{"id":"4f189f61-c2d7-4bbf-b1b2-c74358631607","entityType":"agent","slug":"clawhub-ankylala-docpilot","name":"智能文档助手","canonicalUrl":"https://www.xpersona.co/agent/clawhub-ankylala-docpilot","canonicalPath":"/agent/clawhub-ankylala-docpilot","generatedAt":"2026-10-11T16:00:35.401Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T13:05:41.105Z","emptyReason":null},"description":"智能文档处理专家，支持文档解析、信息抽取、文档分类 Skill: 智能文档助手 Owner: ankylala Summary: 智能文档处理专家，支持文档解析、信息抽取、文档分类 Tags: latest:2.0.4 Version history: v2.0.4 | 2026-04-24T16:11:18.455Z | user - Version bump from 2.0.0 to 2.0.4 - No file or documentation changes detected in this release v2.0.3 | 2026-04-24T15:50:28.782Z | user - Enhanced documentation describing DocPilot’s high-precision document parsing, extraction, and classification capabilities. - Detailed explan","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s1749k021s8ehj82qtdwad7emn841bhy:docpilot","sourceUrl":"https://clawhub.ai/ankylala/docpilot","homepage":"https://clawhub.ai/ankylala/skills/docpilot","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/ankylala/docpilot","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/ankylala/skills/docpilot","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"智能文档处理专家，支持文档解析、信息抽取、文档分类 Skill: 智能文档助手 Owner: ankylala Summary: 智能文档处理专家，支持文档解析、信息抽取、文档分类 Tags: latest:2.0.4 Version history: v2.0.4 | 2026-04-24T16:11:18.455Z"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T13:05:41.105Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T13:05:41.105Z","emptyReason":null},"stars":null,"forks":null,"downloads":1060,"packageName":null,"latestVersion":"2.0.4","tractionLabel":"1.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T13:05:41.050Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T13:05:41.105Z","lastCrawledAt":"2026-10-11T13:05:41.050Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T13:05:41.050Z","lastVerifiedAt":null,"highlights":[{"version":"2.0.4","createdAt":"2026-04-24T16:11:18.455Z","changelog":"- Version bump from 2.0.0 to 2.0.4 - No file or documentation changes detected in this release","fileCount":13,"zipByteSize":18619},{"version":"2.0.3","createdAt":"2026-04-24T15:50:28.782Z","changelog":"- Enhanced documentation describing DocPilot’s high-precision document parsing, extraction, and classification capabilities. - Detailed explanation of three core abilities and six unique advantages, including evidence tracing, hybrid document segmentation, seal detection, cross-page table merging, handwritten text recognition, and full-format support. - Expanded usage guides for all core commands (parse, extract, classify) with clear parameter tables and examples. - Added configuration instructions (via environment variables or config file). - Included sample outputs, typical application scenarios, error codes, and dependency information.","fileCount":12,"zipByteSize":17209}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1749k021s8ehj82qtdwad7emn841bhy:docpilot","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ankylala-docpilot/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ankylala-docpilot/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ankylala-docpilot/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ankylala-docpilot/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ankylala-docpilot/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-ankylala-docpilot/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T16:00:35.400Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ankylala-docpilot/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ankylala-docpilot/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ankylala-docpilot/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ankylala-docpilot/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T13:05:41.105Z","emptyReason":null},"readme":"Skill: 智能文档助手\n\nOwner: ankylala\n\nSummary: 智能文档处理专家，支持文档解析、信息抽取、文档分类\n\nTags: latest:2.0.4\n\nVersion history:\n\nv2.0.4 | 2026-04-24T16:11:18.455Z | user\n\n- Version bump from 2.0.0 to 2.0.4\n- No file or documentation changes detected in this release\n\nv2.0.3 | 2026-04-24T15:50:28.782Z | user\n\n- Enhanced documentation describing DocPilot’s high-precision document parsing, extraction, and classification capabilities.\n- Detailed explanation of three core abilities and six unique advantages, including evidence tracing, hybrid document segmentation, seal detection, cross-page table merging, handwritten text recognition, and full-format support.\n- Expanded usage guides for all core commands (parse, extract, classify) with clear parameter tables and examples.\n- Added configuration instructions (via environment variables or config file).\n- Included sample outputs, typical application scenarios, error codes, and dependency information.\n\nArchive index:\n\nArchive v2.0.4: 13 files, 18619 bytes\n\nFiles: clawhub.yaml (3686b), config.example.json (87b), config.json (76b), extract_schema.json (128b), icon.svg (2649b), index.py (15865b), README_zh.md (7505b), README.md (8182b), requirements.txt (17b), skill-card.md (2499b), SKILL.md (6252b), test_schema.json (438b), _meta.json (127b)\n\nFile v2.0.4:SKILL.md\n\n---\nname: DocPilot\ndescription: 智能文档处理专家，支持文档解析、信息抽取、文档分类\nversion: 2.0.0\nauthor: TokenAI\ntags:\n  - pdf\n  - document\n  - extraction\n  - ocr\n  - table\n  - parser\n  - classify\ncommands:\n  - parse\n  - extract\n  - classify\n---\n\n# DocPilot — 智能文档处理专家\n\n高精度文档处理技能，支持文档解析、信息抽取、文档分类。\n\n## 为什么选择 DocPilot？\n\n### 三层能力 + 六大核心优势\n\n**三层能力**\n1. **解析** — 高精度识别文档内容，保留版面结构\n2. **抽取** — 按需求提取关键字段，每条结果都能溯源到原文位置\n3. **分类** — 自动识别文档类型，混合文档也能自动切分\n\n**六大核心优势**\n\n#### 1. 证据溯源 — 每个字段都有\"身份证\" ⭐ 独家\n```json\n{\n  \"key\": \"合同金额\",\n  \"value\": \"¥1,200,000\",\n  \"confidence\": \"high\",\n  \"evidence\": [{\n    \"text\": \"合同总金额：¥1,200,000\",\n    \"page\": 2,\n    \"quad\": [[120, 350], [480, 350], [480, 380], [120, 380]]\n  }]\n}\n```\n> 审计、法务、财务场景必备 — 知道数据从哪来，才能相信数据是对的。\n\n#### 2. 混合文档切分 — 一份文件，多种类型 ⭐ 独家\n上传一份包含\"合同+发票+报价单\"的混合文件，自动识别边界并逐段分类。\n\n#### 3. 印章检测 — 公章/签名章/骑缝章自动识别 ⭐ 独家\n自动检测文档中的印章和签章，返回位置和类型信息，适用于合同审查、资质验证。\n\n#### 4. 跨页表格合并 — 断裂表格智能还原 ⭐ 独家\n自动识别跨页断裂的表格，智能合并表头和表体，输出完整结构。\n\n#### 5. 手写字体识别 — 印刷+手写混合识别 ⭐ 独家\n支持印刷体和手写体混合识别，覆盖表单填写、手写批注、签字确认等场景。\n\n#### 6. 全格式支持 — 一个技能全部搞定\nPDF · 图片 · Word · Excel · CSV — 无需组合多个工具。\n\n---\n\n## 命令\n\n### 解析文档\n```\nDocPilot parse <文件路径> [选项]\n```\n\n示例：\n```\nDocPilot parse C:\\docs\\report.pdf\nDocPilot parse C:\\docs\\scan.jpg --output markdown\nDocPilot parse C:\\docs\\data.xlsx\nDocPilot parse C:\\docs\\contract.pdf --seal --bbox\n```\n\n### 信息抽取\n```\nDocPilot extract <文件路径> --schema <JSON>\n```\n\n示例：\n```\nDocPilot extract C:\\docs\\contract.pdf --schema \"{\\\"fields\\\":[{\\\"key\\\":\\\"甲方\\\",\\\"type\\\":\\\"string\\\"},{\\\"key\\\":\\\"乙方\\\",\\\"type\\\":\\\"string\\\"}]}\"\nDocPilot extract C:\\docs\\invoice.pdf --schema schema.json\n```\n\n### 文档分类\n```\nDocPilot classify <文件路径> [选项]\n```\n\n示例：\n```\nDocPilot classify C:\\docs\\mixed.pdf\nDocPilot classify C:\\docs\\docs.pdf --mode classify_and_split --categories \"[{\\\"name\\\":\\\"合同\\\",\\\"description\\\":\\\"合同协议\\\"},{\\\"name\\\":\\\"发票\\\",\\\"description\\\":\\\"发票单据\\\"}]\"\n```\n\n---\n\n## 参数说明\n\n### parse 命令\n\n| 参数 | 说明 | 示例 |\n|------|------|------|\n| 文件路径 | PDF/图片/Word/Excel 文件路径 | `C:\\docs\\report.pdf` |\n| --output | 输出格式 (structured/markdown/text) | `--output markdown` |\n| --layout | 启用版面分析 | `--layout` |\n| --table | 启用表格识别（含跨页合并） | `--table` |\n| --seal | 启用印章识别 | `--seal` |\n| --dpi | DPI (72/144/200/216) | `--dpi 200` |\n| --pages | 页码范围 | `--pages 1-5,8,10-12` |\n| --bbox | 包含边界框坐标 | `--bbox` |\n| --normalize | 返回格式化解析数据 (默认开启) | `--normalize` |\n| --raw | 返回原始解析格式 | `--raw` |\n| --include-image | markdown 中包含图片 | `--include-image` |\n| --image-format | 图片格式 (url/base64) | `--image-format url` |\n\n### extract 命令\n\n| 参数 | 说明 | 示例 |\n|------|------|------|\n| 文件路径 | 文档文件路径 | `C:\\docs\\contract.pdf` |\n| --schema | 字段 schema（必填） | `--schema '{\"fields\":[...]}'` |\n| --prompt | 提示词模式 schema | `--prompt '{\"fields\":[...]}'` |\n| --schema-ref | 模板引用 | `--schema-ref DocPilot/contract/v1` |\n| --options | 扩展配置 | `--options '{\"mode\":\"fast\"}'` |\n\n### classify 命令\n\n| 参数 | 说明 | 示例 |\n|------|------|------|\n| 文件路径 | 文档文件路径 | `C:\\docs\\mixed.pdf` |\n| --mode | 分类模式 | `--mode classify_and_split` |\n| --categories | 分类 schema | `--categories '[{\"name\":\"合同\",\"description\":\"...