菜单
Processes documents through case.dev OCR for text and table extraction. Supports PDF and image files up to 500MB with page-level and word-level output. Use when the user mentions "OCR", "text extraction", "scan document", "digitize", "extract text from PDF", or needs word-level positional data from documents.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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/lev-os/agents --skill ocr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。
Routes adaptive multi-agent deliberation with fractal context cycles. Use when using /cdo, think/deep/debug/parliament work, or long runs paired with autoresearch scheduling.
Use when you need an evidence-first provenance report from `cass`, repo docs, `.lev`, `~/.agents/diagrams`, `qmd`, or Grep/Glob tools.
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions, high fan-out, refactor candidates, code quality audit, graph query syntax, Cypher query examples, edge types, how to use search_graph.
基于 SOC 职业分类
正在显示 SKILL.md
| name | ocr |
| description | Processes documents through case.dev OCR for text and table extraction. Supports PDF and image files up to 500MB with page-level and word-level output. Use when the user mentions "OCR", "text extraction", "scan document", "digitize", "extract text from PDF", or needs word-level positional data from documents. |
Production-grade document OCR with table extraction and word-level positional data. Processes PDFs and images (PNG, JPG, TIFF, BMP, WEBP) up to 500MB.
Requires the casedev CLI. See setup skill for installation and auth.
casedev ocr process --document-url "https://example.com/contract.pdf" --json
Flags: --document-url (required), --document-id (optional tag), --engine (override).
Returns a job ID and initial status.
casedev ocr status JOB_ID --json
Statuses: queued -> processing -> completed or failed.
casedev ocr watch JOB_ID --json
Flags: --interval (default: 3s), --timeout (default: 900s).
casedev ocr words --vault VAULT_ID --object OBJECT_ID --json
Requires the document to be in a vault with completed OCR ingestion.
Flags: --page (specific page), --word-start, --word-end (index range).
Returns per-page word arrays with text, word index, and confidence scores.
# 1. Upload (triggers automatic ingestion + OCR)
casedev vault object upload ./scanned-contract.pdf --vault VAULT_ID --json
# 2. Check ingestion status
casedev vault object list --vault VAULT_ID --json
# 3. Get word-level data
casedev ocr words --vault VAULT_ID --object OBJECT_ID --json
casedev ocr process --document-url "https://storage.example.com/doc.pdf" --json
casedev ocr watch JOB_ID --json
"Invalid file type for OCR": Only PDFs and images supported. Check content type with casedev vault object list.
Job stuck in "processing": Increase timeout with --timeout 1800. Large documents (100+ pages) take longer.
"OCR job failed": Document may be corrupted or unsupported. Re-upload and retry.