← 返回 Skills 市场
🔌

Recall.ai

作者 OOMOL · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
25
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install oo-recallai
功能描述
Recall.ai (recall.ai). Use this skill for ANY Recall.ai request — reading, creating, updating, and deleting data. Whenever a task involves Recall.ai, use thi...
使用说明 (SKILL.md)

Recall.ai

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

Category: Communication, AI. Exposes 5 action(s).

Running an action

Assume the user has already installed the oo CLI, signed in, and connected Recall.ai. 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 "recallai" --action "\x3Caction_name>"

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

oo connector run "recallai" --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_bot — Create a Recall.ai bot with the core scheduling, recording, automatic-leave, and metadata fields needed for a first-pass meeting bot workflow.
  • delete_bot_media — Delete the Recall.ai media artifacts stored for a completed bot after downstream processing is finished.
  • get_bot — Retrieve one Recall.ai bot by bot ID, including its current status changes, recordings, and metadata.
  • list_bots — List Recall.ai bots with optional filters for scheduled date window, meeting URL, platform, status, metadata, and pagination.
  • remove_bot_from_call — Remove a Recall.ai bot from the meeting immediately when it is already active in the call.

Safety

  • Read actions (get / list / search) are safe to run directly.
  • Create, update, send, or post actions change Recall.ai 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 — Recall.ai 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=recallai
    
  • 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
This skill can be installed based on the available clean scan evidence. As with any skill, review its displayed instructions and any requested API keys or external services before use, especially if you plan to run it on private or sensitive data.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The target is a skill version with clean VirusTotal telemetry, clean SkillSpector output, and no supplied non-VT malicious or static-scan signal indicating purpose-mismatched capability.
Instruction Scope
No prompt-injection indicators, unsafe runtime instructions, hidden role changes, or output-format manipulation were supplied for this artifact.
Install Mechanism
The supplied metadata does not show install-time scripts, automatic execution, package mutation, or other hidden installation behavior requiring review.
Credentials
No evidence was supplied of overbroad local indexing, credential/session harvesting, destructive writes, or unrelated network/data flows.
Persistence & Privilege
No evidence was supplied of background persistence, privilege escalation, long-running workers, or persistent changes outside ordinary skill installation.
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-recallai
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /oo-recallai 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
- Operates Recall.ai through an OOMOL-connected account using the `oo` CLI, with credentials handled server-side. - Adds bot lifecycle actions for creating meeting bots, retrieving a bot by ID, and listing bots with filters for schedule, meeting URL, platform, status, metadata, and pagination. - Supports first-pass meeting bot workflows with scheduling, recording, automatic-leave behavior, and metadata fields. - Provides cleanup and control actions to delete completed bot media artifacts and remove an active bot from a call. - Documents schema-first execution for each action so payloads are built against the live connector contract. - Includes safety guidance for read, write, and destructive Recall.ai operations.
元数据
Slug oo-recallai
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

Recall.ai 是什么?

Recall.ai (recall.ai). Use this skill for ANY Recall.ai request — reading, creating, updating, and deleting data. Whenever a task involves Recall.ai, use thi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 25 次。

如何安装 Recall.ai?

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

Recall.ai 是免费的吗?

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

Recall.ai 支持哪些平台?

Recall.ai 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 Recall.ai?

由 OOMOL(@oomol)开发并维护,当前版本 v1.0.0。

💬 留言讨论