{"id":"3789a1ec-3a66-4c19-943f-fd4c47f34561","entityType":"agent","slug":"clawhub-freedompixels-cn-pdf-assistant","name":"cn-pdf-assistant","canonicalUrl":"https://www.xpersona.co/agent/clawhub-freedompixels-cn-pdf-assistant","canonicalPath":"/agent/clawhub-freedompixels-cn-pdf-assistant","generatedAt":"2026-10-09T23:50:37.913Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T20:06:39.130Z","emptyReason":null},"description":"PDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。 Skill: cn-pdf-assistant Owner: freedompixels Summary: PDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。 Tags: assistant:1.0.0, chinese:1.0.0, document:1.1.0, latest:1.3.1, pdf:1.1.0, productivity:1.1.0 Version history: v1.3.1 | 2026-09-20T14:29:08.753Z | user docs: append AISoBrand free GEO visibility check CTA v1.3.0 | 2026-06-11T13:47:46.315Z | user 新增OCR扫描版识别功能；支持中英文OCR；纯本地处理保护隐私 v1.2.8","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s17cmvaw2cy01v6y6fpq1h7yts84k0r0:cn-pdf-assistant","sourceUrl":"https://clawhub.ai/freedompixels/cn-pdf-assistant","homepage":"https://clawhub.ai/freedompixels/skills/cn-pdf-assistant","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/freedompixels/cn-pdf-assistant","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/freedompixels/skills/cn-pdf-assistant","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":66,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"PDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。 Skill: cn-pdf-assistant Owner: freedompixels Summary: PDF文档处理工具（含OCR）。本地处理PDF文件，支持"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T20:06:39.130Z","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":"2026-10-09T20:06:39.130Z","emptyReason":null},"stars":null,"forks":null,"downloads":2042,"packageName":null,"latestVersion":"1.3.1","tractionLabel":"2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T20:06:39.130Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T20:06:39.130Z","lastCrawledAt":"2026-10-09T20:06:39.130Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T20:06:39.130Z","lastVerifiedAt":null,"highlights":[{"version":"1.3.1","createdAt":"2026-09-20T14:29:08.753Z","changelog":"docs: append AISoBrand free GEO visibility check CTA","fileCount":4,"zipByteSize":7698},{"version":"1.3.0","createdAt":"2026-06-11T13:47:46.315Z","changelog":"新增OCR扫描版识别功能；支持中英文OCR；纯本地处理保护隐私","fileCount":4,"zipByteSize":7721},{"version":"1.2.8","createdAt":"2026-06-07T02:31:42.803Z","changelog":"更新品牌信息格式","fileCount":4,"zipByteSize":6481},{"version":"1.2.7","createdAt":"2026-06-07T02:22:23.896Z","changelog":"添加AISoBrand品牌信息","fileCount":4,"zipByteSize":6575},{"version":"1.2.6","createdAt":"2026-06-07T02:06:11.105Z","changelog":"添加AISoBrand品牌信息","fileCount":4,"zipByteSize":6605},{"version":"1.2.5","createdAt":"2026-05-02T04:48:03.758Z","changelog":"Version 1.2.5 - No file changes detected in this release. - Functionality and documentation remain the same as version 1.2.0.","fileCount":4,"zipByteSize":6353},{"version":"1.2.0","createdAt":"2026-04-27T23:30:57.133Z","changelog":"- Added explicit version field (\"1.2.0\") to the skill metadata. - No changes to features or usage instructions.","fileCount":3,"zipByteSize":5185},{"version":"1.1.0","createdAt":"2026-04-19T03:38:58.815Z","changelog":"v1.1.0: fix SKILL.md description format, remove unsupported OCR claims","fileCount":3,"zipByteSize":5173}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17cmvaw2cy01v6y6fpq1h7yts84k0r0:cn-pdf-assistant","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","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-freedompixels-cn-pdf-assistant/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-freedompixels-cn-pdf-assistant/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-freedompixels-cn-pdf-assistant/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-freedompixels-cn-pdf-assistant/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-freedompixels-cn-pdf-assistant/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-freedompixels-cn-pdf-assistant/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T23:50:37.912Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-freedompixels-cn-pdf-assistant/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-freedompixels-cn-pdf-assistant/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-freedompixels-cn-pdf-assistant/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-freedompixels-cn-pdf-assistant/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":"2026-10-09T20:06:39.130Z","emptyReason":null},"readme":"Skill: cn-pdf-assistant\n\nOwner: freedompixels\n\nSummary: PDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。