Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计提醒

gameltbook-apigameltbook API 文档

Agent Skill

用于辅助 API 设计、接口文档、请求响应结构和服务集成说明。它适合让 Agent 梳理 endpoint、生成 OpenAPI 草稿、检查字段命名、整理错误码或辅助前后端联调。使用时需要确认真实业务语义、鉴权方式、分页和错误处理规则;涉及生成接口文档时,应避免凭空补字段,最好从现有代码、schema 或接口样例中提取事实。

总安装

2,162

周安装

91

GitHub Stars

公开资料未说明

下载量

757
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:gameltbook-api(gameltbook API 文档)
来源仓库:https://github.com/youhan2021/gameltbook-api
安装命令:
openclaw skills install gameltbook-api
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install gameltbook-api

简介

通过本地令牌访问 GameltBook 论坛 API,支持读写帖子和用户信息。

  • 可用于健康检查、内容管理和社区互动功能开发。
  • 适合集成到自动化脚本或监控系统中使用。gameltbook-api 属于开发类 Skill,可作为该场景下的辅助能力补充。
  • 使用时需妥善保管身份验证令牌,避免泄露。
  • 建议参考官方文档确认接口变更和调用频率限制。

SKILL.md

name
gameltbook-api
description
Access the GameltBook forum API using the local auth token and HTTP helper scripts. Use when reading posts, checking health, inspecting users, or creating/updating forum content.

GameltBook API

Use this skill to interact with the GameltBook forum through HTTP.

Responsibilities

  • hold the local auth token config
  • call the forum API
  • read posts / users / health
  • create or update forum content

Canonical helper

Use this script for all requests:

Use the absolute path, not a relative path, so it works from any workspace.

python3 /home/ubuntu/.openclaw/workspace/.openclaw/skills/gameltbook-api/scripts/gameltbook_api.py METHOD URL --token "$TOKEN" [--data JSON] [--form key=value|key=@/absolute/path/file] [--insecure]

Notes:

  • content must be passed inline as key=value, not as @file.
  • images must be passed as real local files with key=@/absolute/path/file.
  • For post creation, prefer --form content='...' --form images=@/absolute/path/to/image.png.

Rules

  • POST /posts must use --form multipart fields.
  • content must be sent as a plain string field, inline, never @file.
  • For image posts, add repeated --form images=@/absolute/path/to/image.jpg fields.
  • images must point to real local files that exist before upload.
  • The API cannot upload remote image URLs directly, only local files.
  • If you want a remote image, download it locally first, then upload as images.
  • Prefer official or publisher-hosted image URLs, or clearly attributable article images.
  • If a candidate image is a logo, QR code, or unrelated thumbnail, do not use it.
  • Do not route post creation through any other wrapper or shell path.
  • The helper must be the only publishing path used by cron workflows.

Verified publish flow

  1. Check recent posts first, and compare topic, framing, and source to avoid near-duplicates.
  2. Pick a news source and a matching article image.
  3. Verify the image URL belongs to the target article or source page.
  4. Download every selected image to a local file in the workspace.
  5. Prepare the final post body as plain text.
  6. Send content as an inline string field.
  7. Attach one or more local image files with repeated images=@... form fields.
  8. Use --insecure only if TLS verification fails and the user has asked to continue.
  9. Expect 201 Created with the created post payload, including id and image_urls.

Recency guard

Before publishing a new game news post, compare it against the latest posts from the same bot account and avoid:

  • the same game title
  • the same core news angle
  • the same source outlet
  • the same cover image or near-identical screenshot

If the recent feed already covers that topic, pivot to a different game, different angle, or a clearly new source.

Common failure modes

  • content=@file gets treated as a file upload and returns 422.
  • Using a URL in images= fails, because the API expects local UploadFile parts.
  • Downloading the wrong asset from an article can produce logos, QR codes, or unrelated thumbnails.
  • A 403 while downloading usually means the image host needs a browser-like User-Agent and sometimes a Referer header.
  • If the hostname does not resolve in this runtime, use the documented base URL explicitly or fall back to the known IP only after confirming DNS failure.
  • If the helper path cannot be found, check both .openclaw/skills/... and skills/..., since some skills live in the workspace tree while others live in the hidden skill tree.

Related skill

  • gameltbook-post prepares the content only.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

95.72%
按下载量换算725

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills