← 返回 Skills 市场
youteacherasia

Mongolian AI for Codex

作者 Buhe · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
46
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install mongolian-ai-codex
功能描述
Use for Mongolian-language work through the Mongol Open Idea API at https://mongol.open-idea.net/api/v1, including Chinese, traditional Mongolian, and Cyrill...
使用说明 (SKILL.md)

Mongolian AI

Use the Mongol Open Idea API directly from Codex. This is not the OpenAI API and does not use OpenClaw gateway commands.

Base URL: https://mongol.open-idea.net/api/v1

This skill is suitable for public distribution because it does not bundle API keys or account-specific configuration. Each user must provide their own API key.

Setup

Read the API key from MONGOL_OPEN_IDEA_API_KEY.

If the variable is missing, tell the user:

MONGOL_OPEN_IDEA_API_KEY is not configured. Create an API key at https://mongol.open-idea.net, then set it in your local shell or Codex environment as MONGOL_OPEN_IDEA_API_KEY. Do not paste the key into chat.

Never ask the user to paste the key into the conversation. If the user already pasted a key, warn them to revoke it and create a new one. Do not echo the key.

Do not store API keys in this skill folder, examples, logs, screenshots, or generated artifacts.

Route Each Request

Choose the endpoint every turn:

  • Image input or "OCR": POST /ocr.
  • Audio input or transcription: prefer async POST /audio/async, then poll GET /audio/async/{jobId} every 3-5 seconds until done.
  • Read aloud, synthesize speech, or play audio: prefer async POST /tts/async, then poll GET /tts/async/{jobId}; use sync POST /tts only for very short text.
  • Pure translation or script conversion, including "translate", "what does this mean", "Cyrillic to traditional Mongolian": POST /translation.
  • Mongolian text plus a request to answer in Chinese: POST /chat/completions with a Chinese system message.
  • Mongolian input without translation intent: POST /chat/completions with a Mongolian-only system message.
  • Word/PDF document translation: use the matching document endpoint; read references/api-reference.md first.

For OCR -> translation or ASR -> translation chains, pass the prior response field by variable or structured data. Do not manually copy text from logs, terminal previews, or chat snippets into the next paid request.

Cost Confirmation

Short translations and short chats can be called directly.

Before long text, batch jobs, Word/PDF translation, OCR, ASR, or TTS, estimate cost and ask for confirmation. See references/behavior.md for rates and retry rules.

Do not repeat a successful paid request just because the visible output looks odd or the user dislikes the result. Ask for explicit approval before any redo that may charge again.

Output Contract

After a successful API call, final user-visible output must be:

  1. Business content only.
  2. Billing line(s), if the response headers or JSON body include billing fields.

Business content fields:

  • POST /translation: data.tgtText; concatenate segments in order.
  • POST /chat/completions: choices[0].message.content.
  • POST /ocr, POST /word/translation, POST /pdf/translation: data.text.
  • POST /audio and completed POST /audio/async: data.text.
  • POST /tts: save/play the binary audio; do not print binary, base64, or full WAV content.
  • Completed POST /tts/async: decode audioBase64 to WAV; do not print base64.

Billing fields:

  • Headers: X-Mengguyu-Billing-Charged, X-Mengguyu-Billing-Balance, X-Mengguyu-Billing-Currency.
  • JSON: billingCharged, billingBalance, and any returned currency field.

If billing fields are present, append exactly:

本次扣费: {charged} {currency}, 余额: {balance} {currency}

If multiple successful calls in one workflow each include billing fields, append one billing line per call in call order. If no billing fields are present, do not invent a billing line.

Do not expose request payloads, raw JSON, internal routing notes, model names, token usage, or code blocks in the final answer unless the user is debugging the integration.

Implementation Help

Prefer scripts/mongol_api.py for JSON requests because it preserves headers and body together for billing extraction:

python3 scripts/mongol_api.py translation --from zh --to mw --content "你好"

Read these references only when needed:

  • references/api-reference.md: endpoint payloads, language codes, TTS/ASR polling, chat token sizing.
  • references/behavior.md: cost, retry, redo, and output self-check rules.
安全使用建议
Install only if you are comfortable sending the relevant Mongolian text, audio, images, or documents to the Mongol Open Idea API using your own API key. Keep the key in MONGOL_OPEN_IDEA_API_KEY, do not paste it into chat, and review charges before long text, document, OCR, ASR, or TTS jobs.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The artifacts consistently describe Mongolian translation, chat, OCR, ASR, TTS, and document translation through a single external API, and the helper script only implements that API workflow.
Instruction Scope
The skill includes cost-confirmation and output rules, but its agent default prompt is narrowly worded for Chinese-to-traditional-Mongolian translation, which could steer ambiguous invocations even though the main SKILL.md routes requests by user intent.
Install Mechanism
No bundled dependencies, installer hooks, hidden setup, or embedded credentials were found; it reads MONGOL_OPEN_IDEA_API_KEY from the environment and explicitly tells users not to paste or store keys in artifacts.
Credentials
User-provided text, images, audio, and documents may be sent to the Mongol Open Idea API and may incur charges, but this is disclosed and proportionate to the stated functionality.
Persistence & Privilege
No background workers, privilege escalation, broad local indexing, credential-store access, or durable persistence were found; TTS audio file output is expected for the feature.
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 mongolian-ai-codex
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /mongolian-ai-codex 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
Initial public Codex skill for Mongol Open Idea API translation, chat, OCR, ASR, and TTS.
元数据
Slug mongolian-ai-codex
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

Mongolian AI for Codex 是什么?

Use for Mongolian-language work through the Mongol Open Idea API at https://mongol.open-idea.net/api/v1, including Chinese, traditional Mongolian, and Cyrill... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 46 次。

如何安装 Mongolian AI for Codex?

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

Mongolian AI for Codex 是免费的吗?

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

Mongolian AI for Codex 支持哪些平台?

Mongolian AI for Codex 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 Mongolian AI for Codex?

由 Buhe(@youteacherasia)开发并维护,当前版本 v1.0.0。

💬 留言讨论