feat: skills i18n 改造(schemaVersion 1.1,零向后兼容) (#1)

* feat: skills i18n 改造 — schemaVersion 1.1,零向后兼容

把 21 个 skills + 1 个 agent + manifest/categories 全量迁移到 schemaVersion 1.1
的 i18n 结构,配套 CI AI 翻译流水线(GitHub Models)与本地工具链。

## 关键变更

### 数据结构(破坏性,schemaVersion 1.0 → 1.1)
- SKILL.md: 顶层 name 改为 ASCII slug(== 目录名,符合 agentskills.io 规范);
  中文显示名/short_desc/description 全部迁入 metadata.i18n.<locale>
- agents/<id>/agent.json: shortDesc/fullDesc/tags/persona.{role,traits} 迁入
  i18n.<locale>;changelog[].changes 改为 { <locale>: string[] } 对象
- categories.json: 每个分类的 label/description 迁入 i18n.<locale>,顶层只剩
  color/icon
- manifest.json: 加 supportedLocales / defaultLocale;顶层 description 迁入
  i18n.<locale>

### Body 文件结构
- 根 SKILL.md = frontmatter + default_locale (en-US) body
- SKILL.<locale>.md = 各 locale 的 markdown body(首行 <!-- locale: xx --> 自校验)

### 工具链(scripts/i18n/)
- glossary.json: zh→en 术语表 + do_not_translate 白名单
- schema/skill-frontmatter.schema.json: i18n frontmatter JSON Schema
- validate-i18n.py: 8 条校验规则(name 合规 / locale 完整性 / hash 一致性等)
- translate.py: GitHub Models / Anthropic 双 backend,sha256 增量翻译
- migrate.py: 一次性迁移脚本(旧格式 → i18n 结构)

### CI(.github/workflows/)
- i18n-validate.yml: PR 触发跑 validate + translate --check
- i18n-translate.yml: PR 触发用 GitHub Models(默认 openai/gpt-5-mini)翻译缺失
  locale,自动追加 commit;可切到 ANTHROPIC_API_KEY 走 Claude

### 文档
- docs/I18N.md: 作者贡献指南(schema 说明 / 提交流程 / 常见问题)
- README.md: 加多语言段落

## 验证

- uv run scripts/i18n/validate-i18n.py: OK,49 文件 0 错误
- uv run scripts/i18n/translate.py --check: 0 stale locale
- 21 skills 标题数 zh-CN == en-US 严格对齐(最大 66=66)
- skills-ref 规范校验:全部通过(顶层 name ASCII slug + description 单字段)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(i18n): 修复 PR #1 review 反馈的 6 项问题

- schema: translated_by 正则放宽为 ^(human|ai:[A-Za-z0-9._:/-]+)$,接受
  'ai:github:openai/gpt-5-mini' 这类 backend:model 形式(CI 翻译输出格式)
- README + docs/I18N.md: 修正"CI 用 Claude API"误导描述,正确说明默认是
  GitHub Models(openai/gpt-5-mini)+ GITHUB_TOKEN,可选切到 Anthropic
- skills/minimax-tts/SKILL.md & SKILL.zh-CN.md: 删除多余的 ``` 闭合,避免
  Markdown 后续渲染错乱
- skills/docx/SKILL.md: 翻译时丢失的 • Unicode escape 示例已恢复,
  与 zh-CN 版本对齐

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-05 00:26:33 +08:00
committed by GitHub
parent 1c107a9344
commit 1f7c8b9673
59 changed files with 10533 additions and 2014 deletions

