desirecore/market
2
0
Fork 0
mirror of https://git.openapi.site/https://github.com/desirecore/market.git synced 2026-06-06 07:10:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* 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:
yi-ge
2026-05-05 00:26:33 +08:00
committed by GitHub
parent 1c107a9344
commit 1f7c8b9673
59 changed files with 10533 additions and 2014 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
skills/pdf/SKILL.md
View File

@@ -1,5 +1,5 @@
---
name: PDF 文档处理
name: pdf
description: >-
Use this skill whenever the user wants to do anything with PDF files. This
includes reading or extracting text/tables from PDFs, combining or merging
@@ -22,6 +22,29 @@ tags:
metadata:
author: anthropic
updated_at: '2026-04-13'
i18n:
default_locale: en-US
source_locale: zh-CN
locales:
- zh-CN
- en-US
zh-CN:
name: PDF 文档处理
short_desc: 读取、创建、合并、拆分和填写 PDF 文档
description: >-
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. Use when 用户提到 PDF、读取PDF、合并PDF、拆分PDF、填写表单、加水印、提取文字、 扫描识别。
body: ./SKILL.zh-CN.md
source_hash: sha256:15805c1921ac2c1e
translated_by: human
en-US:
name: PDF Document Processing
short_desc: Read, create, merge, split, and fill PDF documents
description: >-
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. Use when the user mentions PDF, reading PDFs, merging PDFs, splitting PDFs, filling forms, adding watermarks, extracting text, or OCR.
body: ./SKILL.md
source_hash: sha256:15805c1921ac2c1e
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
@@ -35,7 +58,6 @@ market:
stroke="url(#pd-a)" stroke-width="1.3" stroke-linecap="round"/><path
d="M17 11v6l2-1.5 2 1.5v-6z" fill="#FF3B30"
fill-opacity="0.8"/></svg>
short_desc: 读取、创建、合并、拆分和填写 PDF 文档
category: productivity
maintainer:
name: DesireCore Official
@@ -43,67 +65,67 @@ market:
channel: latest
---
# pdf 技能
# pdf skill
## L0：一句话摘要
## L0: One-Sentence Summary
读取、创建、合并、拆分和填写 PDF 文档，支持 OCR 识别和命令行工具。
Read, create, merge, split, and fill PDF documents, with OCR support and command-line tools.
## L1：概述与使用场景
## L1: Overview and Use Cases
### 能力描述
### Capability Description
pdf 是一个**流程型技能（Procedural Skill）**，提供 PDF 文档的完整处理能力。基于 Python 库（pypdf、pdfplumber、reportlab）和命令行工具（qpdf、pdftotext、pdftk），支持文本提取、表格提取、合并拆分、旋转、水印、加密、表单填写和 OCR 识别。
pdf is a **Procedural Skill** that provides full PDF document processing capabilities. Built on Python libraries (pypdf, pdfplumber, reportlab) and command-line tools (qpdf, pdftotext, pdftk), it supports text extraction, table extraction, merging/splitting, rotation, watermarking, encryption, form filling, and OCR.
### 使用场景
### Use Cases
- 用户需要从 PDF 中提取文本或表格数据
- 用户需要合并多个 PDF 或拆分页面
- 用户需要创建新的 PDF 文档
- 用户需要填写 PDF 表单、添加水印或加密
- The user needs to extract text or table data from a PDF
- The user needs to merge multiple PDFs or split pages
- The user needs to create a new PDF document
- The user needs to fill PDF forms, add watermarks, or encrypt PDFs
## L2：详细规范
## L2: Detailed Specification
## Prerequisites
### Python 3（必需）
### Python 3 (required)
在执行任何 Python 操作之前，先检测 Python 是否可用：
Before performing any Python operation, check that Python is available:
```bash
python3 --version 2>/dev/null || python --version 2>/dev/null
```
如果命令失败（Python 不可用），**必须停止并告知用户安装 Python 3**：
If the command fails (Python is not available), **you must stop and tell the user to install Python 3**:
- **macOS**: `brew install python3` 或从 https://www.python.org/downloads/ 下载
- **Windows**: `winget install Python.Python.3` 或从 python.org 下载（安装时勾选 "Add Python to PATH"）
- **macOS**: `brew install python3`, or download from https://www.python.org/downloads/
- **Windows**: `winget install Python.Python.3`, or download from python.org (check "Add Python to PATH" during installation)
- **Linux (Debian/Ubuntu)**: `sudo apt install python3 python3-pip`
- **Linux (Fedora/RHEL)**: `sudo dnf install python3 python3-pip`
如需更详细的环境配置帮助：Python 相关问题加载 `python-runtime` 技能；
其他（系统工具如 poppler / tesseract、容器 / WSL）加载 `dev-environment-setup` 技能。
For more detailed environment setup help: load the `python-runtime` skill for Python issues;
load the `dev-environment-setup` skill for everything else (system tools like poppler / tesseract, containers / WSL).
### Python 包依赖
### Python Package Dependencies
本技能依赖以下 Python 包（按需检测）：
This skill depends on the following Python packages (checked on demand):
- `pypdf` — PDF 基础操作（读取、合并、拆分、旋转）
- `pdfplumber` — 表格提取、带布局的文本提取
- `Pillow` — 图片处理（水印、验证图等）
- `reportlab` — PDF 创建（可选，按需安装）
- `pdf2image` — PDF 转图片（可选，需要 poppler）
- `pypdf` — Basic PDF operations (read, merge, split, rotate)
- `pdfplumber` — Table extraction, layout-aware text extraction
- `Pillow` — Image processing (watermarks, verification images, etc.)
- `reportlab` — PDF creation (optional, install on demand)
- `pdf2image` — PDF-to-image conversion (optional, requires poppler)
核心包检测：
Core package check:
```bash
python3 -c "import pypdf; import pdfplumber; import PIL" 2>/dev/null || echo "MISSING"
```
缺失时告知用户安装：`pip install pypdf pdfplumber Pillow`
If missing, tell the user to install: `pip install pypdf pdfplumber Pillow`
## Output Rule
When you create or modify a .pdf file, you **MUST** tell the user the absolute path of the output file in your response. Example: "文件已保存到：`/path/to/output.pdf`"
When you create or modify a .pdf file, you **MUST** tell the user the absolute path of the output file in your response. Example: "File saved to: `/path/to/output.pdf`"
## Overview