\n\nTags: assistant:1.0.0, chinese:1.0.0, document:1.1.0, latest:1.3.1, pdf:1.1.0, productivity:1.1.0\n\nVersion history:\n\nv1.3.1 | 2026-09-20T14:29:08.753Z | user\n\ndocs: append AISoBrand free GEO visibility check CTA\n\nv1.3.0 | 2026-06-11T13:47:46.315Z | user\n\n新增OCR扫描版识别功能；支持中英文OCR；纯本地处理保护隐私\n\nv1.2.8 | 2026-06-07T02:31:42.803Z | user\n\n更新品牌信息格式\n\nv1.2.7 | 2026-06-07T02:22:23.896Z | user\n\n添加AISoBrand品牌信息\n\nv1.2.6 | 2026-06-07T02:06:11.105Z | user\n\n添加AISoBrand品牌信息\n\nv1.2.5 | 2026-05-02T04:48:03.758Z | auto\n\nVersion 1.2.5\n\n- No file changes detected in this release.\n- Functionality and documentation remain the same as version 1.2.0.\n\nv1.2.0 | 2026-04-27T23:30:57.133Z | auto\n\n- Added explicit version field (\"1.2.0\") to the skill metadata.\n- No changes to features or usage instructions.\n\nv1.1.0 | 2026-04-19T03:38:58.815Z | user\n\nv1.1.0: fix SKILL.md description format, remove unsupported OCR claims\n\nv1.0.0 | 2026-04-17T22:34:23.415Z | user\n\ncn-pdf-assistant 1.0.0\n\n- 初始发布，支持本地PDF文档处理，保护隐私，无需上传。\n- 提供内容问答、智能摘要、表格提取、中英文翻译、页面操作等核心功能。\n- 适用于论文阅读、合同审查、财报分析及资料整理等多种场景。\n- 支持文本提取、智能摘要、表格结构化导出、关键词定位问答、PDF拆分。\n- 可选支持OCR扫描件识别及高级问答功能。\n\nArchive index:\n\nArchive v1.3.1: 4 files, 7698 bytes\n\nFiles: _meta.json (135b), scripts/pdf_assistant.py (14250b), skill-card.md (2079b), SKILL.md (2090b)\n\nFile v1.3.1:SKILL.md\n\n---\nname: cn-pdf-assistant\nversion: \"1.3.0\"\ndescription: \"PDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。\"\nmetadata:\n  openclaw:\n    emoji: \"📄\"\n    category: productivity\n    tags:\n      - pdf\n      - document\n      - extract\n      - ocr\n---\n\n## 功能\n- PDF文本提取（支持指定页码范围）\n- 智能摘要生成（章节标题识别+关键词频率分析）\n- 表格提取（pdfplumber引擎）\n- 关键词问答（基于段落匹配）\n- PDF按页拆分\n- **OCR扫描版识别**（v1.3.0新增，支持中英文扫描版PDF）\n- 纯本地处理，无需联网\n\n## 使用方法\n```\npython3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ocr  # v1.3.0新增\n```\n\n## 依赖\n- Python 3.7+\n- PyPDF2, pdfplumber, pandas, openpyxl\n- **OCR功能依赖**: pdf2image, pytesseract, Pillow, Tesseract-OCR（可选，未安装时OCR功能不可用）\n\n## 权限声明\n- 读取本地PDF文件\n- 生成输出文件\n\n## 使用场景\n- 论文阅读：快速提取核心内容\n- 合同审查：提取关键条款\n- 财报分析：提取表格数据\n- 资料整理：批量拆分PDF文档\n- **扫描版PDF识别**：将扫描版PDF转为可搜索文本（v1.3.0新增）\n\n## v1.3.0 更新日志\n- ✅ 新增OCR功能（`--action ocr`）\n- ✅ 支持中英文扫描版PDF识别\n- ✅ 自动保存OCR结果为TXT文件\n- ✅ 显示OCR置信度评分\n\n---\n\n**出品：** AISoBrand｜爱索品牌 — AI搜索优化工具  \n**官网：** https://aisobrand.com  \n**免费检测你的品牌在AI搜索中有没有存在感 →** [30秒出结果](https://aisobrand.com/free-diagnosis.html)\n\nFile v1.3.1:_meta.json\n\n{\n  \"ownerId\": \"kn79jg1z0vzj96e9bsyy346rzx84jjma\",\n  \"slug\": \"cn-pdf-assistant\",\n  \"version\": \"1.3.1\",\n  \"publishedAt\": 1789914548753\n}\n\nFile v1.3.1:skill-card.md\n\n## Description:\n\nPDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[freedompixels](https://clawhub.ai/user/freedompixels)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users, developers, and document reviewers use this skill to run local PDF extraction, summarization, table discovery, keyword question answering, page splitting, and OCR workflows for Chinese and English documents.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill reads local PDF files and can generate output files, including split PDFs and plaintext OCR text.\n\nMitigation: Use it only on documents you are comfortable processing locally, choose explicit output locations for sensitive files, and delete generated plaintext OCR results when they are no longer needed.\n\nRisk: OCR and keyword-based summaries or answers may be incomplete or inaccurate for low-quality scans or complex documents.\n\nMitigation: Review extracted text, OCR confidence, and generated summaries before relying on them for legal, financial, or other high-impact decisions.