View File

@@ -1,5 +1,5 @@
---
name: MiniMax 语音合成
name: minimax-tts
description: >-
Use this skill when the user wants to convert text to speech using MiniMax's
T2A (Text-to-Audio) API. Supports multiple voice styles, emotional control,
@@ -24,6 +24,29 @@ requires:
metadata:
author: desirecore
updated_at: '2026-04-25'
i18n:
default_locale: en-US
source_locale: zh-CN
locales:
- zh-CN
- en-US
zh-CN:
name: MiniMax 语音合成
short_desc: 基于 MiniMax Speech-02 的文本转语音技能
description: >-
Use this skill when the user wants to convert text to speech using MiniMax's T2A (Text-to-Audio) API. Supports multiple voice styles, emotional control, and voice cloning. Use when 用户提到 语音合成、文字转语音、TTS、朗读、 读出来、生成语音、生成音频、文本转音频、配音、念出来、MiniMax 语音。
body: ./SKILL.zh-CN.md
source_hash: sha256:455a2ee6365958c2
translated_by: human
en-US:
name: MiniMax Text-to-Speech
short_desc: Text-to-speech skill powered by MiniMax Speech-02
description: >-
Use this skill when the user wants to convert text to speech using MiniMax's T2A (Text-to-Audio) API. Supports multiple voice styles, emotional control, and voice cloning. Use when the user mentions text-to-speech, TTS, read aloud, read it out, generate speech, generate audio, text-to-audio, voiceover, narrate it, MiniMax voice.
body: ./SKILL.md
source_hash: sha256:455a2ee6365958c2
translated_by: ai:claude-opus-4-7
translated_at: '2026-05-03'
market:
icon: >-
<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0
@@ -32,7 +55,6 @@ market:
fill-opacity="0.1"/><path d="M8 9v6M11 7v10M14 10v4M17 8v8"
stroke="#007AFF" stroke-width="2"
stroke-linecap="round"/></svg>
short_desc: 基于 MiniMax Speech-02 的文本转语音技能
category: media
maintainer:
name: DesireCore Official
@@ -41,33 +63,33 @@ market:
listed: false
---
# minimax-tts 技能
# minimax-tts Skill
## 强制规则(违反将导致功能失败)
## Mandatory Rules (violations will cause feature failure)
1. **必须用 HTTPS 访问 agent-service**`https://127.0.0.1:${PORT}` `-k` 跳过证书验证
2. **全程使用 Bash curl** — 不要使用 HttpRequest 工具或 Python
1. **Must access agent-service over HTTPS**`https://127.0.0.1:${PORT}` with `-k` to skip certificate verification
2. **Use Bash curl throughout** — do not use the HttpRequest tool or Python
## 完整执行流程
## Complete Execution Flow
### 前置条件
### Prerequisites
- 用户已在资源管理器-算力中配置 MiniMax Media Provider 并填写 API Key
- agent-service 正在运行
- The user has configured a MiniMax Media Provider with an API Key under Resources → Compute
- agent-service is running
### 语音选择指南
### Voice Selection Guide
| voice_id | 特点 | 适用场景 |
| voice_id | Characteristics | Use Cases |
|----------|------|---------|
| male-qn-qingse | 青涩男声 | 旁白、播客 |
| female-shaonv | 少女女声 | 有声书、对话 |
| female-yujie | 御姐女声 | 专业播报 |
| presenter_male | 主持人男声 | 新闻、正式场合 |
| presenter_female | 主持人女声 | 新闻、正式场合 |
| male-qn-qingse | Young male voice | Narration, podcasts |
| female-shaonv | Young female voice | Audiobooks, dialogue |
| female-yujie | Mature female voice | Professional broadcasting |
| presenter_male | Male anchor voice | News, formal occasions |
| presenter_female | Female anchor voice | News, formal occasions |
### 生成语音
### Generate Speech
MiniMax TTS 返回 JSON包含音频 URL hex 数据),`responseType` 使用 `"json"`
MiniMax TTS returns JSON (containing an audio URL or hex data); use `"json"` for `responseType`.
```bash
PORT=$(cat ~/.desirecore/agent-service.port)
@@ -94,11 +116,11 @@ curl -sk -X POST "https://127.0.0.1:${PORT}/api/media-proxy" \
}'
```
### 响应处理
### Response Handling
MiniMax TTS 返回 JSON根据请求参数可能返回 URL hex 格式:
MiniMax TTS returns JSON which, depending on the request parameters, may contain a URL or hex format:
