← 返回 Skills 市场
🔌

Vapi

作者 OOMOL · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
37
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install oo-vapi
功能描述
Vapi (vapi.ai). Use this skill for ANY Vapi request — reading, creating, updating, and deleting data. Whenever a task involves Vapi, use this skill instead o...
使用说明 (SKILL.md)

Vapi

Operate Vapi through your OOMOL-connected account. This skill calls the vapi connector with the oo CLI; OOMOL injects credentials server-side, so you never handle raw tokens.

Category: AI, Communication. Exposes 38 action(s).

Running an action

Assume the user has already installed the oo CLI, signed in, and connected Vapi. Do not run oo auth login or open the connection URL proactively — just run the action. Fall back to First-time setup only when a command actually fails with an auth or connection error.

1. Inspect the contract to get the authoritative input/output schema before building a payload:

oo connector schema "vapi" --action "\x3Caction_name>"

2. Run the action with a JSON payload that matches the input schema:

oo connector run "vapi" --action "\x3Caction_name>" --data '\x3Cjson>' --json
  • --data takes a JSON object string or @path/to/file.json; omit it to send {}.
  • The response is { "data": ..., "meta": { "executionId": "..." } }; the execution id lives under meta.executionId.

Each action below links to a reference file with its purpose and exact commands. Read the linked file, then fetch the live schema with oo connector schema before constructing --data.

Available actions

  • create_analytics_query — Create and execute one or more Vapi analytics queries across call and subscription data.
  • create_assistant — Create a new Vapi assistant with required transcriber, voice, and model settings plus optional messaging and duration controls.
  • create_eval — Create a Vapi eval for a mock conversation and define the checkpoint messages used to evaluate model behavior.
  • create_openai_chat — Create an OpenAI-compatible Vapi chat response using an assistant or squad, with optional session and transport settings.
  • create_phone_number — Create a Vapi phone number using Vapi, Twilio, Vonage, Telnyx, or bring-your-own provider settings.
  • create_policy — Create a Vapi monitoring policy with severity, threshold, and schedule or interval configuration.
  • create_provider_resource — Create a pronunciation dictionary provider resource in Vapi, defaulting to the 11labs pronunciation-dictionary route used by the upstream toolkit.
  • create_scorecard — Create a Vapi scorecard for observability and evaluation using structured output metrics and conditions.
  • create_session — Create a Vapi session with either an assistant identifier or an inline assistant configuration.
  • delete_call — Delete a Vapi call by its unique identifier.
  • delete_chat — Delete a Vapi chat by its unique identifier.
  • delete_eval — Delete a Vapi eval by its unique identifier.
  • delete_eval_run — Delete a Vapi eval run by its unique identifier.
  • delete_phone_number — Delete a Vapi phone number by its unique identifier.
  • get_assistant — Retrieve a Vapi assistant by its unique identifier.
  • get_call — Retrieve a single Vapi call by its unique identifier.
  • get_chat — Retrieve a Vapi chat by its unique identifier.
  • get_eval — Retrieve a Vapi eval by its unique identifier.
  • get_file — Retrieve Vapi file metadata by file identifier.
  • get_tool — Retrieve a Vapi tool by its unique identifier.
  • list_assistants — List Vapi assistants with optional created/updated timestamp filters and a configurable page size.
  • list_calls — List Vapi calls with optional filtering by call, assistant, phone number, and created or updated timestamps.
  • list_chats — List Vapi chats with pagination plus optional assistant, squad, session, previous chat, and timestamp filters.
  • list_evals — List Vapi evals with pagination plus optional identifier and timestamp-based filters.
  • list_insights — List Vapi insights with pagination plus optional identifier and timestamp filters.
  • list_monitoring_policies — List Vapi monitoring policies with optional severity, monitor, and timestamp filters.
  • list_phone_numbers — List Vapi phone numbers with optional created and updated timestamp filters.
  • list_provider_resources — List Vapi provider resources for a provider and resource type with optional identifier and timestamp filters.
  • list_scorecards — List Vapi scorecards with pagination plus optional identifier and timestamp filters.
  • list_sessions — List Vapi sessions with pagination plus optional identifier, name, assistant, workflow, squad, and timestamp filters.
  • list_structured_outputs — List Vapi structured outputs with pagination plus optional identifier, name, and timestamp filters.
  • test_code_tool_execution — Execute TypeScript code inside Vapi's code tool sandbox and return the logs, result, and execution outcome.
  • update_assistant — Update an existing Vapi assistant and keep only the fields that should change in the request body.
  • update_eval — Update a Vapi eval and keep only the fields that should change in the request body.
  • update_insight — Update a Vapi insight by replacing its name, queries, formulas, grouping, and time range settings.
  • update_phone_number — Update a Vapi phone number and keep only the fields that should change in the request body.
  • update_tool — Update a Vapi tool configuration, including function definitions, HTTP request settings, and retry policies.
  • upload_file — Upload a file to Vapi knowledge storage from a public URL or base64 payload and return the resulting file metadata.