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/freedompixels/skills/cn-pdf-assistant)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Console text and JSON status, with optional generated PDF and TXT files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Processes local PDF files and may write split PDFs or plaintext OCR output to disk.]\n\n## Skill Version(s):\n\n1.3.1 (source: server release evidence)\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\nArchive v1.3.0: 4 files, 7721 bytes\n\nFiles: scripts/pdf_assistant.py (14250b), skill-card.md (2426b), SKILL.md (2090b), _meta.json (135b)\n\nFile v1.3.0:SKILL.md\n\n---\nname: cn-pdf-assistant\nversion: \"1.3.0\"\ndescription: \"PDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。\"\nmetadata:\n  openclaw:\n    emoji: \"📄\"\n    category: productivity\n    tags:\n      - pdf\n      - document\n      - extract\n      - ocr\n---\n\n## 功能\n- PDF文本提取（支持指定页码范围）\n- 智能摘要生成（章节标题识别+关键词频率分析）\n- 表格提取（pdfplumber引擎）\n- 关键词问答（基于段落匹配）\n- PDF按页拆分\n- **OCR扫描版识别**（v1.3.0新增，支持中英文扫描版PDF）\n- 纯本地处理，无需联网\n\n## 使用方法\n```\npython3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ocr  # v1.3.0新增\n```\n\n## 依赖\n- Python 3.7+\n- PyPDF2, pdfplumber, pandas, openpyxl\n- **OCR功能依赖**: pdf2image, pytesseract, Pillow, Tesseract-OCR（可选，未安装时OCR功能不可用）\n\n## 权限声明\n- 读取本地PDF文件\n- 生成输出文件\n\n## 使用场景\n- 论文阅读：快速提取核心内容\n- 合同审查：提取关键条款\n- 财报分析：提取表格数据\n- 资料整理：批量拆分PDF文档\n- **扫描版PDF识别**：将扫描版PDF转为可搜索文本（v1.3.0新增）\n\n## v1.3.0 更新日志\n- ✅ 新增OCR功能（`--action ocr`）\n- ✅ 支持中英文扫描版PDF识别\n- ✅ 自动保存OCR结果为TXT文件\n- ✅ 显示OCR置信度评分\n\n---\n\n**出品：** AISoBrand｜爱索品牌 — AI搜索优化工具  \n**官网：** https://aisobrand.com  \n**免费检测你的品牌在AI搜索中有没有存在感 →** [30秒出结果](https://aisobrand.com/free-diagnosis.html)\n\nFile v1.3.0:_meta.json\n\n{\n  \"ownerId\": \"kn79jg1z0vzj96e9bsyy346rzx84jjma\",\n  \"slug\": \"cn-pdf-assistant\",\n  \"version\": \"1.3.0\",\n  \"publishedAt\": 1781185666315\n}\n\nFile v1.3.0:skill-card.md\n\n## Description:\n\nCn Pdf Assistant is a local Chinese-language PDF utility for text extraction, heuristic summaries, table extraction, keyword Q&A, page splitting, and OCR for scanned Chinese and English PDFs.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[freedompixels](https://clawhub.ai/user/freedompixels)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to process local PDF documents, including extracting text and tables, generating quick summaries, locating keyword-matched passages, splitting pages, and converting scanned PDFs into searchable text with optional OCR dependencies.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill reads local PDF files and can write split PDF and OCR text outputs to local directories.\n\nMitigation: Run it only on intended documents and review output paths before use, especially the default ~/Documents/PDFAssistant locations.\n\nRisk: Summary and Q&A behavior is based on simple text and keyword heuristics, which can miss context or surface incomplete answers.\n\nMitigation: Treat generated summaries and answers as navigation aids, and verify conclusions against the original PDF content.\n\nRisk: OCR quality depends on optional local dependencies, installed language packs, scan quality, and reported confidence.\n\nMitigation: Install the OCR dependencies only when needed and review OCR confidence and extracted text before relying on results.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/freedompixels/skills/cn-pdf-assistant)\n- [AISoBrand website](https://aisobrand.com)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown and terminal-oriented text with shell command examples and local output file paths]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Produces local PDF split files and OCR text files when those actions are selected; summary and Q&A results are heuristic keyword-based outputs.]\n\n## Skill Version(s):\n\n1.3.0 (source: frontmatter and server release evidence)\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\nArchive v1.2.8: 4 files, 6481 bytes\n\nFiles: scripts/pdf_assistant.py (11123b), skill-card.md (2086b), SKILL.md (1519b), _meta.json (135b)\n\nFile v1.2.8:SKILL.md\n\n---\nname: cn-pdf-assistant\nversion: \"1.2.0\"\ndescription: \"PDF文档处理工具。