\"}]'` |\n\n---\n\n## 配置\n\n### 方式一：环境变量\n```\nDOCPilot_BASE_URL=https://docpilot.token-ai.com.cn\nDOCPilot_API_KEY=your_api_key\n```\n\n### 方式二：配置文件\n在技能目录创建 `config.json`：\n```json\n{\n  \"base_url\": \"https://docpilot.token-ai.com.cn\",\n  \"api_key\": \"your_api_key\"\n}\n```\n\n---\n\n## 输出格式\n\n### parse 输出\n- **document_id**: 文档唯一标识\n- **page_count**: 页数\n- **file_type**: 文件类型\n- **pages**: 页面数组（含 elements）\n- **sheets**: 工作表数组（Excel/CSV）\n- **markdown**: Markdown 格式文本\n\n### extract 输出\n- **extraction_id**: 抽取任务 ID\n- **fields**: 提取的字段列表（含 evidence 溯源）\n- **unfound_fields**: 未找到的字段\n- **metadata**: 元数据（耗时、token 数等）\n\n### classify 输出\n- **mode**: 分类模式\n- **classification**: 分类结果（classify_only 模式）\n- **segments**: 文档片段列表（classify_and_split 模式）\n- **metadata**: 元数据\n\n---\n\n## 典型应用场景\n\n| 场景 | 使用方式 | 核心能力 |\n|------|----------|----------|\n| **合同审查** | 抽取关键字段 + 印章检测 | 证据溯源 + 印章识别 |\n| **财务审计** | 跨页表格合并 + 字段抽取 | 跨页合并 + 溯源 |\n| **档案整理** | 混合文档自动分类切分 | 文档分类 |\n| **招投标文件** | 识别报价单/资质/方案并分别处理 | 文档分类 + 解析 |\n| **表单处理** | 手写内容识别 + 结构化抽取 | 手写识别 + 信息抽取 |\n| **合规检查** | 检测印章、签章，验证文档完整性 | 印章检测 |\n\n---\n\n## 依赖\n- requests\n\n## 错误码\n\n| 错误码 | 消息 | 说明 |\n|--------|------|------|\n| 10000 | Success | 成功 |\n| 10001 | Missing parameter | 参数缺失 |\n| 10002 | Invalid parameter | 非法参数 |\n| 10003 | Invalid file | 文件格式非法 |\n| 10004 | Failed to recognize | 识别失败 |\n| 10005 | Internal error | 内部错误 |\n\nFile v2.0.4:README.md\n\n# DocPilot — Intelligent Document Processing Expert\n\n> OpenClaw Skill - Document Parsing, Information Extraction, and Classification\n\nExtract structured data from PDF, images, Word, and Excel documents. Perform field extraction and document classification.\n\n## Why Choose DocPilot?\n\n### Three-Layer Capabilities + Six Core Advantages\n\n**Three-Layer Capabilities**\n1. **Parse** — High-precision document content recognition with layout preservation\n2. **Extract** — Extract key fields with evidence tracing back to original positions\n3. **Classify** — Auto-identify document types, split mixed documents automatically\n\n**Six Core Advantages**\n\n#### 1. Evidence Tracing — Every Field Has an \"ID Card\" ⭐ Exclusive\n```json\n{\n  \"key\": \"Contract Amount\",\n  \"value\": \"¥1,200,000\",\n  \"confidence\": \"high\",\n  \"evidence\": [{\n    \"text\": \"Total Contract Amount: ¥1,200,000\",\n    \"page\": 2,\n    \"quad\": [[120, 350], [480, 350], [480, 380], [120, 380]]\n  }]\n}\n```\n> Essential for audit, legal, and finance — know where data comes from to trust it.\n\n#### 2. Mixed Document Splitting — One File, Multiple Types ⭐ Exclusive\nUpload a mixed file containing \"contract + invoice + quotation\", auto-identify boundaries and classify segment by segment.\n\n#### 3. Seal Detection — Official/Signature/Cross-page Seals ⭐ Exclusive\nAuto-detect seals and stamps in documents, return position and type info. Ideal for contract review and qualification verification.\n\n#### 4. Cross-page Table Merging — Smart Reconstruction ⭐ Exclusive\nAuto-identify tables split across pages, intelligently merge headers and bodies, output complete structures.\n\n#### 5. Handwriting Recognition — Print + Handwriting Mixed ⭐ Exclusive\nSupport mixed recognition of printed and handwritten text. Covers form filling, handwritten annotations, and signature confirmation.\n\n#### 6. Full Format Support — One Skill Does It All\nPDF · Images · Word · Excel · CSV — No need to combine multiple tools.\n\n---\n\n## Features\n\n- ✅ **Multi-format Support**: PDF, Images (JPG/PNG), Word, Excel, CSV\n- ✅ **Layout Analysis**: Automatically detect and structure document elements\n- ✅ **Table Recognition**: Extract tables with HTML and Markdown outputs, cross-page merge\n- ✅ **Information Extraction**: Extract structured fields with evidence tracing\n- ✅ **Document Classification**: Single document or mixed document classification & splitting\n- ✅ **Seal Detection**: Detect stamps and seals in documents\n- ✅ **Handwriting Recognition**: Print + handwriting mixed recognition\n- ✅ **Multiple Output Formats**: structured JSON, markdown, plain text\n\n---\n\n## Quick Start\n\n### Installation\n\n```bash\n# Install via ClawHub\nopenclaw skills install DocPilot\n\n# Or manual installation (local development)\ncd E:\\skills\\document-parser\npip install -r requirements.txt\n```\n\n### Configuration\n\n**Option 1: Environment Variables**\n```bash\n# Windows PowerShell\n$env:DOCPilot_BASE_URL=\"https://docpilot.token-ai.com.cn\"\n$env:DOCPilot_API_KEY=\"your_api_key\"\n```\n\n**Option 2: Configuration File**\n```bash\ncd E:\\skills\\DocPilot\ncopy config.example.json config.json\n# Edit config.json with your API endpoint and API key\n```\n\n**Option 2: Configuration File**\n```bash\ncd E:\\skills\\document-parser\ncopy config.example.json config.json\n# Edit config.json with your API endpoint\n```\n\n### Usage\n\n#### Parse a Document\n```bash\n# Basic parsing\nDocPilot parse \"C:\\docs\\report.pdf\"\n\n# Markdown output\nDocPilot parse \"C:\\docs\\scan.jpg\" --output markdown\n\n# Enable seal detection and bbox\nDocPilot parse \"C:\\docs\\contract.pdf\" --seal --bbox\n\n# Parse Excel\nDocPilot parse \"C:\\docs\\data.xlsx\"\n```\n\n#### Extract Information\n```bash\n# Extract fields with schema\nDocPilot extract \"C:\\docs\\contract.pdf\" --schema \"{\\\"fields\\\":[{\\\"key\\\":\\\"Party A\\\",\\\"type\\\":\\\"string\\\"},{\\\"key\\\":\\\"Party B\\\",\\\"type\\\":\\\"string\\\"}]}\"\n\n# Extract with schema file\nDocPilot extract \"C:\\docs\\invoice.pdf\" --schema schema.json\n```\n\n#### Classify Document\n```bash\n# Single document classification\nDocPilot classify \"C:\\docs\\doc.pdf\"\n\n# Mixed document classification and splitting\nDocPilot classify \"C:\\docs\\mixed.pdf\" --mode classify_and_split --categories \"[{\\\"name\\\":\\\"Contract\\\",\\\"description\\\":\\\"Contract agreement\\\"},{\\\"name\\\":\\\"Invoice\\\",\\\"description\\\":\\\"Invoice document\\\"}]\"\n```\n\n---\n\n## Parameters\n\n### parse Command\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| file | string | Yes | PDF/Image/Word/Excel file path |\n| --output | string | No | Output format: structured/markdown/text |\n| --layout | flag | No | Enable layout analysis |\n| --table | flag | No | Enable table recognition (incl. cross-page merge) |\n| --seal | flag | No | Enable seal recognition |\n| --dpi | int | No | DPI: 72/144/200/216 |\n| --pages | string | No | Page range, e.g., \"1-5,8,10-12\" |\n| --bbox | flag | No | Include bbox coordinates |\n| --normalize | flag | No | Return formatted parsed data (default: on) |\n| --raw | flag | No | Return raw parsed format |\n| --include-image | flag | No | Include images in markdown |\n| --image-format | string | No | Image format: url/base64 |\n\n### extract Command\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| file | string | Yes | Document file path |\n| --schema | JSON | Yes | Field schema definition |\n| --prompt | JSON | No | Prompt mode schema |\n| --schema-ref | string | No | Schema reference template |\n| --options | JSON | No | Extended options |\n\n### classify Command\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| file | string | Yes | Document file path |\n| --mode | string | No | classify_only / classify_and_split |\n| --categories | JSON | No | Category schema definition |\n\n---\n\n## Output Format\n\n### parse Response\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"document_id\": \"dp-8a3f-xxxx\",\n    \"page_count\": 25,\n    \"file_type\": \"pdf\",\n    \"pages\": [...],\n    \"markdown\": \"...\"\n  }\n}\n```\n\n### extract Response\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"extraction_id\": \"ext-xxxx\",\n    \"fields\": [\n      {\n        \"key\": \"Party A\",\n        \"value\": \"ABC Company\",\n        \"confidence\": \"high\",\n        \"evidence\": [...]\n      }\n    ],\n    \"unfound_fields\": [],\n    \"metadata\": {...}\n  }\n}\n```\n\n### classify Response\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"mode\": \"classify_only\",\n    \"classification\": {\n      \"category\": \"Contract\",\n      \"confidence\": 0.95,\n      \"reasoning\": \"...\"\n    },\n    \"metadata\": {...