← 返回 Skills 市场
🔌

ScrapingAnt

作者 OOMOL · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
27
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install oo-scrapingant
功能描述
ScrapingAnt (scrapingant.com). Use this skill for ANY ScrapingAnt request — searching and reading data. Whenever a task involves ScrapingAnt, use this skill...
使用说明 (SKILL.md)

ScrapingAnt

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

Category: AI, Data & Analytics, Developer Tools. Exposes 4 action(s).

Running an action

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

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

oo connector run "scrapingant" --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

Safety

  • Read actions (get / list / search) are safe to run directly.
  • Create, update, send, or post actions change ScrapingAnt 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 — ScrapingAnt 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=scrapingant
    
  • 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 want agents to help with ClawHub and Convex maintenance. Review any authenticated GitHub, Convex, ClawHub moderation, or full-access review command before allowing it to run, especially actions that change roles, bans, PR comments, deployments, or local repository state.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The workspace contains repo-local skills for ClawHub maintenance, Convex setup/auth/migrations/performance work, UI proof, and review workflows; the described commands match those purposes.
Instruction Scope
The instructions are scoped to explicit user tasks, require confirmation for moderation writes, recommend verification, and do not contain prompt-injection or role-override behavior.
Install Mechanism
The skill content is plain markdown plus small metadata/icons and one review helper script; no automatic installer, autorun hook, or hidden persistence mechanism was found.
Credentials
The skills use local repo tools, package managers, GitHub/Convex/ClawHub CLIs, and authenticated APIs where expected for development and moderation workflows.
Persistence & Privilege
Some workflows can perform high-impact actions, such as moderation changes or full-access nested code review, but those are disclosed, user-invoked, and bounded by existing authentication and confirmation guidance.
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-scrapingant
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /oo-scrapingant 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 ScrapingAnt through the connected `scrapingant` connector without handling raw API tokens. - Supports full page scraping via ScrapingAnt's extended v2 output, including HTML, text, cookies, headers, XHRs, and iframes. - Converts web pages into Markdown using ScrapingAnt's Markdown transformation endpoint. - Extracts structured top-level JSON data from pages with ScrapingAnt's AI extraction endpoint. - Provides an action to check ScrapingAnt subscription status and remaining API credits. - Documents the standard `oo connector schema` and `oo connector run` workflow, including setup and safety guidance.
元数据
Slug oo-scrapingant
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

ScrapingAnt 是什么?

ScrapingAnt (scrapingant.com). Use this skill for ANY ScrapingAnt request — searching and reading data. Whenever a task involves ScrapingAnt, use this skill... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 27 次。

如何安装 ScrapingAnt?

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

ScrapingAnt 是免费的吗?

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

ScrapingAnt 支持哪些平台?

ScrapingAnt 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 ScrapingAnt?

由 OOMOL(@oomol)开发并维护,当前版本 v1.0.0。

💬 留言讨论