用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/xberg-io/xberg --skill format-specific-extraction命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Cargo feature flags for crates/xberg — ORT-incompatible targets (WASM, Android x86_64 emulator), type-only and tract inference companion features, WASM/Android-safe variants, PDF backend, mutually-exclusive ORT variants, platform-conditional deps, aggregate feature sets, and build profiles. Load when adding, wiring, or debugging a Cargo feature, or when reasoning about what compiles on WASM/Android/Windows/macOS-intel targets.
Use when extracting from many files at once with shared config, bounded parallelism, per-file overrides, and error recovery. Covers the `batch` command, `--file-configs`, `--max-concurrent`, and output layout.
Use when splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers, tokenizer-based sizing, and the standalone `chunk` command.
基于 SOC 职业分类
正在显示 SKILL.md
| name | format-specific-extraction |
| description | Format-specific document extraction workflows |
| priority | high |
ZIP archive → Security validation → XML parsing → Text + tables + metadata
ZipBombValidator::new(limits).validate(&mut archive)?word/document.xml, ppt/slides/*.xml, content.xml)quick-xml::Reader (streaming) + DepthValidator + StringGrowthValidatorcrate::extraction::office_metadata::extract_metadata()extractors/docx.rs, extractors/pptx.rs, extractors/odt.rsBytes → pdf_oxide → Per-page text + OCR fallback → Tables → Metadata
pdf_oxide::PdfDocument::from_bytes(content)?config.force_ocr || !has_searchable_text()config.pages enabled#[cfg(feature = "pdf")]extractors/pdf/mod.rsValidate → Extract metadata → Extract plaintext files only
ZipBombValidator BEFORE any extractionbuild_archive_result() helperextractors/archive.rs, extraction/archive/*.rsDetect format from MIME → Parse → Pretty-print → Metadata
Single StructuredExtractor handles multiple MIME types. Parse with format-specific library, pretty-print to text.
See: extractors/structured.rs
Parse headers → Extract body (text/html) → Process attachments
See: extraction/email.rs, extractors/email.rs
| Helper | Location | Purpose |
|---|---|---|
office_metadata::extract_metadata() | extraction/office.rs | Office XML metadata |
cells_to_markdown() | extraction/mod.rs | Convert cell grid to GFM table |
build_archive_result() | extraction/archive/mod.rs | Standard archive result |
EXT_TO_MIME in core/mime.rsDocumentExtractor traitsupported_mime_types() and priority() (default: 50)extractors/mod.rs → register_default_extractors()#[cfg(feature = "my-format")]