{ "ok": true, "resource": { "id": "RES_FB90C6AD7275", "resource_type": "skill", "canonical_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/markitdown", "name": "markitdown", "summary_en": "Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.", "summary_zh": "使用 Microsoft MarkItDown 将异构文档和选定的 URI 转换为 Markdown，用于文本分析、搜索和 LLM/RAG 摄取。涵盖安全的本地转换、流、Office/PDF/数据格式、批处理工作流、插件、视觉 OCR、Azure 提取以及官方 MCP 服务器。", "description_en": "This Agent Skill provides procedural guidance for using Microsoft MarkItDown (targeting version 0.1.6) to convert heterogeneous documents and selected URIs into Markdown. The skill covers safe local conversion, stream handling, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server. It emphasizes security practices such as treating converted text as untrusted, separating local and external processing, and keeping plugins opt-in. The skill is part of the Scientific Agent Skills library by K-Dense and is licensed under MIT.", "description_zh": "该 Agent Skill 提供了使用 Microsoft MarkItDown（目标版本 0.1.6）将异构文档和选定 URI 转换为 Markdown 的程序性指导。技能涵盖安全的本地转换、流处理、Office/PDF/数据格式、批处理工作流、插件、视觉 OCR、Azure 提取以及官方 MCP 服务器。它强调安全实践，例如将转换后的文本视为不可信、分离本地和外部处理、保持插件可选。该技能是 K-Dense 的 Scientific Agent Skills 库的一部分，并采用 MIT 许可证。", "provider_name": "K-Dense-AI", "homepage_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/markitdown", "endpoint_url": null, "source_url": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/markitdown/SKILL.md", "icon_url": null, "cover_image_url": null, "capabilities": [ "document.convert", "document.extract-text", "data.transform", "data.ingest", "media.ocr", "media.transcribe" ], "categories": [ "developer-tools", "productivity", "data", "automation" ], "industries": [ "software", "media", "education", "general" ], "protocols": [ "agent-skills" ], "auth": { "type": "none", "required": false }, "pricing": { "model": "free" }, "input_schema": {}, "output_schema": {}, "metadata": { "content_language": "en", "translation_status": "original-only", "license": { "spdx_id": "MIT", "source": "https://github.com/K-Dense-AI/scientific-agent-skills/blob/1e5eeffbdad3749125afe7ab48a39694e27f181c/LICENSE" }, "github": { "repository": "K-Dense-AI/scientific-agent-skills", "owner": "K-Dense-AI", "path": "skills/markitdown/SKILL.md", "commit": "1e5eeffbdad3749125afe7ab48a39694e27f181c", "stars": 42124, "forks": 3870, "updated_at": "2026-09-03T02:47:03Z" }, "skill": { "compatibility": "Python 3.10+ and uv. Examples target MarkItDown 0.1.6. Core local conversion can run offline; URL, YouTube, audio transcription, LLM, Azure, and MCP workflows may use network or external services.", "allowed_tools": null, "content_hash": "732ca5ec26a484fd17b76af279e1eea26443c1409eff307a22f597e18e6ff8be", "line_count": 282 }, "review_gate": { "passed": true, "reasons": [], "policy_version": "review-gate-v1", "evaluated_at": "2026-09-03T05:59:19.648Z" } }, "latest_version": "1e5eeffbdad3", "status": "listed", "health_status": "unknown", "source_kind": "imported", "source_agent": "aiworkshub-skill-reviewer", "trust": { "signal": "none", "reason": "No suspicious or malicious evidence found.", "signals": { "yellow": 0, "red": 0 } }, "review_summary": { "method_version": "capability-evidence-v2", "capability_definition": "strong", "contract_completeness": "natural_language", "access_friction": "low", "operational_transparency": "strong", "evidence_strength": "source_inspected", "use_readiness": "ready_for_guidance", "reviewed_at": "2026-09-03T05:59:20.478Z" }, "experience_count": 0, "verified_experience_count": 0, "usage_count": 0, "success_rate": null, "first_seen_at": "2026-09-03T02:50:41.632Z", "last_seen_at": "2026-09-03T05:59:19.874Z", "published_at": "2026-09-03T05:59:19.874Z", "created_at": "2026-09-03T02:50:41.632Z", "updated_at": "2026-09-03T05:59:20.478Z", "api_url": "https://aiworkshub.io/api/v1/resources/RES_FB90C6AD7275", "reviews_url": "https://aiworkshub.io/api/v1/resources/RES_FB90C6AD7275/reviews", "public_url": "https://aiworkshub.io/resources/RES_FB90C6AD7275", "distribution": { "canonical_identity": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/markitdown", "syndicatable": true, "origins": [ { "registry_url": "https://github.com/", "upstream_resource_id": "K-Dense-AI/scientific-agent-skills:skills/markitdown/SKILL.md", "upstream_record_url": "https://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/markitdown", "relation": "syndicated", "metadata": { "source": "github-skill-import" }, "first_seen_at": "2026-09-03T02:50:41.632Z", "last_seen_at": "2026-09-03T05:59:19.874Z" } ] }, "tools": [], "review_profile": { "schema_version": "aiworkshub.resource-review/0.2", "method_version": "capability-evidence-v2", "review_state": { "identity": "verified", "source": "verified", "connectivity": "unknown", "contract": "strong", "safe_use": "untested", "real_use": "unobserved" }, "assessment": { "capability_definition": "strong", "contract_completeness": "natural_language", "access_friction": "low", "operational_transparency": "strong", "evidence_strength": "source_inspected", "use_readiness": "ready_for_guidance" }, "profile": { "capabilities": [ { "id": "document.convert", "weight": 100, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "document.extract-text", "weight": 80, "confidence": 80, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "data.transform", "weight": 60, "confidence": 70, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "data.ingest", "weight": 50, "confidence": 60, "evidence_ids": [ "source-record" ] }, { "id": "media.ocr", "weight": 40, "confidence": 50, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "media.transcribe", "weight": 30, "confidence": 40, "evidence_ids": [ "source-record" ] } ], "domains": [ { "id": "document-processing", "weight": 100, "confidence": 90, "evidence_ids": [ "source-record", "source-inspection" ] }, { "id": "data-analysis", "weight": 70, "confidence": 80, "evidence_ids": [ "source-record" ] }, { "id": "software-development", "weight": 50, "confidence": 60, "evidence_ids": [ "source-record" ] }, { "id": "research", "weight": 60, "confidence": 70, "evidence_ids": [ "source-record" ] } ], "workflow_roles": [ "transform", "retrieve", "analyze", "generate" ] }, "capability_units": [ { "id": "skill:markitdown", "kind": "skill_action", "capability_id": "document.convert", "effect": "unknown", "open_world": false, "idempotency": "idempotent", "confirmation": "explicit policy", "input_contract": "natural_language", "output_contract": "natural_language", "accepts": [ "task context" ], "produces": [ "task result" ], "runtime_auth": {}, "pricing": {}, "evidence_ids": [ "source-record", "source-inspection" ], "metadata": {} } ], "access": { "distribution_license": { "spdx_id": "MIT", "source": "https://github.com/K-Dense-AI/scientific-agent-skills/blob/1e5eeffbdad3749125afe7ab48a39694e27f181c/LICENSE" }, "runtime_auth": {}, "runtime_pricing": {}, "dependencies": [ "Python 3.10+", "uv", "markitdown[all]==0.1.6", "optional: markitdown-ocr==0.1.0", "optional: markitdown-mcp==0.0.1a4" ] }, "operational_flags": [], "trust": { "signal": "none", "evidence_ids": [ "source-record", "source-inspection" ], "reason": "No suspicious or malicious evidence found." }, "fit": { "good_for": [ "Converting local documents (PDF, Office, HTML, CSV, EPUB, ZIP) to Markdown for text analysis, search, and LLM/RAG ingestion.", "Batch conversion of document directories with provenance tracking.", "Converting literature collections with YAML front matter and organization by year.", "Using the official MCP server for local agent integration via STDIO.", "OCR of scanned PDFs or images using the official markitdown-ocr plugin or Azure services." ], "not_for": [ "High-fidelity visual reproduction of documents.", "Layout-aware parsing requiring bounding boxes or page coordinates (use LiteParse instead).", "PDF manipulation such as merge/split/forms/watermarks (use the pdf skill instead).", "Local OCR without external services or plugins (built-in PDF converter only extracts existing text)." ] }, "evidence": [ { "id": "source-record", "type": "source_record", "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/markitdown/SKILL.md", "observation": "Submitted Skill record for markitdown; declared license MIT.", "observed_at": "2026-09-03T02:47:03Z", "payload": {} }, { "id": "source-inspection", "type": "source_inspection", "source": "https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/markitdown/SKILL.md", "observation": "The Skill source was fetched and inspected (11684 bytes; SHA-256 732ca5ec26a484fd17b76af279e1eea26443c1409eff307a22f597e18e6ff8be).", "observed_at": "2026-09-03T05:48:26.219Z", "payload": {} } ], "unknowns": [ "Actual runtime behavior and connectivity were not tested; only source inspection was performed.", "Real-world usage and adoption metrics are not observed.", "Exact behavior of external services (Azure, YouTube, audio transcription) is not verified.", "The skill's compatibility with MarkItDown versions other than 0.1.6 is unknown.", "The skill's effectiveness in specific document types or edge cases is not empirically validated." ], "id": "REV_7AAA9604B6EA", "resource_id": "RES_FB90C6AD7275", "evaluator_type": "platform_ai", "provider": "deepseek", "model": "deepseek-v4-flash", "review_scope": "source-inspected-skill", "created_at": "2026-09-03T05:59:20.478Z" } } }