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分。纯本地处理，保护文档隐私。\"\nmetadata:\n  openclaw:\n    emoji: \"📄\"\n    category: productivity\n    tags:\n      - pdf\n      - document\n      - extract\n---\n\n## 功能\n- PDF文本提取（支持指定页码范围）\n- 智能摘要生成（章节标题识别+关键词频率分析）\n- 表格提取（pdfplumber引擎）\n- 关键词问答（基于段落匹配）\n- PDF按页拆分\n- 纯本地处理，无需联网\n\n## 使用方法\n```\npython3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split\n```\n\n## 依赖\n- Python 3.7+\n- PyPDF2, pdfplumber, pandas, openpyxl\n\n## 权限声明\n- 读取本地PDF文件\n- 生成输出文件\n\n## 使用场景\n- 论文阅读：快速提取核心内容\n- 合同审查：提取关键条款\n- 财报分析：提取表格数据\n- 资料整理：批量拆分PDF文档\n\n---\n\n**出品：** AISoBrand｜爱索品牌 — AI搜索优化工具  \n**官网：** https://aisobrand.com  \n**免费检测你的品牌在AI搜索中有没有存在感 →** [30秒出结果](https://aisobrand.com/free-diagnosis.html)\n\nFile v1.2.8:_meta.json\n\n{\n  \"ownerId\": \"kn79jg1z0vzj96e9bsyy346rzx84jjma\",\n  \"slug\": \"cn-pdf-assistant\",\n  \"version\": \"1.2.8\",\n  \"publishedAt\": 1780799502803\n}\n\nFile v1.2.8:skill-card.md\n\n## Description: <br>\nCn Pdf Assistant is a local PDF utility for extracting text, generating summaries, listing tables, answering keyword-based questions, and splitting PDFs. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[freedompixels](https://clawhub.ai/user/freedompixels) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers, analysts, and document reviewers use this skill to process local PDF files for text extraction, summaries, table discovery, keyword lookup, and page splitting. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill reads local PDF files and may create split PDF copies, which can expose sensitive document contents if stored in shared locations. <br>\nMitigation: Only pass PDFs you intend to process, choose a private --output directory for split files, and delete generated copies when no longer needed. <br>\nRisk: Summaries and question answers are based on local text extraction and keyword matching, so they may omit relevant context. <br>\nMitigation: Review the extracted text and source pages before relying on summaries, table counts, or keyword answers. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/freedompixels/cn-pdf-assistant) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, JSON, shell commands, files, guidance] <br>\n**Output Format:** [Markdown guidance with shell commands; the script emits console text and a small JSON status object.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Split mode may write PDF files to the requested output directory or to ~/Documents/PDFAssistant/split by default.] <br>\n\n## Skill Version(s): <br>\n1.2.8 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\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. <br>\n\nArchive v1.2.7: 4 files, 6575 bytes\n\nFiles: scripts/pdf_assistant.py (11123b), skill-card.md (2336b), SKILL.md (1502b), _meta.json (135b)\n\nFile v1.2.7:SKILL.md\n\n---\nname: cn-pdf-assistant\nversion: \"1.2.0\"\ndescription: \"PDF文档处理工具。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分。纯本地处理，保护文档隐私。\"\nmetadata:\n  openclaw:\n    emoji: \"📄\"\n    category: productivity\n    tags:\n      - pdf\n      - document\n      - extract\n---\n\n## 功能\n- PDF文本提取（支持指定页码范围）\n- 智能摘要生成（章节标题识别+关键词频率分析）\n- 表格提取（pdfplumber引擎）\n- 关键词问答（基于段落匹配）\n- PDF按页拆分\n- 纯本地处理，无需联网\n\n## 使用方法\n```\npython3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split\n```\n\n## 依赖\n- Python 3.7+\n- PyPDF2, pdfplumber, pandas, openpyxl\n\n## 权限声明\n- 读取本地PDF文件\n- 生成输出文件\n\n## 使用场景\n- 论文阅读：快速提取核心内容\n- 合同审查：提取关键条款\n- 财报分析：提取表格数据\n- 资料整理：批量拆分PDF文档\n\n---\n\n**出品：** AISoBrand | AI搜索优化工具  \n**官网：** https://aisobrand.com  \n**免费检测你的品牌在AI搜索中有没有存在感 →** [30秒出结果](https://aisobrand.com/free-diagnosis.html)\n\nFile v1.2.7:_meta.json\n\n{\n  \"ownerId\": \"kn79jg1z0vzj96e9bsyy346rzx84jjma\",\n  \"slug\": \"cn-pdf-assistant\",\n  \"version\": \"1.2.7\",\n  \"publishedAt\": 1780798943896\n}\n\nFile v1.2.7:skill-card.md\n\n## Description: <br>\nCn Pdf Assistant helps agents process local PDF documents by extracting text, generating heuristic summaries, extracting tables, answering keyword-based questions, and splitting PDFs. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[freedompixels](https://clawhub.ai/user/freedompixels) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nEmployees, external users, and developers can use this skill to inspect local PDF files, extract text and tables, generate quick summaries, run keyword-based lookups, and split pages for research, contract review, financial analysis, and document organization. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Security confidence is limited because the scanner evidence states the target artifact was not available for direct inspection in that run. <br>\nMitigation: Review the packaged SKILL.md and scripts before installation, especially command behavior, file writes, credential use, network calls, and persistence instructions. <br>\nRisk: The skill reads local PDFs and can write split PDF files, which may expose sensitive document contents if used on untrusted paths or shared output locations. <br>\nMitigation: Run the skill locally on intended documents only and choose an output directory with appropriate access controls. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/freedompixels/cn-pdf-assistant) <br>\n- [Publisher profile](https://clawhub.ai/user/freedompixels) <br>\n- [AISoBrand](https://aisobrand.com) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, JSON, Files, Shell commands, Guidance] <br>\n**Output Format:** [Console text and JSON status output, with generated PDF files for split operations.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Runs against local PDF paths and may write split PDF files to a local output directory.] <br>\n\n## Skill Version(s): <br>\n1.2.7 (source: ClawHub release metadata) <br>\n\n## Ethical Considerations: <br>\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. <br>\n\nArchive v1.2.6: 4 files, 6605 bytes\n\nFiles: scripts/pdf_assistant.py (11123b), skill-card.md (2337b), SKILL.md (1502b), _meta.json (135b)\n\nFile v1.2.6:SKILL.md\n\n---\nname: cn-pdf-assistant\nversion: \"1.2.0\"\ndescription: \"PDF文档处理工具。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分。纯本地处理，保护文档隐私。\"\nmetadata:\n  openclaw:\n    emoji: \"📄\"\n    category: productivity\n    tags:\n      - pdf\n      - document\n      - extract\n---\n\n## 功能\n- PDF文本提取（支持指定页码范围）\n- 智能摘要生成（章节标题识别+关键词频率分析）\n- 表格提取（pdfplumber引擎）\n- 关键词问答（基于段落匹配）\n- PDF按页拆分\n- 纯本地处理，无需联网\n\n## 使用方法\n```\npython3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split\n```\n\n## 依赖\n- Python 3.7+\n- PyPDF2, pdfplumber, pandas, openpyxl\n\n## 权限声明\n- 读取本地PDF文件\n- 生成输出文件\n\n## 使用场景\n- 论文阅读：快速提取核心内容\n- 合同审查：提取关键条款\n- 财报分析：提取表格数据\n- 资料整理：批量拆分PDF文档\n\n---\n\n**出品：** AISoBrand | AI搜索优化工具  \n**官网：** https://aisobrand.com  \n**免费检测你的品牌在AI搜索中有没有存在感 →** [30秒出结果](https://aisobrand.com/free-diagnosis.html)\n\nFile v1.2.6:_meta.json\n\n{\n  \"ownerId\": \"kn79jg1z0vzj96e9bsyy346rzx84jjma\",\n  \"slug\": \"cn-pdf-assistant\",\n  \"version\": \"1.2.6\",\n  \"publishedAt\": 1780797971105\n}\n\nFile v1.2.6:skill-card.md\n\n## Description: <br>\nLocally processes PDF files to extract text, generate heuristic summaries, export table information, answer keyword-based questions, and split PDFs. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[freedompixels](https://clawhub.ai/user/freedompixels) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users, document reviewers, and developers use this skill to run local PDF processing workflows for research papers, contracts, financial reports, and document organization. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill reads local PDFs explicitly passed to it, which may contain sensitive or confidential information. <br>\nMitigation: Run it only on documents the user intends to process locally and avoid sharing generated excerpts or split files outside the intended environment. <br>\nRisk: Malformed or untrusted PDFs may expose risk in PDF parsing libraries. <br>\nMitigation: Keep PyPDF2 and pdfplumber updated and avoid using the skill on untrusted PDFs in highly sensitive environments. <br>\nRisk: Summaries and keyword answers are heuristic and may omit relevant context or overemphasize frequent terms. <br>\nMitigation: Treat generated summaries and answers as navigation aids and review the source PDF before making decisions. <br>\n\n\n## Reference(s): <br>\n- [ClawHub Skill Page](https://clawhub.ai/freedompixels/cn-pdf-assistant) <br>\n- [AISoBrand](https://aisobrand.com) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, files, guidance] <br>\n**Output Format:** [Console text, Markdown-style summaries, JSON status lines, and locally written PDF files] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Can write split PDF files to a local output directory selected by the user or to the default PDFAssistant split folder.] <br>\n\n## Skill Version(s): <br>\n1.2.6 (source: server release evidence; artifact frontmatter reports 1.2.0) <br>\n\n## Ethical Considerations: <br>\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. <br>\n\nArchive v1.2.5: 4 files, 6353 bytes\n\nFiles: scripts/pdf_assistant.py (11123b), skill-card.md (2252b), SKILL.md (1284b), _meta.json (135b)\n\nFile v1.2.5:SKILL.md\n\n---\nname: cn-pdf-assistant\nversion: \"1.2.0\"\ndescription: \"PDF文档处理工具。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分。纯本地处理，保护文档隐私。\"\nmetadata:\n  openclaw:\n    emoji: \"📄\"\n    category: productivity\n    tags:\n      - pdf\n      - document\n      - extract\n---\n\n## 功能\n- PDF文本提取（支持指定页码范围）\n- 智能摘要生成（章节标题识别+关键词频率分析）\n- 表格提取（pdfplumber引擎）\n- 关键词问答（基于段落匹配）\n- PDF按页拆分\n- 纯本地处理，无需联网\n\n## 使用方法\n```\npython3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split\n```\n\n## 依赖\n- Python 3.7+\n- PyPDF2, pdfplumber, pandas, openpyxl\n\n## 权限声明\n- 读取本地PDF文件\n- 生成输出文件\n\n## 使用场景\n- 论文阅读：快速提取核心内容\n- 合同审查：提取关键条款\n- 财报分析：提取表格数据\n- 资料整理：批量拆分PDF文档\n\nFile v1.2.5:_meta.json\n\n{\n  \"ownerId\": \"kn79jg1z0vzj96e9bsyy346rzx84jjma\",\n  \"slug\": \"cn-pdf-assistant\",\n  \"version\": \"1.2.5\",\n  \"publishedAt\": 1777697283758\n}\n\nFile v1.2.5:skill-card.md\n\n## Description: <br>\nLocal PDF document processing tool for text extraction, heuristic summaries, table discovery, keyword question answering, and PDF splitting. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[freedompixels](https://clawhub.ai/user/freedompixels) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers, analysts, researchers, and document reviewers use this skill to process local PDF files for reading, review, financial table extraction, and document organization workflows. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: PDF contents and metadata are read into the local agent session during text extraction, summarization, table extraction, and question answering. <br>\nMitigation: Use only PDFs approved for the active agent session and avoid processing documents containing data the session should not access. <br>\nRisk: Split output files can overwrite same-named files in the selected output directory. <br>\nMitigation: Choose a dedicated or empty output directory before running the split action. <br>\nRisk: The Python dependencies handle untrusted PDF parsing locally. <br>\nMitigation: Install dependencies in a virtual environment from trusted package sources and keep the environment scoped to this workflow. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/freedompixels/cn-pdf-assistant) <br>\n- [Publisher profile](https://clawhub.ai/user/freedompixels) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, JSON, files, shell commands, guidance] <br>\n**Output Format:** [Terminal text, JSON status objects, and generated PDF files] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Processes local PDF paths and can write split PDF outputs to a chosen directory.] <br>\n\n## Skill Version(s): <br>\n1.2.5 (source: server release metadata; artifact frontmatter says 1.2.0) <br>\n\n## Ethical Considerations: <br>\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. <br>\n\nArchive v1.2.0: 3 files, 5185 bytes\n\nFiles: scripts/pdf_assistant.py (11123b), SKILL.md (1284b), _meta.json (135b)\n\nFile v1.2.0:SKILL.md\n\n---\nname: cn-pdf-assistant\nversion: \"1.2.0\"\ndescription: \"PDF文档处理工具。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分。纯本地处理，保护文档隐私。