**URL 格式响应**(推荐,需在 audio_setting 中设置 `"format": "url"`
**URL format response** (recommended, requires `"format": "url"` in audio_setting):
```json
{
"success": true,
@@ -115,7 +137,7 @@ MiniMax TTS 返回 JSON根据请求参数可能返回 URL 或 hex 格式:
}
```
**Hex 格式响应**(默认):
**Hex format response** (default):
```json
{
"success": true,
@@ -136,11 +158,11 @@ MiniMax TTS 返回 JSON根据请求参数可能返回 URL 或 hex 格式:
}
```
### 下载并上传到 media-store
### Download and Upload to media-store
音频 URL 有时效限制,必须立即下载并保存到本地 media-store
Audio URLs have a time limit, so they must be downloaded immediately and saved to the local media-store.
**URL 格式**
**URL format**:
```bash
PORT=$(cat ~/.desirecore/agent-service.port)
AUDIO_URL="响应中的audio_url"
@@ -149,7 +171,7 @@ curl -sk -X POST "https://127.0.0.1:${PORT}/api/media/upload" \
-F "file=@/tmp/minimax-tts.mp3;type=audio/mpeg"
```
**Hex 格式**
**Hex format**:
```bash
PORT=$(cat ~/.desirecore/agent-service.port)
HEX_DATA="响应中的hex数据"
@@ -158,49 +180,48 @@ curl -sk -X POST "https://127.0.0.1:${PORT}/api/media/upload" \
-F "file=@/tmp/minimax-tts.mp3;type=audio/mpeg"
```
从 JSON 响应中提取 `mediaId` 字段。
Extract the `mediaId` field from the JSON response.
### 展示结果
### Display the Result
在回复中使用 dc-media 协议引用(前端会自动识别音频扩展名并渲染播放器):
Reference it in your reply using the dc-media protocol (the frontend will automatically detect the audio extension and render a player):
```
![语音合成结果](dc-media://这里替换为mediaId)
```
```
### 参数说明
### Parameter Reference
| 参数 | 说明 | 默认值 |
| Parameter | Description | Default |
|------|------|--------|
| model | 模型 | "speech-02-hd"(高清)或 "speech-02-turbo"(快速) |
| text | 要转换的文本 | 最大 10000 字符 |
| voice_setting.voice_id | 语音角色 | "male-qn-qingse" |
| voice_setting.speed | 语速 | 1.0 |
| voice_setting.vol | 音量 | 1.0 |
| voice_setting.pitch | 音调 | 0 |
| audio_setting.format | 音频格式 | "mp3" |
| audio_setting.sample_rate | 采样率 | 32000 |
| model | Model | "speech-02-hd" (HD) or "speech-02-turbo" (fast) |
| text | Text to convert | Max 10000 characters |
| voice_setting.voice_id | Voice persona | "male-qn-qingse" |
| voice_setting.speed | Speaking speed | 1.0 |
| voice_setting.vol | Volume | 1.0 |
| voice_setting.pitch | Pitch | 0 |
| audio_setting.format | Audio format | "mp3" |
| audio_setting.sample_rate | Sample rate | 32000 |
### 特殊语法
### Special Syntax
MiniMax TTS 支持在文本中插入停顿标记:
- `<#0.5#>` — 停顿 0.5 秒
- `<#2#>` — 停顿 2 秒
- 有效范围:0.01 ~ 99.99
MiniMax TTS supports inserting pause markers in the text:
- `<#0.5#>`pause for 0.5 seconds
- `<#2#>`pause for 2 seconds
- Valid range: 0.01 ~ 99.99 seconds
示例:`"你好<#1#>欢迎来到 DesireCore"`
Example: `"你好<#1#>欢迎来到 DesireCore"`
### 错误处理
### Error Handling
- `success: false` + `statusCode: 400`:文本为空或参数格式错误
- `success: false` + `statusCode: 401`API Key 无效
- `success: false` + `statusCode: 429`:频率限制
- `success: false` + `error: "未找到匹配的供应商"`:未配置 MiniMax Media Provider
- `success: false` + `statusCode: 400`: empty text or malformed parameters
- `success: false` + `statusCode: 401`: invalid API Key
- `success: false` + `statusCode: 429`: rate limited
- `success: false` + `error: "未找到匹配的供应商"`: MiniMax Media Provider not configured
### 注意事项
### Notes
- 文本超过 3000 字符时建议使用流式输出(但代理模式暂不支持流式)
- 返回的 audio_url 有 24 小时时效
- 如果用户未明确要求,默认使用 `speech-02-hd` + `male-qn-qingse` + 1.0 倍速
- 长文本建议分段调用,每段不超过 3000 字符
- For text exceeding 3000 characters, streaming output is recommended (proxy mode does not yet support streaming)
- Returned audio_url is valid for 24 hours
- Unless the user specifies otherwise, default to `speech-02-hd` + `male-qn-qingse` + 1.0x speed
- For long text, split it into segments of no more than 3000 characters each