MarkItDown
Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcription, HTML, YouTube and direct URLs. Use when the user asks to read / analyze / summarize / extract / translate / Q
as observed 2026-10-12T15:36:43.438Z- Identifier
markitdown-skill- Source
- ClawHub
- Version observed
- 1.8.11
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-09-02T06:49:02.991Z
- Observations recorded
- 18
- Installs (reported upstream)
- 1
- Weekly downloads (upstream)
- 520
- Declared license
- MIT-0
Observation history
2026-10-12T15:36:43.438Z
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"中英双语文档一致性修复：v1.8.9 已将 token 节省上报改为严格 opt-in（未设置 SAVINGS_URL 时零请求），本版清除 SKILL.md 个别章节残留的旧「自动上报」措辞（触发表/数据流表/组件清单/章节标题，ClawHub SkillSpector TP4/SDI-4 复扫指认），全文统一为单一真实数据流模型；无代码变更；版本对齐 | "中英双语文档措辞精度修复：token_saver 描述由「runs entirely offline」校准为「offline by default；可选 --report 推送需显式设置 SAVINGS_URL」——该脚本确有 opt-in 联网路径（默认零请求），旧措辞把保证说满了，ClawHub SkillSpector TP4 指认；无代码变更，行为 |
latestVersion |
"1.8.10" | "1.8.11" |
summary |
"Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr | "Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr |
2026-10-11T14:42:02.570Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"中英双语安全修复：token 节省上报（report_savings.py）改为严格 opt-in——未显式设置 SAVINGS_URL 时默认完全禁用，除抓取目标 URL 外零网络请求（含本机回环），消除腾讯云鼎实验室与 ClawHub SkillSpector 指认的披露与默认行为矛盾；SKILL.md/README/SECURITY 数据流披露同步校 | "中英双语文档一致性修复：v1.8.9 已将 token 节省上报改为严格 opt-in（未设置 SAVINGS_URL 时零请求），本版清除 SKILL.md 个别章节残留的旧「自动上报」措辞（触发表/数据流表/组件清单/章节标题，ClawHub SkillSpector TP4/SDI-4 复扫指认），全文统一为单一真实数据流模型；无代码变更；版本对齐 |
latestVersion |
"1.8.9" | "1.8.10" |
2026-10-10T14:15:52.413Z
Fields that differed: changelog displayName latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Neutralized public release: removed internal-architecture references (pm-dashboard / 看板 / collector.js / 隧道 / open-dashboard-tunnel.cmd) from docs and scripts while keeping the op | "中英双语安全修复：token 节省上报（report_savings.py）改为严格 opt-in——未显式设置 SAVINGS_URL 时默认完全禁用，除抓取目标 URL 外零网络请求（含本机回环），消除腾讯云鼎实验室与 ClawHub SkillSpector 指认的披露与默认行为矛盾；SKILL.md/README/SECURITY 数据流披露同步校 |
displayName |
"MarkItDown 安全版" | "MarkItDown" |
latestVersion |
"1.8.8" | "1.8.9" |
summary |
"Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr | "Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr |
2026-10-09T13:20:37.280Z
Fields that differed: changelog displayName latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Adds --browser-fallback auto|off|always as an explicit informed choice for the local-browser fallback (auto now prints a one-off notice); legacy --no-browser/--force-browser still | "Neutralized public release: removed internal-architecture references (pm-dashboard / 看板 / collector.js / 隧道 / open-dashboard-tunnel.cmd) from docs and scripts while keeping the op |
displayName |
"MarkItDown" | "MarkItDown 安全版" |
latestVersion |
"1.8.5" | "1.8.8" |
summary |
"Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr | "Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr |
2026-10-08T12:19:32.804Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Security hardening: bounded response read in the SPA JSON fallback path; reworded documentation comments that static analyzers read as embedded prompt-injection text; explicit cap | "Adds --browser-fallback auto|off|always as an explicit informed choice for the local-browser fallback (auto now prints a one-off notice); legacy --no-browser/--force-browser still |
latestVersion |
"1.8.3" | "1.8.5" |
2026-10-06T10:50:34.888Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v1.8.0: SSRF hardening (response/decompressed size caps, redirect-hop limit, reject embedded credentials); prompt-injection boundary (--sanitize); per-conversion provenance manife | "Security hardening: bounded response read in the SPA JSON fallback path; reworded documentation comments that static analyzers read as embedded prompt-injection text; explicit cap |
latestVersion |
"1.8.0" | "1.8.3" |
2026-09-21T23:20:53.854Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Fix silent mojibake on gzip/deflate/brotli responses: Content-Encoding is now decompressed before decoding (urllib does not auto-decompress, so compressed bodies were silently dec | "v1.8.0: SSRF hardening (response/decompressed size caps, redirect-hop limit, reject embedded credentials); prompt-injection boundary (--sanitize); per-conversion provenance manife |
latestVersion |
"1.7.9" | "1.8.0" |
2026-09-17T19:21:46.989Z
Fields that differed: license description
| Field | Before | After |
|---|---|---|
license |
null | "MIT-0" |
description |
"Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr | null |
2026-09-15T17:18:40.266Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Declare network + environment capabilities in allowed-tools (least-privilege alignment). Neutral wording for the permission-check docs. Description names the optional local token- | "Fix silent mojibake on gzip/deflate/brotli responses: Content-Encoding is now decompressed before decoding (urllib does not auto-decompress, so compressed bodies were silently dec |
latestVersion |
"1.7.7" | "1.7.9" |
2026-09-13T15:17:50.529Z
