← 返回 Skills 市场
🔌

MetatextAI

作者 OOMOL · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
32
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install oo-metatextai
功能描述
MetatextAI (metatext.ai). Use this skill for ANY MetatextAI request — reading, creating, and updating data. Whenever a task involves MetatextAI, use this ski...
使用说明 (SKILL.md)

MetatextAI

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

Category: AI, Security & Identity. Exposes 4 action(s).

Running an action

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

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

oo connector run "metatextai" --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_policy — Create one guardrail policy for the connected MetatextAI application.
  • evaluate — Evaluate one chat transcript against the connected MetatextAI application's configured guardrails.
  • list_policies — List all guardrail policies configured for the connected MetatextAI application.
  • run_test_scan — Run a MetatextAI red-team test scan for the connected application with the selected probes.

Safety

  • Read actions (get / list / search) are safe to run directly.
  • Create, update, send, or post actions change MetatextAI 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 — MetatextAI 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=metatextai
    
  • 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 this only if you intend to let an agent operate your connected MetatextAI account through OOMOL. Review any create_policy or test-scan payload before approval, since those actions can change application guardrails or consume service resources.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The skill's stated purpose matches its capabilities: listing and creating guardrail policies, evaluating transcripts, and running MetatextAI test scans through the metatextai connector.
Instruction Scope
Runtime instructions are scoped to oo connector schema/run commands and explicitly require user confirmation before write or destructive actions.
Install Mechanism
First-time setup includes a remote oo CLI installer command, but it is disclosed and only presented as a fallback when the CLI is missing.
Credentials
The allowed tool scope is limited to Bash(oo *), and external service access is expected for this connector-based integration.
Persistence & Privilege
The skill relies on an OOMOL-connected MetatextAI account and persistent service credentials, but says credentials are injected server-side and raw tokens are not handled by the skill.
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-metatextai
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /oo-metatextai 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 the initial `oo-metatextai` skill for operating MetatextAI through an OOMOL-connected account without handling raw API tokens. - Supports creating guardrail policies for a connected MetatextAI application. - Supports listing configured guardrail policies to inspect current application protection rules. - Supports evaluating chat transcripts against the application's configured guardrails. - Supports running MetatextAI red-team test scans with selected probes. - Includes action-level usage references and safety guidance for schema inspection, write confirmation, authentication fallback, and connector execution through the `oo` CLI.
元数据
Slug oo-metatextai
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

MetatextAI 是什么?

MetatextAI (metatext.ai). Use this skill for ANY MetatextAI request — reading, creating, and updating data. Whenever a task involves MetatextAI, use this ski... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 32 次。

如何安装 MetatextAI?

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

MetatextAI 是免费的吗?

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

MetatextAI 支持哪些平台?

MetatextAI 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 MetatextAI?

由 OOMOL(@oomol)开发并维护,当前版本 v1.0.0。

💬 留言讨论