}\n  }\n}\n```\n\n---\n\n## Supported Document Elements\n\n| Type | Description |\n|------|-------------|\n| DocumentTitle | Document title |\n| LevelTitle | Section heading |\n| Paragraph | Text paragraph |\n| Table | Table (with cross-page merge) |\n| Image | Image |\n| Seal | Seal/Stamp |\n| FigureTitle | Figure title |\n| Handwriting | Handwritten text |\n\n---\n\n## Typical Use Cases\n\n| Scenario | Usage | Core Capability |\n|----------|-------|-----------------|\n| **Contract Review** | Extract key fields + seal detection | Evidence tracing + Seal recognition |\n| **Financial Audit** | Cross-page table merge + field extraction | Cross-page merge + Tracing |\n| **Archive Organization** | Mixed document auto-classification & splitting | Document classification |\n| **Bidding Documents** | Identify quotations/qualifications/proposals separately | Classification + Parsing |\n| **Form Processing** | Handwriting recognition + structured extraction | Handwriting + Extraction |\n| **Compliance Check** | Detect seals, verify document integrity | Seal detection |\n\n---\n\n## Error Codes\n\n| Code | Message | Description |\n|------|---------|-------------|\n| 10000 | Success | Successful |\n| 10001 | Missing parameter | Missing required parameter |\n| 10002 | Invalid parameter | Invalid parameter value |\n| 10003 | Invalid file | Unsupported file format |\n| 10004 | Failed to recognize | Recognition failed |\n| 10005 | Internal error | Internal server error |\n\n---\n\n## Dependencies\n\n- Python 3.8+\n- requests>=2.28.0\n\n---\n\n## License\n\nMIT License\n\n---\n\n## Support\n\nFile an issue or contact TokenAI for help.\n\nFile v2.0.4:_meta.json\n\n{\n  \"ownerId\": \"kn7ewjb6a59zsr2zz60ky1wrzx82gdqg\",\n  \"slug\": \"docpilot\",\n  \"version\": \"2.0.4\",\n  \"publishedAt\": 1777047078455\n}\n\nFile v2.0.4:README_zh.md\n\n# DocPilot — 智能文档处理专家\n\n> OpenClaw Skill - 高精度文档解析、信息抽取、文档分类\n\n从 PDF、图片、Word、Excel 文档中提取结构化数据，支持信息抽取和文档分类。\n\n## 为什么选择 DocPilot？\n\n### 三层能力 + 六大核心优势\n\n**三层能力**\n1. **解析** — 高精度识别文档内容，保留版面结构\n2. **抽取** — 按需求提取关键字段，每条结果都能溯源到原文位置\n3. **分类** — 自动识别文档类型，混合文档也能自动切分\n\n**六大核心优势**\n\n#### 1. 证据溯源 — 每个字段都有\"身份证\" ⭐ 独家\n```json\n{\n  \"key\": \"合同金额\",\n  \"value\": \"¥1,200,000\",\n  \"confidence\": \"high\",\n  \"evidence\": [{\n    \"text\": \"合同总金额：¥1,200,000\",\n    \"page\": 2,\n    \"quad\": [[120, 350], [480, 350], [480, 380], [120, 380]]\n  }]\n}\n```\n> 审计、法务、财务场景必备 — 知道数据从哪来，才能相信数据是对的。\n\n#### 2. 混合文档切分 — 一份文件，多种类型 ⭐ 独家\n上传一份包含\"合同+发票+报价单\"的混合文件，自动识别边界并逐段分类。\n\n#### 3. 印章检测 — 公章/签名章/骑缝章自动识别 ⭐ 独家\n自动检测文档中的印章和签章，返回位置和类型信息，适用于合同审查、资质验证。\n\n#### 4. 跨页表格合并 — 断裂表格智能还原 ⭐ 独家\n自动识别跨页断裂的表格，智能合并表头和表体，输出完整结构。\n\n#### 5. 手写字体识别 — 印刷+手写混合识别 ⭐ 独家\n支持印刷体和手写体混合识别，覆盖表单填写、手写批注、签字确认等场景。\n\n#### 6. 全格式支持 — 一个技能全部搞定\nPDF · 图片 · Word · Excel · CSV — 无需组合多个工具。\n\n---\n\n## 功能特性\n\n- ✅ **多格式支持**: PDF、图片 (JPG/PNG)、Word、Excel、CSV\n- ✅ **版面分析**: 自动检测和解析文档结构元素\n- ✅ **表格识别**: 提取表格并输出 HTML 和 Markdown 格式，支持跨页合并\n- ✅ **信息抽取**: 按 schema 提取结构化字段，带证据溯源\n- ✅ **文档分类**: 单文档分类或混合文档切分分类\n- ✅ **印章检测**: 检测文档中的印章和签章\n- ✅ **手写识别**: 印刷体+手写体混合识别\n- ✅ **多种输出格式**: structured JSON、markdown、纯文本\n\n---\n\n## 快速开始\n\n### 安装\n\n```bash\n# 通过 ClawHub 安装\nopenclaw skills install DocPilot\n\n# 或手动安装（本地开发）\ncd E:\\skills\\document-parser\npip install -r requirements.txt\n```\n\n### 配置\n\n**方式一：环境变量**\n```bash\n# Windows PowerShell\n$env:DOCPilot_BASE_URL=\"https://docpilot.token-ai.com.cn\"\n$env:DOCPilot_API_KEY=\"your_api_key\"\n```\n\n**方式二：配置文件**\n```bash\ncd E:\\skills\\DocPilot\ncopy config.example.json config.json\n# 编辑 config.json 填入你的 API 地址和 API Key\n```\n\n**方式二：配置文件**\n```bash\ncd E:\\skills\\document-parser\ncopy config.example.json config.json\n# 编辑 config.json 填入你的 API 地址\n```\n\n### 使用方法\n\n#### 解析文档\n```bash\n# 基础解析\nDocPilot parse \"C:\\docs\\report.pdf\"\n\n# Markdown 输出\nDocPilot parse \"C:\\docs\\scan.jpg\" --output markdown\n\n# 启用印章检测和边界框\nDocPilot parse \"C:\\docs\\contract.pdf\" --seal --bbox\n\n# 解析 Excel\nDocPilot parse \"C:\\docs\\data.xlsx\"\n```\n\n#### 信息抽取\n```bash\n# 按 schema 抽取字段\nDocPilot extract \"C:\\docs\\contract.pdf\" --schema \"{\\\"fields\\\":[{\\\"key\\\":\\\"甲方\\\",\\\"type\\\":\\\"string\\\"},{\\\"key\\\":\\\"乙方\\\",\\\"type\\\":\\\"string\\\"}]}\"\n\n# 使用 schema 文件\nDocPilot extract \"C:\\docs\\invoice.pdf\" --schema schema.json\n```\n\n#### 文档分类\n```bash\n# 单文档分类\nDocPilot classify \"C:\\docs\\doc.pdf\"\n\n# 混合文档分类和切分\nDocPilot classify \"C:\\docs\\mixed.pdf\" --mode classify_and_split --categories \"[{\\\"name\\\":\\\"合同\\\",\\\"description\\\":\\\"合同协议\\\"},{\\\"name\\\":\\\"发票\\\",\\\"description\\\":\\\"发票单据\\\"}]\"\n```\n\n---\n\n## 参数说明\n\n### parse 命令\n\n| 参数 | 类型 | 必填 | 说明 |\n|------|------|------|------|\n| file | string | 是 | PDF/图片/Word/Excel 文件路径 |\n| --output | string | 否 | 输出格式：structured/markdown/text |\n| --layout | flag | 否 | 启用版面分析 |\n| --table | flag | 否 | 启用表格识别（含跨页合并） |\n| --seal | flag | 否 | 启用印章检测 |\n| --dpi | int | 否 | DPI：72/144/200/216 |\n| --pages | string | 否 | 页码范围，如 \"1-5,8,10-12\" |\n| --bbox | flag | 否 | 包含边界框坐标 |\n| --normalize | flag | 否 | 返回格式化解析数据（默认开启） |\n| --raw | flag | 否 | 返回原始解析格式 |\n| --include-image | flag | 否 | markdown 中包含图片 |\n| --image-format | string | 否 | 图片格式：url/base64 |\n\n### extract 命令\n\n| 参数 | 类型 | 必填 | 说明 |\n|------|------|------|------|\n| file | string | 是 | 文档文件路径 |\n| --schema | JSON | 是 | 字段 schema 定义 |\n| --prompt | JSON | 否 | 提示词模式 schema |\n| --schema-ref | string | 否 | 模板引用 |\n| --options | JSON | 否 | 扩展配置 |\n\n### classify 命令\n\n| 参数 | 类型 | 必填 | 说明 |\n|------|------|------|------|\n| file | string | 是 | 文档文件路径 |\n| --mode | string | 否 | classify_only / classify_and_split |\n| --categories | JSON | 否 | 分类 schema 定义 |\n\n---\n\n## 输出格式\n\n### parse 响应\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"document_id\": \"dp-8a3f-xxxx\",\n    \"page_count\": 25,\n    \"file_type\": \"pdf\",\n    \"pages\": [...],\n    \"markdown\": \"...\"\n  }\n}\n```\n\n### extract 响应\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"extraction_id\": \"ext-xxxx\",\n    \"fields\": [\n      {\n        \"key\": \"甲方\",\n        \"value\": \"某某公司\",\n        \"confidence\": \"high\",\n        \"evidence\": [...]\n      }\n    ],\n    \"unfound_fields\": [],\n    \"metadata\": {...}\n  }\n}\n```\n\n### classify 响应\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"mode\": \"classify_only\",\n    \"classification\": {\n      \"category\": \"合同\",\n      \"confidence\": 0.95,\n      \"reasoning\": \"...\"\n    },\n    \"metadata\": {...}\n  }\n}\n```\n\n---\n\n## 支持的文档元素\n\n| 类型 | 说明 |\n|------|------|\n| DocumentTitle | 文档标题 |\n| LevelTitle | 层级标题 |\n| Paragraph | 段落 |\n| Table | 表格（支持跨页合并） |\n| Image | 图片 |\n| Seal | 印章 |\n| FigureTitle | 图表标题 |\n| Handwriting | 手写文字 |\n\n---\n\n## 典型应用场景\n\n| 场景 | 使用方式 | 核心能力 |\n|------|----------|----------|\n| **合同审查** | 抽取关键字段 + 印章检测 | 证据溯源 + 印章识别 |\n| **财务审计** | 跨页表格合并 + 字段抽取 | 跨页合并 + 溯源 |\n| **档案整理** | 混合文档自动分类切分 | 文档分类 |\n| **招投标文件** | 识别报价单/资质/方案并分别处理 | 文档分类 + 解析 |\n| **表单处理** | 手写内容识别 + 结构化抽取 | 手写识别 + 信息抽取 |\n| **合规检查** | 检测印章、签章，验证文档完整性 | 印章检测 |\n\n---\n\n## 错误码\n\n| 错误码 | 消息 | 说明 |\n|--------|------|------|\n| 10000 | Success | 成功 |\n| 10001 | Missing parameter | 参数缺失 |\n| 10002 | Invalid parameter | 非法参数 |\n| 10003 | Invalid file | 文件格式非法 |\n| 10004 | Failed to recognize | 识别失败 |\n| 10005 | Internal error | 内部错误 |\n\n---\n\n## 依赖\n\n- Python 3.8+\n- requests>=2.28.0\n\n---\n\n## 许可证\n\nMIT License\n\n---\n\n## 支持\n\n如有问题请提交 Issue 或联系 TokenAI。\n\nFile v2.0.4:skill-card.md\n\n## Description:\n\n智能文档处理专家，支持文档解析、信息抽取、文档分类。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[ankylala](https://clawhub.ai/user/ankylala)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to parse PDFs, images, Word, Excel, and CSV files, extract structured fields with source evidence, and classify or split mixed document sets. Typical workflows include contract review, finance audits, archive organization, form processing, and compliance checks.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill uploads selected documents to the DocPilot/TokenAI service or another configured endpoint, and privacy controls are under-documented.\n\nMitigation: Use only documents approved for that external service until the publisher documents retention, deletion, jurisdiction, and privacy terms.\n\nRisk: The bundled configuration includes credential-like data and can override environment variables.\n\nMitigation: Remove bundled secrets, rotate any exposed credentials, and require deployers to provide API keys through approved secret management.\n\nRisk: The service destination is configurable, which can send document contents to an unexpected endpoint.\n\nMitigation: Restrict deployment to approved HTTPS destinations and review endpoint configuration before each release.\n\nRisk: Dependencies are not pinned.\n\nMitigation: Pin and review dependencies before production deployment.