Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

md-translator医学博士翻译

Agent Skill

md-translator 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

449

周安装

18

GitHub Stars

158

下载量

145
CodexClaudeCursorGemini CLI

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

unknown

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:md-translator(医学博士翻译)
来源仓库:https://github.com/panaversity/agentfactory
仓库路径:skills/md-translator
安装命令:
npx skills add https://github.com/panaversity/agentfactory --skill md-translator
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/panaversity/agentfactory --skill md-translator

简介

用于查找、检索和筛选相关信息。md-translator 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

  • 适合在关键词搜索或任务场景中快速定位候选结果。
  • 通过 GitHub 安装,建议核验权限范围和联网行为。
  • 使用前应确认维护状态及是否会触发文件读写操作。
  • 可结合原始 README 进一步了解具体用法。

SKILL.md

Markdown Translator for Docusaurus

Translate Docusaurus docs (MD/MDX and i18n JSON) to a target language while preserving all syntax, structure, and Docusaurus-specific components.

Before Implementation

SourceGather
ConversationTarget locale, scope (file/chapter/all/JSON), resume vs fresh
ManifestRead apps/learn-app/translation-work/manifest.json for current state
GlossaryLoad references/glossary-<locale>.md for terminology
Source filesRead files to translate from apps/learn-app/docs/
RulesRead references/translation-rules.md before first translation

Required Clarifications

  1. What locale? (if not specified or inferrable from conversation)
  2. What scope? Single file, chapter, all JSON files, or full locale

Optional Clarifications

  1. Resume from manifest or start fresh? (default: resume)
  2. Specific files to prioritize? (default: by chapter order)

Critical Rule: YOU Do the Translation

The extract/reassemble/validate scripts are helpers. The actual translation is YOUR job. Read each segment's original field and write a real, fluent, human-quality translation in the target language.

  • Output MUST be actual text in the target script (Urdu = نستعلیق, Hindi = देवनागरी, Chinese = 中文)
  • NEVER append language tags like [UR], copy English unchanged, or write placeholders
  • If you cannot translate well enough, STOP and tell the user
  • Use the glossary for terminology consistency
  • See references/validation-guide.md for correct vs wrong examples

Prerequisites

pip install markdown-it-py

Core Pipeline

Every MD/MDX file follows this pipeline:

Check Manifest → Extract (script) → Translate (YOU) → Reassemble (script) → Validate (script) → Update Manifest

Step 1: Check Manifest

Read apps/learn-app/translation-work/manifest.json. Follow the decision tree in references/manifest-guide.md to determine what work is needed.

Step 2: Extract Segments

python scripts/translate_md.py extract <source.md> <segments.json> --lang <code>

Output to: apps/learn-app/translation-work/<locale>/<name>_<locale>_segments.json

<name> = source filename stem (e.g., 01-the-2025-inflection-point). See references/docusaurus-i18n.md for full naming conventions and path examples.

Step 3: Translate Segments (YOUR JOB)

  1. Read the segments JSON (frontmatter_segments, body_segments, and admonition_segments)
  2. For EACH segment, translate originaltranslated in the target language
  3. Preserve all inline Markdown formatting (see references/translation-rules.md)
  4. Skip pure code, URLs, and numbers (copy as-is)
  5. Translate admonition_segments titles (e.g., "Pro Tip" → target language)
  6. Save to: apps/learn-app/translation-work/<locale>/<name>_<locale>_translated.json
  7. Run quality gate from references/validation-guide.md before proceeding

Step 4: Reassemble

python scripts/translate_md.py reassemble <source.md> <translated.json> <output.md>

Output to: apps/learn-app/i18n/<locale>/docusaurus-plugin-content-docs/current/<path>/

Create parent directories first: mkdir -p <parent>

Step 5: Validate

python scripts/translate_md.py validate <source.md> <output.md>

Step 6: Update Manifest

Update status and timestamps after each step. See references/manifest-guide.md.

Workflow Modes

Status Check (always start here)

Report current translation state for the requested locale from the manifest.

Single File

Run the full pipeline (Steps 1-6) for one MD/MDX file.

Chapter Batch

  1. Discover path: ls -d apps/learn-app/docs/*/<chapter-num>-*/
  2. List all .md/.mdx files in the chapter
  3. Check manifest — skip files already completed with current MD5
  4. Run the pipeline for each file needing work
  5. Report: "Translated X new, skipped Y done, Z total"

JSON Files

Translate the 4 Docusaurus i18n JSON files (code.json, current.json, navbar.json, footer.json):

  1. Read each source JSON
  2. Translate "message" values (keep "description" in English)
  3. Preserve all {placeholder} tokens and | pluralization separators
  4. Urdu is NOT Arabic — use the correct language
  5. Write to apps/learn-app/i18n/<locale>/<path>
  6. Update manifest

Resume / Continue

Read manifest, find incomplete files, resume from last completed step.

New Content Sync

Scan docs/ against manifest, mark new files as missing, changed files as stale, then translate only what needs updating.

Reference Files

FileWhen to Read
references/translation-rules.mdBefore first translation in a session
references/docusaurus-i18n.mdWhen unsure about output paths or folder structure
references/manifest-guide.mdWhen checking/updating translation state
references/validation-guide.mdBefore marking any file as translated
references/glossary-<locale>.mdBefore translating to that locale
references/glossary-template.mdWhen adding a new locale with no glossary

Error Recovery

ProblemAction
Script fails on extractCheck file encoding, ensure markdown-it-py installed
Malformed JSON after translateValidate JSON before saving, fix syntax errors
Validation failsRead the specific failure, fix the translated output, re-validate
Wrong language in outputMark wrong_language in manifest, re-translate
Source file changedMark stale in manifest, re-extract and re-translate
Cannot translate wellSTOP, tell the user, suggest alternative approach

Output

  • Working files: apps/learn-app/translation-work/<locale>/
  • Final MD: apps/learn-app/i18n/<locale>/docusaurus-plugin-content-docs/current/<path>/
  • Final JSON: apps/learn-app/i18n/<locale>/<path>/
  • Manifest: Always update apps/learn-app/translation-work/manifest.json

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

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

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

Codex

32.1%
按下载量换算47

Claude

30.97%
按下载量换算45

Cursor

18.68%
按下载量换算27

Gemini CLI

8.8%
按下载量换算13

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。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