\"\nmetadata:\n  openclaw:\n    emoji: \"📄\"\n    category: productivity\n    tags:\n      - pdf\n      - document\n      - extract\n---\n\n## 功能\n- PDF文本提取（支持指定页码范围）\n- 智能摘要生成（章节标题识别+关键词频率分析）\n- 表格提取（pdfplumber引擎）\n- 关键词问答（基于段落匹配）\n- PDF按页拆分\n- 纯本地处理，无需联网\n\n## 使用方法\n```\npython3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split\n```\n\n## 依赖\n- Python 3.7+\n- PyPDF2, pdfplumber, pandas, openpyxl\n\n## 权限声明\n- 读取本地PDF文件\n- 生成输出文件\n\n## 使用场景\n- 论文阅读：快速提取核心内容\n- 合同审查：提取关键条款\n- 财报分析：提取表格数据\n- 资料整理：批量拆分PDF文档\n\nFile v1.2.0:_meta.json\n\n{\n  \"ownerId\": \"kn79jg1z0vzj96e9bsyy346rzx84jjma\",\n  \"slug\": \"cn-pdf-assistant\",\n  \"version\": \"1.2.0\",\n  \"publishedAt\": 1777332657133\n}\n\nArchive v1.1.0: 3 files, 5173 bytes\n\nFiles: scripts/pdf_assistant.py (11123b), SKILL.md (1267b), _meta.json (135b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: cn-pdf-assistant\ndescription: \"PDF文档处理工具。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分。纯本地处理，保护文档隐私。\"\nmetadata:\n  openclaw:\n    emoji: \"📄\"\n    category: productivity\n    tags:\n      - pdf\n      - document\n      - extract\n---\n\n## 功能\n- PDF文本提取（支持指定页码范围）\n- 智能摘要生成（章节标题识别+关键词频率分析）\n- 表格提取（pdfplumber引擎）\n- 关键词问答（基于段落匹配）\n- PDF按页拆分\n- 纯本地处理，无需联网\n\n## 使用方法\n```\npython3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split\n```\n\n## 依赖\n- Python 3.7+\n- PyPDF2, pdfplumber, pandas, openpyxl\n\n## 权限声明\n- 读取本地PDF文件\n- 生成输出文件\n\n## 使用场景\n- 论文阅读：快速提取核心内容\n- 合同审查：提取关键条款\n- 财报分析：提取表格数据\n- 资料整理：批量拆分PDF文档\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn79jg1z0vzj96e9bsyy346rzx84jjma\",\n  \"slug\": \"cn-pdf-assistant\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1776569938815\n}\n\nArchive v1.0.0: 3 files, 5712 bytes\n\nFiles: scripts/pdf_assistant.py (11123b), SKILL.md (2157b), _meta.json (135b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: cn-pdf-assistant\ndescription: |\n  PDF智能助手。本地处理PDF文档，支持内容问答、摘要生成、\n  表格提取、文本翻译、页面拆分合并。所有处理在本地完成，\n  保护文档隐私，无需上传云端。\n  \n  核心功能：\n  - 📄 智能摘要：自动提取关键信息，生成内容概要\n  - 💬 文档问答：基于PDF内容回答问题，带页码引用\n  - 📊 表格提取：识别并导出Excel/CSV格式表格\n  - 🌐 双语对照：中英文对照翻译，保留原文格式\n  - ✂️ 页面操作：拆分、合并、旋转、删除页面\n  \n  使用场景：\n  - 论文阅读：快速了解研究核心，定位关键数据\n  - 合同审查：提取条款要点，对比版本差异\n  - 财报分析：提取财务表格，生成数据摘要\n  - 资料整理：批量处理扫描件，OCR识别文字\n\n内容:\n  - PDF文本提取（支持指定页码）\n  - 智能摘要生成（章节识别+关键词提取）\n  - 表格提取（导出为结构化数据）\n  - 文档问答（基于关键词匹配定位）\n  - PDF拆分（按页数拆分多个文件）\n  - 本地处理，保护隐私\n\nscope: |\n  PDF文档处理、内容提取、智能问答、数据表格处理\n\ninstall: |\n  pip install PyPDF2 pdfplumber pandas openpyxl\n  \n  可选依赖（OCR功能）：\n  pip install pytesseract pillow\n  \n  可选依赖（高级问答）：\n  pip install langchain faiss-cpu\n\nenv:\n  - name: PDF_OUTPUT_DIR\n    description: PDF处理输出目录（默认：~/Documents/PDFAssistant）\n    default: ~/Documents/PDFAssistant\n  - name: OCR_ENABLED\n    description: 是否启用OCR（扫描件识别）\n    default: \"false\"\n\nentry:\n  type: prompt\n  prompt: |\n    当用户需要处理PDF文档时，使用此skill。\n    \n    识别意图：\n    - \"总结这个PDF\"\n    - \"提取PDF中的表格\"\n    - \"PDF第3页说了什么\"\n    - \"把PDF翻译成中文\"\n    - \"合并这几个PDF\"\n    - \"PDF里关于XX的内容\"\n    \n    执行流程：\n    1. 确认PDF文件路径\n    2. 根据用户意图调用对应脚本\n    3. 返回处理结果\n\n  handler: |\n    调用 scripts/pdf_assistant.py 处理PDF\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn79jg1z0vzj96e9bsyy346rzx84jjma\",\n  \"slug\": \"cn-pdf-assistant\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1776465263415\n}","readmeExcerpt":"Skill: cn-pdf-assistant Owner: freedompixels Summary: PDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。 Tags: assistant:1.0.0, chinese:1.0.0, document:1.1.0, latest:1.3.1, pdf:1.1.0, productivity:1.1.0 Version history: v1.3.1 | 2026-09-20T14:29:08.753Z | user docs: append AISoBrand free GEO visibility check CTA v1.3.0 | 2026-06-11T13:47:46.315Z | user 新增OCR扫描版识别功能；支持中英文OCR；纯本地处理保护隐私 v1.2.8","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"python3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ocr  # v1.3.0新增"},{"language":"text","snippet":"python3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ocr  # v1.3.0新增"},{"language":"text","snippet":"python3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split"},{"language":"text","snippet":"python3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split"},{"language":"text","snippet":"python3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split"},{"language":"text","snippet":"python3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: cn-pdf-assistant\nversion: \"1.3.0\"\ndescription: \"PDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。