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/ankylala/skills/docpilot)\n- [DocPilot Service Endpoint](https://docpilot.token-ai.com.cn)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, configuration, guidance]\n\n**Output Format:** [JSON, Markdown, or plain text document-processing results]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Parse outputs may include document IDs, page counts, layout elements, tables, seals, bounding boxes, and markdown; extraction and classification outputs include structured fields, evidence, segments, confidence, and metadata.]\n\n## Skill Version(s):\n\n2.0.4 (source: server release evidence; source files report 2.0.0)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v2.0.4:config.example.json\n\n{\n  \"base_url\": \"https://docpilot.token-ai.com.cn\",\n  \"api_key\": \"your_api_key_here\"\n}\n\nFile v2.0.4:config.json\n\n{\n  \"base_url\": \"https://docpilot.token-ai.com.cn\",\n  \"api_key\": \"123456\"\n}\n\nFile v2.0.4:extract_schema.json\n\n{\n  \"fields\": [\n    {\n      \"key\": \"利润表\",\n      \"type\": \"string\",\n      \"description\": \"利润表相关内容\"\n    }\n  ]\n}\n\nFile v2.0.4:test_schema.json\n\n{\n  \"fields\": [\n    {\"key\": \"营业收入\", \"type\": \"string\", \"description\": \"利润表中的营业收入金额\"},\n    {\"key\": \"营业成本\", \"type\": \"string\", \"description\": \"利润表中的营业成本金额\"},\n    {\"key\": \"净利润\", \"type\": \"string\", \"description\": \"利润表中的净利润金额\"},\n    {\"key\": \"归属于母公司股东的净利润\", \"type\": \"string\", \"description\": \"归属于母公司股东的净利润\"}\n  ]\n}\n\nFile v2.0.4:clawhub.yaml\n\n# ClawHub Skill Package Configuration\n# DocPilot 文档智能处理技能 - ClawHub 发布配置\n\nname: DocPilot\nversion: 2.0.0\nauthor: TokenAI\ndescription:\n  en: Document parsing, information extraction, and document classification with high precision\n  zh: 高精度文档解析、信息抽取、文档分类\n\ncategory: tool\ntags:\n  - pdf\n  - document\n  - extraction\n  - ocr\n  - table\n  - parser\n  - classify\n  - openclaw\n\n# OpenClaw 技能入口\nentry: index.py\n\n# Python 依赖\ndependencies:\n  - requests>=2.28.0\n\n# 配置项\nconfig:\n  - name: DOCPilot_BASE_URL\n    type: string\n    required: false\n    default: https://docpilot.token-ai.com.cn\n    description:\n      en: API Base URL\n      zh: API 基础地址\n\n  - name: DOCPilot_API_KEY\n    type: string\n    required: true\n    description:\n      en: API Key for authentication (Bearer token)\n      zh: API 鉴权密钥（Bearer token）\n\n# 命令定义\ncommands:\n  - name: parse\n    description:\n      en: Parse a document (PDF/Image/Word/Excel)\n      zh: 解析文档（PDF/图片/Word/Excel）\n    usage: DocPilot parse <file_path> [options]\n    options:\n      - name: --output\n        description:\n          en: Output format (structured/markdown/text)\n          zh: 输出格式\n        value: structured|markdown|text\n      - name: --layout\n        description:\n          en: Enable layout analysis\n          zh: 启用版面分析\n      - name: --table\n        description:\n          en: Enable table recognition\n          zh: 启用表格识别\n      - name: --seal\n        description:\n          en: Enable seal recognition\n          zh: 启用印章检测\n      - name: --dpi\n        description:\n          en: DPI for PDF/image conversion\n          zh: PDF/图片转图像分辨率\n        value: 72|144|200|216\n      - name: --pages\n        description:\n          en: Page range (e.g., 1-5,8,10-12)\n          zh: 页码范围\n      - name: --bbox\n        description:\n          en: Include bbox coordinates in elements\n          zh: 包含边界框坐标\n      - name: --include-image\n        description:\n          en: Include images in markdown output\n          zh: 在 markdown 中包含图片\n      - name: --image-format\n        description:\n          en: Image format (url/base64)\n          zh: 图片格式\n        value: url|base64\n\n  - name: extract\n    description:\n      en: Extract structured fields from document\n      zh: 从文档中抽取结构化字段\n    usage: DocPilot extract <file_path> --schema <JSON>\n    options:\n      - name: --schema\n        description:\n          en: Field schema (JSON string or file path)\n          zh: 字段 schema（JSON 字符串或文件路径）\n        required: true\n      - name: --prompt\n        description:\n          en: Prompt mode schema\n          zh: 提示词模式 schema\n      - name: --schema-ref\n        description:\n          en: Schema reference template\n          zh: 模板引用\n      - name: --options\n        description:\n          en: Extended options\n          zh: 扩展配置\n\n  - name: classify\n    description:\n      en: Classify document type\n      zh: 文档分类\n    usage: DocPilot classify <file_path> [options]\n    options:\n      - name: --mode\n        description:\n          en: Classification mode\n          zh: 分类模式\n        value: classify_only|classify_and_split\n      - name: --categories\n        description:\n          en: Category schema (JSON string or file path)\n          zh: 分类 schema（JSON 字符串或文件路径）\n\n# 打包文件列表\nfiles:\n  - index.py\n  - SKILL.md\n  - requirements.txt\n  - config.example.json\n  - icon.svg\n  - README_zh.md\n  - README.md\n  - clawhub.yaml\n\n# 许可证\nlicense: MIT\n\nFile v2.0.4:requirements.txt\n\nrequests>=2.28.0\n\nArchive v2.0.3: 12 files, 17209 bytes\n\nFiles: clawhub.yaml (3686b), config.example.json (87b), config.json (76b), extract_schema.json (128b), icon.svg (2649b), index.py (15865b), README_zh.md (7505b), README.md (8182b), requirements.txt (17b), SKILL.md (6252b), test_schema.json (438b), _meta.json (127b)\n\nFile v2.0.3:SKILL.md\n\n---\nname: DocPilot\ndescription: 智能文档处理专家，支持文档解析、信息抽取、文档分类\nversion: 2.0.0\nauthor: TokenAI\ntags:\n  - pdf\n  - document\n  - extraction\n  - ocr\n  - table\n  - parser\n  - classify\ncommands:\n  - parse\n  - extract\n  - classify\n---\n\n# DocPilot — 智能文档处理专家\n\n高精度文档处理技能，支持文档解析、信息抽取、文档分类。\n\n## 为什么选择 DocPilot？\n\n### 三层能力 + 六大核心优势\n\n**三层能力**\n1. **解析** — 高精度识别文档内容，保留版面结构\n2. **抽取** — 按需求提取关键字段，每条结果都能溯源到原文位置\n3. **分类** — 自动识别文档类型，混合文档也能自动切分\n\n**六大核心优势**\n\n#### 1. 证据溯源 — 每个字段都有\"身份证\" ⭐ 独家\n```json\n{\n  \"key\": \"合同金额\",\n  \"value\": \"¥1,200,000\",\n  \"confidence\": \"high\",\n  \"evidence\": [{\n    \"text\": \"合同总金额：¥1,200,000\",\n    \"page\": 2,\n    \"quad\": [[120, 350], [480, 350], [480, 380], [120, 380]]\n  }]\n}\n```\n> 审计、法务、财务场景必备 — 知道数据从哪来，才能相信数据是对的。\n\n#### 2. 混合文档切分 — 一份文件，多种类型 ⭐ 独家\n上传一份包含\"合同+发票+报价单\"的混合文件，自动识别边界并逐段分类。\n\n#### 3. 印章检测 — 公章/签名章/骑缝章自动识别 ⭐ 独家\n自动检测文档中的印章和签章，返回位置和类型信息，适用于合同审查、资质验证。\n\n#### 4. 跨页表格合并 — 断裂表格智能还原 ⭐ 独家\n自动识别跨页断裂的表格，智能合并表头和表体，输出完整结构。\n\n#### 5. 手写字体识别 — 印刷+手写混合识别 ⭐ 独家\n支持印刷体和手写体混合识别，覆盖表单填写、手写批注、签字确认等场景。\n\n#### 6. 全格式支持 — 一个技能全部搞定\nPDF · 图片 · Word · Excel · CSV — 无需组合多个工具。\n\n---\n\n## 命令\n\n### 解析文档\n```\nDocPilot parse <文件路径> [选项]\n```\n\n示例：\n```\nDocPilot parse C:\\docs\\report.pdf\nDocPilot parse C:\\docs\\scan.jpg --output markdown\nDocPilot parse C:\\docs\\data.xlsx\nDocPilot parse C:\\docs\\contract.pdf --seal --bbox\n```\n\n### 信息抽取\n```\nDocPilot extract <文件路径> --schema <JSON>\n```\n\n示例：\n```\nDocPilot extract C:\\docs\\contract.pdf --schema \"{\\\"fields\\\":[{\\\"key\\\":\\\"甲方\\\",\\\"type\\\":\\\"string\\\"},{\\\"key\\\":\\\"乙方\\\",\\\"type\\\":\\\"string\\\"}]}\"\nDocPilot extract C:\\docs\\invoice.pdf --schema schema.json\n```\n\n### 文档分类\n```\nDocPilot classify <文件路径> [选项]\n```\n\n示例：\n```\nDocPilot classify C:\\docs\\mixed.pdf\nDocPilot classify C:\\docs\\docs.pdf --mode classify_and_split --categories \"[{\\\"name\\\":\\\"合同\\\",\\\"description\\\":\\\"合同协议\\\"},{\\\"name\\\":\\\"发票\\\",\\\"description\\\":\\\"发票单据\\\"}]\"\n```\n\n---\n\n## 参数说明\n\n### parse 命令\n\n| 参数 | 说明 | 示例 |\n|------|------|------|\n| 文件路径 | PDF/图片/Word/Excel 文件路径 | `C:\\docs\\report.pdf` |\n| --output | 输出格式 (structured/markdown/text) | `--output markdown` |\n| --layout | 启用版面分析 | `--layout` |\n| --table | 启用表格识别（含跨页合并） | `--table` |\n| --seal | 启用印章识别 | `--seal` |\n| --dpi | DPI (72/144/200/216) | `--dpi 200` |\n| --pages | 页码范围 | `--pages 1-5,8,10-12` |\n| --bbox | 包含边界框坐标 | `--bbox` |\n| --normalize | 返回格式化解析数据 (默认开启) | `--normalize` |\n| --raw | 返回原始解析格式 | `--raw` |\n| --include-image | markdown 中包含图片 | `--include-image` |\n| --image-format | 图片格式 (url/base64) | `--image-format url` |\n\n### extract 命令\n\n| 参数 | 说明 | 示例 |\n|------|------|------|\n| 文件路径 | 文档文件路径 | `C:\\docs\\contract.pdf` |\n| --schema | 字段 schema（必填） | `--schema '{\"fields\":[...]}'` |\n| --prompt | 提示词模式 schema | `--prompt '{\"fields\":[...]}'` |\n| --schema-ref | 模板引用 | `--schema-ref DocPilot/contract/v1` |\n| --options | 扩展配置 | `--options '{\"mode\":\"fast\"}'` |\n\n### classify 命令\n\n| 参数 | 说明 | 示例 |\n|------|------|------|\n| 文件路径 | 文档文件路径 | `C:\\docs\\mixed.pdf` |\n| --mode | 分类模式 | `--mode classify_and_split` |\n| --categories | 分类 schema | `--categories '[{\"name\":\"合同\",\"description\":\"...