Safety

  • Read actions (get / list / search) are safe to run directly.
  • Create, update, send, or post actions change Vapi state — confirm the exact payload and effect with the user before running.
  • Delete or remove actions are destructive — always confirm the target and get explicit approval first.

First-time setup

These are one-time steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.

  • oo: command not found — install the oo CLI (other platforms: \x3Chttps://cli.oomol.com/install-guide.md>):

    curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
    
    irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell
    
  • Not signed in / authentication error — sign in to your OOMOL account once:

    oo auth login
    
  • scope_missing / credential_expired / app_not_ready / app_not_found — Vapi is not connected, or the connection expired or lacks a scope. Connect once (auth type: API key) at:

    https://console.oomol.com/app-connections?provider=vapi
    
  • HTTP 402 / OOMOL_INSUFFICIENT_CREDIT — billing stop. Recharge at https://console.oomol.com/billing/token-recharge before retrying.

Resources

安全使用建议
Review this before installing if you do not need Vapi code-tool testing. If installed, use it only with a Vapi account you trust it to manage, confirm all write/delete payloads, and require explicit approval before running the TypeScript execution action.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The stated purpose is broad Vapi account operations, and most actions fit that purpose, including read, create, update, upload, and delete workflows. However, the artifact also includes test_code_tool_execution, which runs TypeScript in Vapi's code-tool sandbox and is higher-impact than ordinary Vapi data management.
Instruction Scope
The skill instructs agents to inspect schemas and confirms writes/deletes with the user, which is good. The code-execution action is disclosed in the action list, but it lacks comparable guidance about approval, allowed use cases, network access, secrets, or sandbox limits.
Install Mechanism
Installation and setup use the oo CLI and OOMOL account connection, with a documented curl/PowerShell installer fallback only if the CLI is missing. This is disclosed, but users should be comfortable with OOMOL mediating the Vapi connection.
Credentials
The declared local tool access is limited to Bash commands beginning with oo, which is proportionate for an OOMOL connector. The remote Vapi authority is broad because it can read, create, update, upload, delete, and execute sandboxed code through the connected account.
Persistence & Privilege
The skill requires a persistent OOMOL/Vapi connection and sensitive credentials, but it says credentials are injected server-side and does not show hidden local persistence, background workers, or local credential harvesting.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install oo-vapi
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /oo-vapi 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of the `oo-vapi` skill for operating Vapi through an OOMOL-connected account via the `oo` CLI. - Supports 38 Vapi actions for assistants, calls, chats, sessions, phone numbers, files, tools, evals, scorecards, insights, analytics, monitoring policies, and provider resources. - Provides read workflows for listing and retrieving Vapi resources with filtering, pagination, and timestamp-based query options where supported. - Enables controlled create and update workflows for assistants, chats, sessions, phone numbers, evals, scorecards, analytics queries, policies, tools, files, and provider resources. - Includes destructive delete actions for calls, chats, evals, eval runs, and phone numbers, with explicit safety guidance requiring confirmation before use. - Documents schema-first execution: inspect each live action contract with `oo connector schema`, then run the connector with validated JSON payloads.
元数据
Slug oo-vapi
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Vapi 是什么?

Vapi (vapi.ai). Use this skill for ANY Vapi request — reading, creating, updating, and deleting data. Whenever a task involves Vapi, use this skill instead o... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 37 次。

如何安装 Vapi?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install oo-vapi」即可一键安装,无需额外配置。

Vapi 是免费的吗?

是的,Vapi 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Vapi 支持哪些平台?

Vapi 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Vapi?

由 OOMOL(@oomol)开发并维护,当前版本 v1.0.0。

💬 留言讨论