: the calendar it books against is campaign configuration, and the campaign cannot go live until one is set. type: object additionalProperties: {} properties: id: type: string minLength: 1 description: Stable skill id. Generated when omitted during creation. type: type: string const: appointment_booking name: type: string minLength: 1 maxLength: 120 pattern: \S description: >- Human-readable name for the skill. Longer input is truncated to 120 characters and saved, not rejected. Whitespace is trimmed first, so a whitespace-only name is rejected as empty. whenToUse: type: string maxLength: 300 default: '' description: >- Plain-English trigger: when the agent should reach for this. Longer input is truncated to 300 characters and saved, not rejected. enabled: type: boolean default: true description: >- Whether the skill is active on the agent. A disabled skill is kept but its tool is not installed. required: - type - name responses: ValidationError: description: Validation failed / malformed request. content: application/json: schema: $ref: '#/components/schemas/ApiError' Unauthorized: description: Missing or invalid authentication. content: application/json: schema: $ref: '#/components/schemas/ApiError' Forbidden: description: Authenticated but not permitted (role or tenant scope). content: application/json: schema: $ref: '#/components/schemas/ApiError' NotFound: description: Resource not found. content: application/json: schema: $ref: '#/components/schemas/ApiError' RateLimited: description: Rate limit exceeded. content: application/json: schema: $ref: '#/components/schemas/ApiError' ServerError: description: Unexpected server error. content: application/json: schema: $ref: '#/components/schemas/ApiError' securitySchemes: ApiKeyAuth: type: http scheme: bearer bearerFormat: API key description: 'Send your API key as `Authorization: Bearer YOUR_API_KEY`.' ````