\"}]'` |\n\n---\n\n## 配置\n\n### 方式一：环境变量\n```\nDOCPilot_BASE_URL=https://docpilot.token-ai.com.cn\nDOCPilot_API_KEY=your_api_key\n```\n\n### 方式二：配置文件\n在技能目录创建 `config.json`：\n```json\n{\n  \"base_url\": \"https://docpilot.token-ai.com.cn\",\n  \"api_key\": \"your_api_key\"\n}\n```\n\n---\n\n## 输出格式\n\n### parse 输出\n- **document_id**: 文档唯一标识\n- **page_count**: 页数\n- **file_type**: 文件类型\n- **pages**: 页面数组（含 elements）\n- **sheets**: 工作表数组（Excel/CSV）\n- **markdown**: Markdown 格式文本\n\n### extract 输出\n- **extraction_id**: 抽取任务 ID\n- **fields**: 提取的字段列表（含 evidence 溯源）\n- **unfound_fields**: 未找到的字段\n- **metadata**: 元数据（耗时、token 数等）\n\n### classify 输出\n- **mode**: 分类模式\n- **classification**: 分类结果（classify_only 模式）\n- **segments**: 文档片段列表（classify_and_split 模式）\n- **metadata**: 元数据\n\n---\n\n## 典型应用场景\n\n| 场景 | 使用方式 | 核心能力 |\n|------|----------|----------|\n| **合同审查** | 抽取关键字段 + 印章检测 | 证据溯源 + 印章识别 |\n| **财务审计** | 跨页表格合并 + 字段抽取 | 跨页合并 + 溯源 |\n| **档案整理** | 混合文档自动分类切分 | 文档分类 |\n| **招投标文件** | 识别报价单/资质/方案并分别处理 | 文档分类 + 解析 |\n| **表单处理** | 手写内容识别 + 结构化抽取 | 手写识别 + 信息抽取 |\n| **合规检查** | 检测印章、签章，验证文档完整性 | 印章检测 |\n\n---\n\n## 依赖\n- requests\n\n## 错误码\n\n| 错误码 | 消息 | 说明 |\n|--------|------|------|\n| 10000 | Success | 成功 |\n| 10001 | Missing parameter | 参数缺失 |\n| 10002 | Invalid parameter | 非法参数 |\n| 10003 | Invalid file | 文件格式非法 |\n| 10004 | Failed to recognize | 识别失败 |\n| 10005 | Internal error | 内部错误 |\n\nFile v2.0.3:README.md\n\n# DocPilot — Intelligent Document Processing Expert\n\n> OpenClaw Skill - Document Parsing, Information Extraction, and Classification\n\nExtract structured data from PDF, images, Word, and Excel documents. Perform field extraction and document classification.\n\n## Why Choose DocPilot?\n\n### Three-Layer Capabilities + Six Core Advantages\n\n**Three-Layer Capabilities**\n1. **Parse** — High-precision document content recognition with layout preservation\n2. **Extract** — Extract key fields with evidence tracing back to original positions\n3. **Classify** — Auto-identify document types, split mixed documents automatically\n\n**Six Core Advantages**\n\n#### 1. Evidence Tracing — Every Field Has an \"ID Card\" ⭐ Exclusive\n```json\n{\n  \"key\": \"Contract Amount\",\n  \"value\": \"¥1,200,000\",\n  \"confidence\": \"high\",\n  \"evidence\": [{\n    \"text\": \"Total Contract Amount: ¥1,200,000\",\n    \"page\": 2,\n    \"quad\": [[120, 350], [480, 350], [480, 380], [120, 380]]\n  }]\n}\n```\n> Essential for audit, legal, and finance — know where data comes from to trust it.\n\n#### 2. Mixed Document Splitting — One File, Multiple Types ⭐ Exclusive\nUpload a mixed file containing \"contract + invoice + quotation\", auto-identify boundaries and classify segment by segment.\n\n#### 3. Seal Detection — Official/Signature/Cross-page Seals ⭐ Exclusive\nAuto-detect seals and stamps in documents, return position and type info. Ideal for contract review and qualification verification.\n\n#### 4. Cross-page Table Merging — Smart Reconstruction ⭐ Exclusive\nAuto-identify tables split across pages, intelligently merge headers and bodies, output complete structures.\n\n#### 5. Handwriting Recognition — Print + Handwriting Mixed ⭐ Exclusive\nSupport mixed recognition of printed and handwritten text. Covers form filling, handwritten annotations, and signature confirmation.\n\n#### 6. Full Format Support — One Skill Does It All\nPDF · Images · Word · Excel · CSV — No need to combine multiple tools.\n\n---\n\n## Features\n\n- ✅ **Multi-format Support**: PDF, Images (JPG/PNG), Word, Excel, CSV\n- ✅ **Layout Analysis**: Automatically detect and structure document elements\n- ✅ **Table Recognition**: Extract tables with HTML and Markdown outputs, cross-page merge\n- ✅ **Information Extraction**: Extract structured fields with evidence tracing\n- ✅ **Document Classification**: Single document or mixed document classification & splitting\n- ✅ **Seal Detection**: Detect stamps and seals in documents\n- ✅ **Handwriting Recognition**: Print + handwriting mixed recognition\n- ✅ **Multiple Output Formats**: structured JSON, markdown, plain text\n\n---\n\n## Quick Start\n\n### Installation\n\n```bash\n# Install via ClawHub\nopenclaw skills install DocPilot\n\n# Or manual installation (local development)\ncd E:\\skills\\document-parser\npip install -r requirements.txt\n```\n\n### Configuration\n\n**Option 1: Environment Variables**\n```bash\n# Windows PowerShell\n$env:DOCPilot_BASE_URL=\"https://docpilot.token-ai.com.cn\"\n$env:DOCPilot_API_KEY=\"your_api_key\"\n```\n\n**Option 2: Configuration File**\n```bash\ncd E:\\skills\\DocPilot\ncopy config.example.json config.json\n# Edit config.json with your API endpoint and API key\n```\n\n**Option 2: Configuration File**\n```bash\ncd E:\\skills\\document-parser\ncopy config.example.json config.json\n# Edit config.json with your API endpoint\n```\n\n### Usage\n\n#### Parse a Document\n```bash\n# Basic parsing\nDocPilot parse \"C:\\docs\\report.pdf\"\n\n# Markdown output\nDocPilot parse \"C:\\docs\\scan.jpg\" --output markdown\n\n# Enable seal detection and bbox\nDocPilot parse \"C:\\docs\\contract.pdf\" --seal --bbox\n\n# Parse Excel\nDocPilot parse \"C:\\docs\\data.xlsx\"\n```\n\n#### Extract Information\n```bash\n# Extract fields with schema\nDocPilot extract \"C:\\docs\\contract.pdf\" --schema \"{\\\"fields\\\":[{\\\"key\\\":\\\"Party A\\\",\\\"type\\\":\\\"string\\\"},{\\\"key\\\":\\\"Party B\\\",\\\"type\\\":\\\"string\\\"}]}\"\n\n# Extract with schema file\nDocPilot extract \"C:\\docs\\invoice.pdf\" --schema schema.json\n```\n\n#### Classify Document\n```bash\n# Single document classification\nDocPilot classify \"C:\\docs\\doc.pdf\"\n\n# Mixed document classification and splitting\nDocPilot classify \"C:\\docs\\mixed.pdf\" --mode classify_and_split --categories \"[{\\\"name\\\":\\\"Contract\\\",\\\"description\\\":\\\"Contract agreement\\\"},{\\\"name\\\":\\\"Invoice\\\",\\\"description\\\":\\\"Invoice document\\\"}]\"\n```\n\n---\n\n## Parameters\n\n### parse Command\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| file | string | Yes | PDF/Image/Word/Excel file path |\n| --output | string | No | Output format: structured/markdown/text |\n| --layout | flag | No | Enable layout analysis |\n| --table | flag | No | Enable table recognition (incl. cross-page merge) |\n| --seal | flag | No | Enable seal recognition |\n| --dpi | int | No | DPI: 72/144/200/216 |\n| --pages | string | No | Page range, e.g., \"1-5,8,10-12\" |\n| --bbox | flag | No | Include bbox coordinates |\n| --normalize | flag | No | Return formatted parsed data (default: on) |\n| --raw | flag | No | Return raw parsed format |\n| --include-image | flag | No | Include images in markdown |\n| --image-format | string | No | Image format: url/base64 |\n\n### extract Command\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| file | string | Yes | Document file path |\n| --schema | JSON | Yes | Field schema definition |\n| --prompt | JSON | No | Prompt mode schema |\n| --schema-ref | string | No | Schema reference template |\n| --options | JSON | No | Extended options |\n\n### classify Command\n\n| Parameter | Type | Required | Description |\n|-----------|------|----------|-------------|\n| file | string | Yes | Document file path |\n| --mode | string | No | classify_only / classify_and_split |\n| --categories | JSON | No | Category schema definition |\n\n---\n\n## Output Format\n\n### parse Response\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"document_id\": \"dp-8a3f-xxxx\",\n    \"page_count\": 25,\n    \"file_type\": \"pdf\",\n    \"pages\": [...],\n    \"markdown\": \"...\"\n  }\n}\n```\n\n### extract Response\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"extraction_id\": \"ext-xxxx\",\n    \"fields\": [\n      {\n        \"key\": \"Party A\",\n        \"value\": \"ABC Company\",\n        \"confidence\": \"high\",\n        \"evidence\": [...]\n      }\n    ],\n    \"unfound_fields\": [],\n    \"metadata\": {...}\n  }\n}\n```\n\n### classify Response\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"mode\": \"classify_only\",\n    \"classification\": {\n      \"category\": \"Contract\",\n      \"confidence\": 0.95,\n      \"reasoning\": \"...\"\n    },\n    \"metadata\": {...