← 返回 Skills 市场
🔌

Claid AI

作者 OOMOL · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
30
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install oo-claid-ai
功能描述
Claid AI (claid.ai). Use this skill for ANY Claid AI request — reading, creating, and updating data. Whenever a task involves Claid AI, use this skill instea...
使用说明 (SKILL.md)

Claid AI

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

Category: AI, Design & Media. Exposes 3 action(s).

Running an action

Assume the user has already installed the oo CLI, signed in, and connected Claid 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 "claid_ai" --action "\x3Caction_name>"

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

oo connector run "claid_ai" --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

  • edit_image — Edit one publicly accessible image with Claid's synchronous image editing API and return the processed image metadata.
  • get_edit_task — Poll one Claid async image editing task by ID and return its current status plus the finished result when available.
  • submit_edit_image — Submit one publicly accessible image to Claid's async image editing API and return the task handle for later polling.

Safety

  • Read actions (get / list / search) are safe to run directly.
  • Create, update, send, or post actions change Claid 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 — Claid 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=claid_ai
    
  • 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
Install only if you trust OOMOL and intend to let your agent use your connected Claid AI account for image editing. Review generated payloads before approving edits, since actions may change Claid AI state or consume credits, and use the remote CLI installer only from the documented OOMOL source.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The stated purpose is to operate Claid AI image-editing actions through the OOMOL `oo` CLI, and the artifact only documents three Claid connector actions for editing and polling image edit tasks.
Instruction Scope
Runtime instructions are scoped to `oo connector schema` and `oo connector run` for the `claid_ai` connector, require live schema inspection, and tell the agent to confirm payloads before write-style actions.
Install Mechanism
The skill includes first-time setup commands that install the `oo` CLI via remote shell installers, but these are disclosed fallback steps only when `oo` is missing.
Credentials
The skill requires a connected Claid AI account/API-key integration through OOMOL and may consume service credits for image edits, which is expected for this purpose and disclosed.
Persistence & Privilege
No executable files, background workers, persistence hooks, broad local indexing, deletion behavior, or privilege escalation were present; tool access is limited to `Bash(oo *)`.
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-claid-ai
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /oo-claid-ai 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
- Adds an OOMOL skill for operating Claid AI through the `claid_ai` connector without handling raw API tokens. - Supports synchronous image editing for publicly accessible images via `edit_image`. - Supports asynchronous image editing workflows with `submit_edit_image` and `get_edit_task`. - Provides action reference files with schema inspection and execution commands for each supported connector action. - Defines safety guidance for confirming write operations and handling first-time setup or connection failures.
元数据
Slug oo-claid-ai
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

Claid AI 是什么?

Claid AI (claid.ai). Use this skill for ANY Claid AI request — reading, creating, and updating data. Whenever a task involves Claid AI, use this skill instea... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 30 次。

如何安装 Claid AI?

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

Claid AI 是免费的吗?

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

Claid AI 支持哪些平台?

Claid 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 Claid AI?

由 OOMOL(@oomol)开发并维护,当前版本 v1.0.0。

💬 留言讨论