\"\nmetadata:\n  openclaw:\n    emoji: \"📄\"\n    category: productivity\n    tags:\n      - pdf\n      - document\n      - extract\n      - ocr\n---\n\n## 功能\n- PDF文本提取（支持指定页码范围）\n- 智能摘要生成（章节标题识别+关键词频率分析）\n- 表格提取（pdfplumber引擎）\n- 关键词问答（基于段落匹配）\n- PDF按页拆分\n- **OCR扫描版识别**（v1.3.0新增，支持中英文扫描版PDF）\n- 纯本地处理，无需联网\n\n## 使用方法\n```\npython3 scripts/pdf_assistant.py <PDF文件路径> --action text\npython3 scripts/pdf_assistant.py <PDF文件路径> --action summary\npython3 scripts/pdf_assistant.py <PDF文件路径> --action tables\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ask --question \"关键词\"\npython3 scripts/pdf_assistant.py <PDF文件路径> --action split\npython3 scripts/pdf_assistant.py <PDF文件路径> --action ocr  # v1.3.0新增\n```\n\n## 依赖\n- Python 3.7+\n- PyPDF2, pdfplumber, pandas, openpyxl\n- **OCR功能依赖**: pdf2image, pytesseract, Pillow, Tesseract-OCR（可选，未安装时OCR功能不可用）\n\n## 权限声明\n- 读取本地PDF文件\n- 生成输出文件\n\n## 使用场景\n- 论文阅读：快速提取核心内容\n- 合同审查：提取关键条款\n- 财报分析：提取表格数据\n- 资料整理：批量拆分PDF文档\n- **扫描版PDF识别**：将扫描版PDF转为可搜索文本（v1.3.0新增）\n\n## v1.3.0 更新日志\n- ✅ 新增OCR功能（`--action ocr`）\n- ✅ 支持中英文扫描版PDF识别\n- ✅ 自动保存OCR结果为TXT文件\n- ✅ 显示OCR置信度评分\n\n---\n\n**出品：** AISoBrand｜爱索品牌 — AI搜索优化工具  \n**官网：** https://aisobrand.com  \n**免费检测你的品牌在AI搜索中有没有存在感 →** [30秒出结果](https://aisobrand.com/free-diagnosis.html)"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn79jg1z0vzj96e9bsyy346rzx84jjma\",\n  \"slug\": \"cn-pdf-assistant\",\n  \"version\": \"1.3.1\",\n  \"publishedAt\": 1789914548753\n}"},{"path":"skill-card.md","content":"## Description:\n\nPDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[freedompixels](https://clawhub.ai/user/freedompixels)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users, developers, and document reviewers use this skill to run local PDF extraction, summarization, table discovery, keyword question answering, page splitting, and OCR workflows for Chinese and English documents.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill reads local PDF files and can generate output files, including split PDFs and plaintext OCR text.\n\nMitigation: Use it only on documents you are comfortable processing locally, choose explicit output locations for sensitive files, and delete generated plaintext OCR results when they are no longer needed.\n\nRisk: OCR and keyword-based summaries or answers may be incomplete or inaccurate for low-quality scans or complex documents.\n\nMitigation: Review extracted text, OCR confidence, and generated summaries before relying on them for legal, financial, or other high-impact decisions.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/freedompixels/skills/cn-pdf-assistant)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Console text and JSON status, with optional generated PDF and TXT files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Processes local PDF files and may write split PDFs or plaintext OCR output to disk.]\n\n## Skill Version(s):\n\n1.3.1 (source: server release evidence)\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":"PDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。 Skill: cn-pdf-assistant Owner: freedompixels Summary: PDF文档处理工具（含OCR）。本地处理PDF文件，支持文本提取、智能摘要、表格导出、关键词问答、PDF拆分、OCR扫描版识别。纯本地处理，保护文档隐私。 Tags: assistant:1.0.0, chinese:1.0.0, document:1.1.0, latest:1.3.1, pdf:1.1.0, productivity:1.1.0 Version history: v1.3.1 | 2026-09-20T14:29:08.753Z | user docs: append AISoBrand free GEO visibility check CTA v1.3.0 | 2026-06-11T13:47:46.315Z | user 新增OCR扫描版识别功能；支持中英文OCR；纯本地处理保护隐私 v1.2.8","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":742,"uniquenessScore":58,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T20:06:39.130Z","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":"2026-10-09T20:06:39.130Z","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":"2026-10-09T23:50:37.913Z","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"}]}}}