Fields that differed: changelog description latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Harden MARKITDOWN_BIN: strict allowlist (absolute path to a regular file; on POSIX must be executable and not group/world-writable) with fallback to python -m markitdown. Docs: sa | "Declare network + environment capabilities in allowed-tools (least-privilege alignment). Neutral wording for the permission-check docs. Description names the optional local token- |
description |
"Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr | "Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr |
latestVersion |
"1.7.6" | "1.7.7" |
summary |
"Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr | "Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr |
2026-09-12T14:17:54.398Z
Fields that differed: changelog description latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"MarkItDown Skill 1.7.4\n\n- Expanded documentation with detailed best practices, security boundaries, and privacy clarification for converting web pages and documents to Markdown. | "Harden MARKITDOWN_BIN: strict allowlist (absolute path to a regular file; on POSIX must be executable and not group/world-writable) with fallback to python -m markitdown. Docs: sa |
description |
"Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Supports PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video trans | "Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr |
latestVersion |
"1.7.4" | "1.7.6" |
summary |
"Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Supports PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video trans | "Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Covers PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video transcr |
2026-09-10T12:18:05.693Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"**MarkItDown Skill 1.7.3**\n\n- Updated documentation to emphasize the recommended workflow for converting web pages (especially WeChat articles) to Markdown before analysis, incl | "MarkItDown Skill 1.7.4\n\n- Expanded documentation with detailed best practices, security boundaries, and privacy clarification for converting web pages and documents to Markdown. |
latestVersion |
"1.7.3" | "1.7.4" |
2026-09-09T11:17:27.097Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"markitdown-skill 1.7.2\n\n- Improved and clarified usage recommendations for converting web pages (including WeChat articles) to Markdown using scripts/url_to_markdown.py, with fa | "**MarkItDown Skill 1.7.3**\n\n- Updated documentation to emphasize the recommended workflow for converting web pages (especially WeChat articles) to Markdown before analysis, incl |
latestVersion |
"1.7.2" | "1.7.3" |
2026-09-08T10:18:19.235Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"- Improved documentation and usage guide for safely converting documents and web pages to Markdown using Microsoft's MarkItDown.\n- Updated best practices for handling a wide rang | "markitdown-skill 1.7.2\n\n- Improved and clarified usage recommendations for converting web pages (including WeChat articles) to Markdown using scripts/url_to_markdown.py, with fa |
latestVersion |
"1.7.1" | "1.7.2" |
2026-09-07T09:39:20.468Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"- Added detailed usage instructions and safety guidelines for converting documents and web pages to Markdown using Microsoft's markitdown CLI.\n- Clarified recommended workflow fo | "- Improved documentation and usage guide for safely converting documents and web pages to Markdown using Microsoft's MarkItDown.\n- Updated best practices for handling a wide rang |
latestVersion |
"1.6.0" | "1.7.1" |
2026-09-06T09:04:43.486Z
Fields that differed: changelog description latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"MarkItDown Skill v1.5.2\n\n- Updated and expanded documentation (SKILL.md) with detailed usage guidance, best practices, and security boundaries for document/webpage conversion.\n | "- Added detailed usage instructions and safety guidelines for converting documents and web pages to Markdown using Microsoft's markitdown CLI.\n- Clarified recommended workflow fo |
description |
"Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Supports PDF, Word, PowerPoint, Excel, images (OCR), audio/video transcription, HTML, Y | "Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Supports PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video trans |
latestVersion |
"1.5.2" | "1.6.0" |
summary |
"Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Supports PDF, Word, PowerPoint, Excel, images (OCR), audio/video transcription, HTML, Y | "Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Supports PDF, Word, PowerPoint, Excel, images (EXIF/LLM description), audio/video trans |
2026-09-03T07:20:35.503Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v1.5.0: P0 正文/boilerplate 检测(含 S3 链接密度补丁); P1a 微信文章结构化抽取; P1b 音视频依赖自检与优雅降级; 英文文档站与中文 UGC 长文边界测试通过。" | "MarkItDown Skill v1.5.2\n\n- Updated and expanded documentation (SKILL.md) with detailed usage guidance, best practices, and security boundaries for document/webpage conversion.\n |
latestVersion |
"1.5.0" | "1.5.2" |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.