}\n  }\n}\n```\n\n---\n\n## Supported Document Elements\n\n| Type | Description |\n|------|-------------|\n| DocumentTitle | Document title |\n| LevelTitle | Section heading |\n| Paragraph | Text paragraph |\n| Table | Table (with cross-page merge) |\n| Image | Image |\n| Seal | Seal/Stamp |\n| FigureTitle | Figure title |\n| Handwriting | Handwritten text |\n\n---\n\n## Typical Use Cases\n\n| Scenario | Usage | Core Capability |\n|----------|-------|-----------------|\n| **Contract Review** | Extract key fields + seal detection | Evidence tracing + Seal recognition |\n| **Financial Audit** | Cross-page table merge + field extraction | Cross-page merge + Tracing |\n| **Archive Organization** | Mixed document auto-classification & splitting | Document classification |\n| **Bidding Documents** | Identify quotations/qualifications/proposals separately | Classification + Parsing |\n| **Form Processing** | Handwriting recognition + structured extraction | Handwriting + Extraction |\n| **Compliance Check** | Detect seals, verify document integrity | Seal detection |\n\n---\n\n## Error Codes\n\n| Code | Message | Description |\n|------|---------|-------------|\n| 10000 | Success | Successful |\n| 10001 | Missing parameter | Missing required parameter |\n| 10002 | Invalid parameter | Invalid parameter value |\n| 10003 | Invalid file | Unsupported file format |\n| 10004 | Failed to recognize | Recognition failed |\n| 10005 | Internal error | Internal server error |\n\n---\n\n## Dependencies\n\n- Python 3.8+\n- requests>=2.28.0\n\n---\n\n## License\n\nMIT License\n\n---\n\n## Support\n\nFile an issue or contact TokenAI for help.\n\nFile v2.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn7ewjb6a59zsr2zz60ky1wrzx82gdqg\",\n  \"slug\": \"docpilot\",\n  \"version\": \"2.0.3\",\n  \"publishedAt\": 1777045828782\n}\n\nFile v2.0.3:README_zh.md\n\n# DocPilot — 智能文档处理专家\n\n> OpenClaw Skill - 高精度文档解析、信息抽取、文档分类\n\n从 PDF、图片、Word、Excel 文档中提取结构化数据，支持信息抽取和文档分类。\n\n## 为什么选择 DocPilot？\n\n### 三层能力 + 六大核心优势\n\n**三层能力**\n1. **解析** — 高精度识别文档内容，保留版面结构\n2. **抽取** — 按需求提取关键字段，每条结果都能溯源到原文位置\n3. **分类** — 自动识别文档类型，混合文档也能自动切分\n\n**六大核心优势**\n\n#### 1. 证据溯源 — 每个字段都有\"身份证\" ⭐ 独家\n```json\n{\n  \"key\": \"合同金额\",\n  \"value\": \"¥1,200,000\",\n  \"confidence\": \"high\",\n  \"evidence\": [{\n    \"text\": \"合同总金额：¥1,200,000\",\n    \"page\": 2,\n    \"quad\": [[120, 350], [480, 350], [480, 380], [120, 380]]\n  }]\n}\n```\n> 审计、法务、财务场景必备 — 知道数据从哪来，才能相信数据是对的。\n\n#### 2. 混合文档切分 — 一份文件，多种类型 ⭐ 独家\n上传一份包含\"合同+发票+报价单\"的混合文件，自动识别边界并逐段分类。\n\n#### 3. 印章检测 — 公章/签名章/骑缝章自动识别 ⭐ 独家\n自动检测文档中的印章和签章，返回位置和类型信息，适用于合同审查、资质验证。\n\n#### 4. 跨页表格合并 — 断裂表格智能还原 ⭐ 独家\n自动识别跨页断裂的表格，智能合并表头和表体，输出完整结构。\n\n#### 5. 手写字体识别 — 印刷+手写混合识别 ⭐ 独家\n支持印刷体和手写体混合识别，覆盖表单填写、手写批注、签字确认等场景。\n\n#### 6. 全格式支持 — 一个技能全部搞定\nPDF · 图片 · Word · Excel · CSV — 无需组合多个工具。\n\n---\n\n## 功能特性\n\n- ✅ **多格式支持**: PDF、图片 (JPG/PNG)、Word、Excel、CSV\n- ✅ **版面分析**: 自动检测和解析文档结构元素\n- ✅ **表格识别**: 提取表格并输出 HTML 和 Markdown 格式，支持跨页合并\n- ✅ **信息抽取**: 按 schema 提取结构化字段，带证据溯源\n- ✅ **文档分类**: 单文档分类或混合文档切分分类\n- ✅ **印章检测**: 检测文档中的印章和签章\n- ✅ **手写识别**: 印刷体+手写体混合识别\n- ✅ **多种输出格式**: structured JSON、markdown、纯文本\n\n---\n\n## 快速开始\n\n### 安装\n\n```bash\n# 通过 ClawHub 安装\nopenclaw skills install DocPilot\n\n# 或手动安装（本地开发）\ncd E:\\skills\\document-parser\npip install -r requirements.txt\n```\n\n### 配置\n\n**方式一：环境变量**\n```bash\n# Windows PowerShell\n$env:DOCPilot_BASE_URL=\"https://docpilot.token-ai.com.cn\"\n$env:DOCPilot_API_KEY=\"your_api_key\"\n```\n\n**方式二：配置文件**\n```bash\ncd E:\\skills\\DocPilot\ncopy config.example.json config.json\n# 编辑 config.json 填入你的 API 地址和 API Key\n```\n\n**方式二：配置文件**\n```bash\ncd E:\\skills\\document-parser\ncopy config.example.json config.json\n# 编辑 config.json 填入你的 API 地址\n```\n\n### 使用方法\n\n#### 解析文档\n```bash\n# 基础解析\nDocPilot parse \"C:\\docs\\report.pdf\"\n\n# Markdown 输出\nDocPilot parse \"C:\\docs\\scan.jpg\" --output markdown\n\n# 启用印章检测和边界框\nDocPilot parse \"C:\\docs\\contract.pdf\" --seal --bbox\n\n# 解析 Excel\nDocPilot parse \"C:\\docs\\data.xlsx\"\n```\n\n#### 信息抽取\n```bash\n# 按 schema 抽取字段\nDocPilot extract \"C:\\docs\\contract.pdf\" --schema \"{\\\"fields\\\":[{\\\"key\\\":\\\"甲方\\\",\\\"type\\\":\\\"string\\\"},{\\\"key\\\":\\\"乙方\\\",\\\"type\\\":\\\"string\\\"}]}\"\n\n# 使用 schema 文件\nDocPilot extract \"C:\\docs\\invoice.pdf\" --schema schema.json\n```\n\n#### 文档分类\n```bash\n# 单文档分类\nDocPilot classify \"C:\\docs\\doc.pdf\"\n\n# 混合文档分类和切分\nDocPilot classify \"C:\\docs\\mixed.pdf\" --mode classify_and_split --categories \"[{\\\"name\\\":\\\"合同\\\",\\\"description\\\":\\\"合同协议\\\"},{\\\"name\\\":\\\"发票\\\",\\\"description\\\":\\\"发票单据\\\"}]\"\n```\n\n---\n\n## 参数说明\n\n### parse 命令\n\n| 参数 | 类型 | 必填 | 说明 |\n|------|------|------|------|\n| file | string | 是 | PDF/图片/Word/Excel 文件路径 |\n| --output | string | 否 | 输出格式：structured/markdown/text |\n| --layout | flag | 否 | 启用版面分析 |\n| --table | flag | 否 | 启用表格识别（含跨页合并） |\n| --seal | flag | 否 | 启用印章检测 |\n| --dpi | int | 否 | DPI：72/144/200/216 |\n| --pages | string | 否 | 页码范围，如 \"1-5,8,10-12\" |\n| --bbox | flag | 否 | 包含边界框坐标 |\n| --normalize | flag | 否 | 返回格式化解析数据（默认开启） |\n| --raw | flag | 否 | 返回原始解析格式 |\n| --include-image | flag | 否 | markdown 中包含图片 |\n| --image-format | string | 否 | 图片格式：url/base64 |\n\n### extract 命令\n\n| 参数 | 类型 | 必填 | 说明 |\n|------|------|------|------|\n| file | string | 是 | 文档文件路径 |\n| --schema | JSON | 是 | 字段 schema 定义 |\n| --prompt | JSON | 否 | 提示词模式 schema |\n| --schema-ref | string | 否 | 模板引用 |\n| --options | JSON | 否 | 扩展配置 |\n\n### classify 命令\n\n| 参数 | 类型 | 必填 | 说明 |\n|------|------|------|------|\n| file | string | 是 | 文档文件路径 |\n| --mode | string | 否 | classify_only / classify_and_split |\n| --categories | JSON | 否 | 分类 schema 定义 |\n\n---\n\n## 输出格式\n\n### parse 响应\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"document_id\": \"dp-8a3f-xxxx\",\n    \"page_count\": 25,\n    \"file_type\": \"pdf\",\n    \"pages\": [...],\n    \"markdown\": \"...\"\n  }\n}\n```\n\n### extract 响应\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"extraction_id\": \"ext-xxxx\",\n    \"fields\": [\n      {\n        \"key\": \"甲方\",\n        \"value\": \"某某公司\",\n        \"confidence\": \"high\",\n        \"evidence\": [...]\n      }\n    ],\n    \"unfound_fields\": [],\n    \"metadata\": {...}\n  }\n}\n```\n\n### classify 响应\n```json\n{\n  \"code\": 10000,\n  \"message\": \"Success\",\n  \"data\": {\n    \"mode\": \"classify_only\",\n    \"classification\": {\n      \"category\": \"合同\",\n      \"confidence\": 0.95,\n      \"reasoning\": \"...\"\n    },\n    \"metadata\": {...}\n  }\n}\n```\n\n---\n\n## 支持的文档元素\n\n| 类型 | 说明 |\n|------|------|\n| DocumentTitle | 文档标题 |\n| LevelTitle | 层级标题 |\n| Paragraph | 段落 |\n| Table | 表格（支持跨页合并） |\n| Image | 图片 |\n| Seal | 印章 |\n| FigureTitle | 图表标题 |\n| Handwriting | 手写文字 |\n\n---\n\n## 典型应用场景\n\n| 场景 | 使用方式 | 核心能力 |\n|------|----------|----------|\n| **合同审查** | 抽取关键字段 + 印章检测 | 证据溯源 + 印章识别 |\n| **财务审计** | 跨页表格合并 + 字段抽取 | 跨页合并 + 溯源 |\n| **档案整理** | 混合文档自动分类切分 | 文档分类 |\n| **招投标文件** | 识别报价单/资质/方案并分别处理 | 文档分类 + 解析 |\n| **表单处理** | 手写内容识别 + 结构化抽取 | 手写识别 + 信息抽取 |\n| **合规检查** | 检测印章、签章，验证文档完整性 | 印章检测 |\n\n---\n\n## 错误码\n\n| 错误码 | 消息 | 说明 |\n|--------|------|------|\n| 10000 | Success | 成功 |\n| 10001 | Missing parameter | 参数缺失 |\n| 10002 | Invalid parameter | 非法参数 |\n| 10003 | Invalid file | 文件格式非法 |\n| 10004 | Failed to recognize | 识别失败 |\n| 10005 | Internal error | 内部错误 |\n\n---\n\n## 依赖\n\n- Python 3.8+\n- requests>=2.28.0\n\n---\n\n## 许可证\n\nMIT License\n\n---\n\n## 支持\n\n如有问题请提交 Issue 或联系 TokenAI。\n\nFile v2.0.3:config.example.json\n\n{\n  \"base_url\": \"https://docpilot.token-ai.com.cn\",\n  \"api_key\": \"your_api_key_here\"\n}\n\nFile v2.0.3:config.json\n\n{\n  \"base_url\": \"https://docpilot.token-ai.com.cn\",\n  \"api_key\": \"123456\"\n}\n\nFile v2.0.3:extract_schema.json\n\n{\n  \"fields\": [\n    {\n      \"key\": \"利润表\",\n      \"type\": \"string\",\n      \"description\": \"利润表相关内容\"\n    }\n  ]\n}\n\nFile v2.0.3:test_schema.json\n\n{\n  \"fields\": [\n    {\"key\": \"营业收入\", \"type\": \"string\", \"description\": \"利润表中的营业收入金额\"},\n    {\"key\": \"营业成本\", \"type\": \"string\", \"description\": \"利润表中的营业成本金额\"},\n    {\"key\": \"净利润\", \"type\": \"string\", \"description\": \"利润表中的净利润金额\"},\n    {\"key\": \"归属于母公司股东的净利润\", \"type\": \"string\", \"description\": \"归属于母公司股东的净利润\"}\n  ]\n}\n\nFile v2.0.3:clawhub.yaml\n\n# ClawHub Skill Package Configuration\n# DocPilot 文档智能处理技能 - ClawHub 发布配置\n\nname: DocPilot\nversion: 2.0.0\nauthor: TokenAI\ndescription:\n  en: Document parsing, information extraction, and document classification with high precision\n  zh: 高精度文档解析、信息抽取、文档分类\n\ncategory: tool\ntags:\n  - pdf\n  - document\n  - extraction\n  - ocr\n  - table\n  - parser\n  - classify\n  - openclaw\n\n# OpenClaw 技能入口\nentry: index.py\n\n# Python 依赖\ndependencies:\n  - requests>=2.28.0\n\n# 配置项\nconfig:\n  - name: DOCPilot_BASE_URL\n    type: string\n    required: false\n    default: https://docpilot.token-ai.com.cn\n    description:\n      en: API Base URL\n      zh: API 基础地址\n\n  - name: DOCPilot_API_KEY\n    type: string\n    required: true\n    description:\n      en: API Key for authentication (Bearer token)\n      zh: API 鉴权密钥（Bearer token）\n\n# 命令定义\ncommands:\n  - name: parse\n    description:\n      en: Parse a document (PDF/Image/Word/Excel)\n      zh: 解析文档（PDF/图片/Word/Excel）\n    usage: DocPilot parse <file_path> [options]\n    options:\n      - name: --output\n        description:\n          en: Output format (structured/markdown/text)\n          zh: 输出格式\n        value: structured|markdown|text\n      - name: --layout\n        description:\n          en: Enable layout analysis\n          zh: 启用版面分析\n      - name: --table\n        description:\n          en: Enable table recognition\n          zh: 启用表格识别\n      - name: --seal\n        description:\n          en: Enable seal recognition\n          zh: 启用印章检测\n      - name: --dpi\n        description:\n          en: DPI for PDF/image conversion\n          zh: PDF/图片转图像分辨率\n        value: 72|144|200|216\n      - name: --pages\n        description:\n          en: Page range (e.g., 1-5,8,10-12)\n          zh: 页码范围\n      - name: --bbox\n        description:\n          en: Include bbox coordinates in elements\n          zh: 包含边界框坐标\n      - name: --include-image\n        description:\n          en: Include images in markdown output\n          zh: 在 markdown 中包含图片\n      - name: --image-format\n        description:\n          en: Image format (url/base64)\n          zh: 图片格式\n        value: url|base64\n\n  - name: extract\n    description:\n      en: Extract structured fields from document\n      zh: 从文档中抽取结构化字段\n    usage: DocPilot extract <file_path> --schema <JSON>\n    options:\n      - name: --schema\n        description:\n          en: Field schema (JSON string or file path)\n          zh: 字段 schema（JSON 字符串或文件路径）\n        required: true\n      - name: --prompt\n        description:\n          en: Prompt mode schema\n          zh: 提示词模式 schema\n      - name: --schema-ref\n        description:\n          en: Schema reference template\n          zh: 模板引用\n      - name: --options\n        description:\n          en: Extended options\n          zh: 扩展配置\n\n  - name: classify\n    description:\n      en: Classify document type\n      zh: 文档分类\n    usage: DocPilot classify <file_path> [options]\n    options:\n      - name: --mode\n        description:\n          en: Classification mode\n          zh: 分类模式\n        value: classify_only|classify_and_split\n      - name: --categories\n        description:\n          en: Category schema (JSON string or file path)\n          zh: 分类 schema（JSON 字符串或文件路径）\n\n# 打包文件列表\nfiles:\n  - index.py\n  - SKILL.md\n  - requirements.txt\n  - config.example.json\n  - icon.svg\n  - README_zh.md\n  - README.md\n  - clawhub.yaml\n\n# 许可证\nlicense: MIT\n\nFile v2.0.3:requirements.txt\n\nrequests>=2.28.0","readmeExcerpt":"Skill: 智能文档助手 Owner: ankylala Summary: 智能文档处理专家，支持文档解析、信息抽取、文档分类 Tags: latest:2.0.4 Version history: v2.0.4 | 2026-04-24T16:11:18.455Z | user - Version bump from 2.0.0 to 2.0.4 - No file or documentation changes detected in this release v2.0.3 | 2026-04-24T15:50:28.782Z | user - Enhanced documentation describing DocPilot’s high-precision document parsing, extraction, and classification capabilities. - Detailed explan","codeSnippets":[],"executableExamples":[{"language":"json","snippet":"{\n  \"key\": \"合同金额\",\n  \"value\": \"¥1,200,000\",\n  \"confidence\": \"high\",\n  \"evidence\": [{\n    \"text\": \"合同总金额：¥1,200,000\",\n    \"page\": 2,\n    \"quad\": [[120, 350], [480, 350], [480, 380], [120, 380]]\n  }]\n}"},{"language":"text","snippet":"DocPilot parse <文件路径> [选项]"},{"language":"text","snippet":"DocPilot parse C:\\docs\\report.pdf\nDocPilot parse C:\\docs\\scan.jpg --output markdown\nDocPilot parse C:\\docs\\data.xlsx\nDocPilot parse C:\\docs\\contract.pdf --seal --bbox"},{"language":"text","snippet":"DocPilot extract <文件路径> --schema <JSON>"},{"language":"text","snippet":"DocPilot extract C:\\docs\\contract.pdf --schema \"{\\\"fields\\\":[{\\\"key\\\":\\\"甲方\\\",\\\"type\\\":\\\"string\\\"},{\\\"key\\\":\\\"乙方\\\",\\\"type\\\":\\\"string\\\"}]}\"\nDocPilot extract C:\\docs\\invoice.pdf --schema schema.json"},{"language":"text","snippet":"DocPilot classify <文件路径> [选项]"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: DocPilot\ndescription: 智能文档处理专家，支持文档解析、信息抽取、文档分类\nversion: 2.0.0\nauthor: TokenAI\ntags:\n  - pdf\n  - document\n  - extraction\n  - ocr\n  - table\n  - parser\n  - classify\ncommands:\n  - parse\n  - extract\n  - classify\n---\n\n# DocPilot — 智能文档处理专家\n\n高精度文档处理技能，支持文档解析、信息抽取、文档分类。\n\n## 为什么选择 DocPilot？\n\n### 三层能力 + 六大核心优势\n\n**三层能力**\n1. **解析** — 高精度识别文档内容，保留版面结构\n2. **抽取** — 按需求提取关键字段，每条结果都能溯源到原文位置\n3. **分类** — 自动识别文档类型，混合文档也能自动切分\n\n**六大核心优势**\n\n#### 1. 证据溯源 — 每个字段都有\"身份证\" ⭐ 独家\n```json\n{\n  \"key\": \"合同金额\",\n  \"value\": \"¥1,200,000\",\n  \"confidence\": \"high\",\n  \"evidence\": [{\n    \"text\": \"合同总金额：¥1,200,000\",\n    \"page\": 2,\n    \"quad\": [[120, 350], [480, 350], [480, 380], [120, 380]]\n  }]\n}\n```\n> 审计、法务、财务场景必备 — 知道数据从哪来，才能相信数据是对的。\n\n#### 2. 混合文档切分 — 一份文件，多种类型 ⭐ 独家\n上传一份包含\"合同+发票+报价单\"的混合文件，自动识别边界并逐段分类。\n\n#### 3. 印章检测 — 公章/签名章/骑缝章自动识别 ⭐ 独家\n自动检测文档中的印章和签章，返回位置和类型信息，适用于合同审查、资质验证。\n\n#### 4. 跨页表格合并 — 断裂表格智能还原 ⭐ 独家\n自动识别跨页断裂的表格，智能合并表头和表体，输出完整结构。\n\n#### 5. 手写字体识别 — 印刷+手写混合识别 ⭐ 独家\n支持印刷体和手写体混合识别，覆盖表单填写、手写批注、签字确认等场景。\n\n#### 6. 全格式支持 — 一个技能全部搞定\nPDF · 图片 · Word · Excel · CSV — 无需组合多个工具。\n\n---\n\n## 命令\n\n### 解析文档\n```\nDocPilot parse <文件路径> [选项]\n```\n\n示例：\n```\nDocPilot parse C:\\docs\\report.pdf\nDocPilot parse C:\\docs\\scan.jpg --output markdown\nDocPilot parse C:\\docs\\data.xlsx\nDocPilot parse C:\\docs\\contract.pdf --seal --bbox\n```\n\n### 信息抽取\n```\nDocPilot extract <文件路径> --schema <JSON>\n```\n\n示例：\n```\nDocPilot extract C:\\docs\\contract.pdf --schema \"{\\\"fields\\\":[{\\\"key\\\":\\\"甲方\\\",\\\"type\\\":\\\"string\\\"},{\\\"key\\\":\\\"乙方\\\",\\\"type\\\":\\\"string\\\"}]}\"\nDocPilot extract C:\\docs\\invoice.pdf --schema schema.json\n```\n\n### 文档分类\n```\nDocPilot classify <文件路径> [选项]\n```\n\n示例：\n```\nDocPilot classify C:\\docs\\mixed.pdf\nDocPilot classify C:\\docs\\docs.pdf --mode classify_and_split --categories \"[{\\\"name\\\":\\\"合同\\\",\\\"description\\\":\\\"合同协议\\\"},{\\\"name\\\":\\\"发票\\\",\\\"description\\\":\\\"发票单据\\\"}]\"\n```\n\n---\n\n## 参数说明\n\n### parse 命令\n\n| 参数 | 说明 | 示例 |\n|------|------|------|\n| 文件路径 | PDF/图片/Word/Excel 文件路径 | `C:\\docs\\report.pdf` |\n| --output | 输出格式 (structured/markdown/text) | `--output markdown` |\n| --layout | 启用版面分析 | `--layout` |\n| --table | 启用表格识别（含跨页合并） | `--table` |\n| --seal | 启用印章识别 | `--seal` |\n| --dpi | DPI (72/144/200/216) | `--dpi 200` |\n| --pages | 页码范围 | `--pages 1-5,8,10-12` |\n| --bbox | 包含边界框坐标 | `--bbox` |\n| --normalize | 返回格式化解析数据 (默认开启) | `--normalize` |\n| --raw | 返回原始解析格式 | `--raw` |\n| --include-image | markdown 中包含图片 | `--include-image` |\n| --image-format | 图片格式 (url/base64) | `--image-format url` |\n\n### extract 命令\n\n| 参数 | 说明 | 示例 |\n|------|------|------|\n| 文件路径 | 文档文件路径 | `C:\\docs\\contract.pdf` |\n| --schema | 字段 schema（必填） | `--schema '{\"fields\":[...]}'` |\n| --prompt | 提示词模式 schema | `--prompt '{\"fields\":[...]}'` |\n| --schema-ref | 模板引用 | `--schema-ref DocPilot/contract/v1` |\n| --options | 扩展配置 | `--options '{\"mode\":\"fast\"}'` |\n\n### classify 命令\n\n| 参数 | 说明 | 示例 |\n|------|------|------|\n| 文件路径 | 文档文件路径 | `C:\\docs\\mixed.pdf` |\n| --mode | 分类模式 | `--mode classify_and_split` |\n| --categories | 分类 schema | `--categories '[{\"name\":\"合同\",\"description\":\".."},{"path":"README.md","content":"# DocPilot — Intelligent Document Processing Expert\n\n> OpenClaw Skill - Document Parsing, Information Extraction, and Classification\n\nExtract structured data from PDF, images, Word, and Excel documents. Perform field extraction and document classification.\n\n## Why Choose DocPilot?\n\n### Three-Layer Capabilities + Six Core Advantages\n\n**Three-Layer Capabilities**\n1. **Parse** — High-precision document content recognition with layout preservation\n2. **Extract** — Extract key fields with evidence tracing back to original positions\n3. **Classify** — Auto-identify document types, split mixed documents automatically\n\n**Six Core Advantages**\n\n#### 1. Evidence Tracing — Every Field Has an \"ID Card\" ⭐ Exclusive\n```json\n{\n  \"key\": \"Contract Amount\",\n  \"value\": \"¥1,200,000\",\n  \"confidence\": \"high\",\n  \"evidence\": [{\n    \"text\": \"Total Contract Amount: ¥1,200,000\",\n    \"page\": 2,\n    \"quad\": [[120, 350], [480, 350], [480, 380], [120, 380]]\n  }]\n}\n```\n> Essential for audit, legal, and finance — know where data comes from to trust it.\n\n#### 2. Mixed Document Splitting — One File, Multiple Types ⭐ Exclusive\nUpload a mixed file containing \"contract + invoice + quotation\", auto-identify boundaries and classify segment by segment.\n\n#### 3. Seal Detection — Official/Signature/Cross-page Seals ⭐ Exclusive\nAuto-detect seals and stamps in documents, return position and type info. Ideal for contract review and qualification verification.\n\n#### 4. Cross-page Table Merging — Smart Reconstruction ⭐ Exclusive\nAuto-identify tables split across pages, intelligently merge headers and bodies, output complete structures.\n\n#### 5. Handwriting Recognition — Print + Handwriting Mixed ⭐ Exclusive\nSupport mixed recognition of printed and handwritten text. Covers form filling, handwritten annotations, and signature confirmation.\n\n#### 6. Full Format Support — One Skill Does It All\nPDF · Images · Word · Excel · CSV — No need to combine multiple tools.\n\n---\n\n## Features\n\n- ✅ **Multi-format Support**: PDF, Images (JPG/PNG), Word, Excel, CSV\n- ✅ **Layout Analysis**: Automatically detect and structure document elements\n- ✅ **Table Recognition**: Extract tables with HTML and Markdown outputs, cross-page merge\n- ✅ **Information Extraction**: Extract structured fields with evidence tracing\n- ✅ **Document Classification**: Single document or mixed document classification & splitting\n- ✅ **Seal Detection**: Detect stamps and seals in documents\n- ✅ **Handwriting Recognition**: Print + handwriting mixed recognition\n- ✅ **Multiple Output Formats**: structured JSON, markdown, plain text\n\n---\n\n## Quick Start\n\n### Installation\n\n```bash\n# Install via ClawHub\nopenclaw skills install DocPilot\n\n# Or manual installation (local development)\ncd E:\\skills\\document-parser\npip install -r requirements.txt\n```\n\n### Configuration\n\n**Option 1: Environment Variables**\n```bash\n# Windows PowerShell\n$env:DOCPilot_BASE_URL=\"https://docpilot.token-ai.com.cn\"\n$env:DOCPilot_API_KEY=\"your_api_key\"\n```\n\n**Option 2: Configura"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7ewjb6a59zsr2zz60ky1wrzx82gdqg\",\n  \"slug\": \"docpilot\",\n  \"version\": \"2.0.4\",\n  \"publishedAt\": 1777047078455\n}"},{"path":"README_zh.md","content":"# DocPilot — 智能文档处理专家\n\n> OpenClaw Skill - 高精度文档解析、信息抽取、文档分类\n\n从 PDF、图片、Word、Excel 文档中提取结构化数据，支持信息抽取和文档分类。\n\n## 为什么选择 DocPilot？\n\n### 三层能力 + 六大核心优势\n\n**三层能力**\n1. **解析** — 高精度识别文档内容，保留版面结构\n2. **抽取** — 按需求提取关键字段，每条结果都能溯源到原文位置\n3. **分类** — 自动识别文档类型，混合文档也能自动切分\n\n**六大核心优势**\n\n#### 1. 证据溯源 — 每个字段都有\"身份证\" ⭐ 独家\n```json\n{\n  \"key\": \"合同金额\",\n  \"value\": \"¥1,200,000\",\n  \"confidence\": \"high\",\n  \"evidence\": [{\n    \"text\": \"合同总金额：¥1,200,000\",\n    \"page\": 2,\n    \"quad\": [[120, 350], [480, 350], [480, 380], [120, 380]]\n  }]\n}\n```\n> 审计、法务、财务场景必备 — 知道数据从哪来，才能相信数据是对的。\n\n#### 2. 混合文档切分 — 一份文件，多种类型 ⭐ 独家\n上传一份包含\"合同+发票+报价单\"的混合文件，自动识别边界并逐段分类。\n\n#### 3. 印章检测 — 公章/签名章/骑缝章自动识别 ⭐ 独家\n自动检测文档中的印章和签章，返回位置和类型信息，适用于合同审查、资质验证。\n\n#### 4. 跨页表格合并 — 断裂表格智能还原 ⭐ 独家\n自动识别跨页断裂的表格，智能合并表头和表体，输出完整结构。\n\n#### 5. 手写字体识别 — 印刷+手写混合识别 ⭐ 独家\n支持印刷体和手写体混合识别，覆盖表单填写、手写批注、签字确认等场景。\n\n#### 6. 全格式支持 — 一个技能全部搞定\nPDF · 图片 · Word · Excel · CSV — 无需组合多个工具。\n\n---\n\n## 功能特性\n\n- ✅ **多格式支持**: PDF、图片 (JPG/PNG)、Word、Excel、CSV\n- ✅ **版面分析**: 自动检测和解析文档结构元素\n- ✅ **表格识别**: 提取表格并输出 HTML 和 Markdown 格式，支持跨页合并\n- ✅ **信息抽取**: 按 schema 提取结构化字段，带证据溯源\n- ✅ **文档分类**: 单文档分类或混合文档切分分类\n- ✅ **印章检测**: 检测文档中的印章和签章\n- ✅ **手写识别**: 印刷体+手写体混合识别\n- ✅ **多种输出格式**: structured JSON、markdown、纯文本\n\n---\n\n## 快速开始\n\n### 安装\n\n```bash\n# 通过 ClawHub 安装\nopenclaw skills install DocPilot\n\n# 或手动安装（本地开发）\ncd E:\\skills\\document-parser\npip install -r requirements.txt\n```\n\n### 配置\n\n**方式一：环境变量**\n```bash\n# Windows PowerShell\n$env:DOCPilot_BASE_URL=\"https://docpilot.token-ai.com.cn\"\n$env:DOCPilot_API_KEY=\"your_api_key\"\n```\n\n**方式二：配置文件**\n```bash\ncd E:\\skills\\DocPilot\ncopy config.example.json config.json\n# 编辑 config.json 填入你的 API 地址和 API Key\n```\n\n**方式二：配置文件**\n```bash\ncd E:\\skills\\document-parser\ncopy config.example.json config.json\n# 编辑 config.json 填入你的 API 地址\n```\n\n### 使用方法\n\n#### 解析文档\n```bash\n# 基础解析\nDocPilot parse \"C:\\docs\\report.pdf\"\n\n# Markdown 输出\nDocPilot parse \"C:\\docs\\scan.jpg\" --output markdown\n\n# 启用印章检测和边界框\nDocPilot parse \"C:\\docs\\contract.pdf\" --seal --bbox\n\n# 解析 Excel\nDocPilot parse \"C:\\docs\\data.xlsx\"\n```\n\n#### 信息抽取\n```bash\n# 按 schema 抽取字段\nDocPilot extract \"C:\\docs\\contract.pdf\" --schema \"{\\\"fields\\\":[{\\\"key\\\":\\\"甲方\\\",\\\"type\\\":\\\"string\\\"},{\\\"key\\\":\\\"乙方\\\",\\\"type\\\":\\\"string\\\"}]}\"\n\n# 使用 schema 文件\nDocPilot extract \"C:\\docs\\invoice.pdf\" --schema schema.json\n```\n\n#### 文档分类\n```bash\n# 单文档分类\nDocPilot classify \"C:\\docs\\doc.pdf\"\n\n# 混合文档分类和切分\nDocPilot classify \"C:\\docs\\mixed.pdf\" --mode classify_and_split --categories \"[{\\\"name\\\":\\\"合同\\\",\\\"description\\\":\\\"合同协议\\\"},{\\\"name\\\":\\\"发票\\\",\\\"description\\\":\\\"发票单据\\\"}]\"\n```\n\n---\n\n## 参数说明\n\n### parse 命令\n\n| 参数 | 类型 | 必填 | 说明 |\n|------|------|------|------|\n| file | string | 是 | PDF/图片/Word/Excel 文件路径 |\n| --output | string | 否 | 输出格式：structured/markdown/text |\n| --layout | flag | 否 | 启用版面分析 |\n| --table | flag | 否 | 启用表格识别（含跨页合并） |\n| --seal | flag | 否 | 启用印章检测 |\n| --dpi | int | 否 | DPI：72/144/200/216 |\n| --pages | string | 否 | 页码范围，如 \"1-5,8,10-12\" |\n| --bbox | flag | 否 | 包含边界框坐标 |\n| --normalize | flag | 否 | 返回格式化解析数据（默认开启） |\n| --raw | flag | 否 | 返回原始解析格式 |\n| --include-ima"},{"path":"skill-card.md","content":"## Description:\n\n智能文档处理专家，支持文档解析、信息抽取、文档分类。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[ankylala](https://clawhub.ai/user/ankylala)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to parse PDFs, images, Word, Excel, and CSV files, extract structured fields with source evidence, and classify or split mixed document sets. Typical workflows include contract review, finance audits, archive organization, form processing, and compliance checks.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill uploads selected documents to the DocPilot/TokenAI service or another configured endpoint, and privacy controls are under-documented.\n\nMitigation: Use only documents approved for that external service until the publisher documents retention, deletion, jurisdiction, and privacy terms.\n\nRisk: The bundled configuration includes credential-like data and can override environment variables.\n\nMitigation: Remove bundled secrets, rotate any exposed credentials, and require deployers to provide API keys through approved secret management.\n\nRisk: The service destination is configurable, which can send document contents to an unexpected endpoint.\n\nMitigation: Restrict deployment to approved HTTPS destinations and review endpoint configuration before each release.\n\nRisk: Dependencies are not pinned.\n\nMitigation: Pin and review dependencies before production deployment.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/ankylala/skills/docpilot)\n- [DocPilot Service Endpoint](https://docpilot.token-ai.com.cn)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, configuration, guidance]\n\n**Output Format:** [JSON, Markdown, or plain text document-processing results]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Parse outputs may include document IDs, page counts, layout elements, tables, seals, bounding boxes, and markdown; extraction and classification outputs include structured fields, evidence, segments, confidence, and metadata.]\n\n## Skill Version(s):\n\n2.0.4 (source: server release evidence; source files report 2.0.0)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"智能文档处理专家，支持文档解析、信息抽取、文档分类 Skill: 智能文档助手 Owner: ankylala Summary: 智能文档处理专家，支持文档解析、信息抽取、文档分类 Tags: latest:2.0.4 Version history: v2.0.4 | 2026-04-24T16:11:18.455Z | user - Version bump from 2.0.0 to 2.0.4 - No file or documentation changes detected in this release v2.0.3 | 2026-04-24T15:50:28.782Z | user - Enhanced documentation describing DocPilot’s high-precision document parsing, extraction, and classification capabilities. - Detailed explan","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1175,"uniquenessScore":50,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T13:05:41.105Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T13:05:41.105Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:00:35.401Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}