[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ES7G6VPD0RCTVKYF8N6ETE":3,"skill-same:01M7ES7G6VPD0RCTVKYF8N6ETE":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7ES7G6VPD0RCTVKYF8N6ETE","view-pdf",null,"Interactive PDF viewer. Use when the user wants to open, show, or view a PDF and collaborate on it visually — annotate, highlight, stamp, fill form fields, place signature\u002Finitials, or review markup together. Not for summarization or text extraction (use native Read instead).","TanNhatCMS\u002Fjarvis","TanNhatCMS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113796420?v=4","01M753MV17KG5CD3152G3WQEQY","KietNT","01M7EKEDYVYQ6PWVJJMZ911VMX",0,"MIT","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-kw-view-pdf\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: view-pdf\ndescription: Interactive PDF viewer. Use when the user wants to open, show, or view a PDF and collaborate on it visually — annotate, highlight, stamp, fill form fields, place signature\u002Finitials, or review markup together. Not for summarization or text extraction (use native Read instead).\n---\n\n\u003C!-- Provenance: adapted from anthropics\u002Fknowledge-work-plugins (Apache-2.0, (c) Anthropic).\nOriginal skill: https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Ftree\u002Fmain\u002Fpdf-viewer\u002Fskills\u002Fview-pdf. Changes for Muse AI: Claude\u002FCowork product refs -> Muse AI; MCP -> connector; CLAUDE.md -> MUSE.md; ${CLAUDE_PLUGIN_ROOT} -> this skill's directory; \u002Fplugin:command refs -> skill refs. -->\n\n\n# PDF Viewer — Interactive Document Workflows\n\nYou have access to a local PDF server that renders documents in a live\nviewer and lets you annotate, fill forms, and place signatures with\nreal-time visual feedback.\n\n## When to use this skill\n\n**Use the PDF viewer when the user wants interactivity:**\n- \"Show me this contract\" \u002F \"Open this paper\"\n- \"Highlight the key terms and let me review\"\n- \"Help me fill out this form\"\n- \"Sign this on page 3\" \u002F \"Add my initials to each page\"\n- \"Stamp this CONFIDENTIAL\" \u002F \"Mark this as approved\"\n- \"Walk me through this document and annotate the important parts\"\n\n**Do NOT use the viewer for pure ingestion:**\n- \"Summarize this PDF\" → use the native Read tool directly\n- \"What does page 5 say?\" → use Read\n- \"Extract the table from section 3\" → use Read\n\nThe viewer's value is showing the user the document and collaborating\non markup — not streaming text back to you.\n\n## Tools\n\n### `list_pdfs`\nList available local PDFs and allowed local directories. No arguments.\n\n### `display_pdf`\nOpen a PDF in the interactive viewer. **Call once per document.**\n- `url` — local file path or HTTPS URL\n- `page` — initial page (optional, default 1)\n- `elicit_form_inputs` — if `true`, prompts the user to fill form\n  fields before displaying (use for interactive form-filling)\n\nReturns a `viewUUID` — pass this to every `interact` call. Calling\n`display_pdf` again creates a **separate** viewer; interact calls with\nthe new UUID won't reach the one the user is looking at.\n\nAlso returns `formFields` (name, type, page, bounding box) if the PDF\nhas fillable fields — use these coordinates for signature placement.\n\n### `interact`\nAll follow-up actions after `display_pdf`. Pass `viewUUID` plus one or\nmore commands. **Batch multiple commands in one call** via the\n`commands` array — they run sequentially. End batches with\n`get_screenshot` to verify changes visually.\n\n**Annotation actions:**\n- `add_annotations` — add markup (see types below)\n- `update_annotations` — modify existing (id + type required)\n- `remove_annotations` — delete by id array\n- `highlight_text` — auto-find text by query and highlight it\n  (preferred over manual rects for text markup)\n\n**Navigation actions:**\n- `navigate` (page), `search` (query), `find` (query, silent),\n  `search_navigate` (matchIndex), `zoom` (scale 0.5–3.0)\n\n**Extraction actions:**\n- `get_text` — extract text from page ranges (max 20 pages). Use for\n  reading content to decide what to annotate, NOT for summarization.\n- `get_screenshot` — capture a page as an image (verify your annotations)\n\n**Form action:**\n- `fill_form` — fill named fields: `fields: [{name, value}, ...]`\n\n## Annotation Types\n\nAll annotations need `id` (unique string), `type`, `page` (1-indexed).\nCoordinates are PDF points (1\u002F72 inch), origin **top-left**, Y increases\ndownward. US Letter is 612×792pt.\n\n| Type | Key properties | Use for |\n|------|----------------|---------|\n| `highlight` | `rects`, `color?`, `content?` | Mark important text |\n| `underline` | `rects`, `color?` | Emphasize terms |\n| `strikethrough` | `rects`, `color?` | Mark deletions |\n| `note` | `x`, `y`, `content`, `color?` | Sticky-note comments |\n| `freetext` | `x`, `y`, `content`, `fontSize?` | Visible text on page |\n| `rectangle` | `x`, `y`, `width`, `height`, `color?`, `fillColor?` | Box regions |\n| `circle` | `x`, `y`, `width`, `height`, `color?`, `fillColor?` | Circle regions |\n| `line` | `x1`, `y1`, `x2`, `y2`, `color?` | Draw lines\u002Farrows |\n| `stamp` | `x`, `y`, `label`, `color?`, `rotation?` | APPROVED, DRAFT, CONFIDENTIAL, etc. |\n| `image` | `imageUrl`, `x?`, `y?`, `width?`, `height?` | **Signatures, initials**, logos |\n\n**Image annotations** accept a local file path or HTTPS URL (no data:\nURIs). Dimensions auto-detected if omitted. Users can also drag & drop\nimages directly onto the viewer.\n\n## Interactive Workflows\n\n### Collaborative annotation (AI-driven)\n1. `display_pdf` to open the document\n2. `interact` → `get_text` on relevant page range to understand content\n3. Propose a batch of annotations to the user (describe what you'll mark)\n4. On approval, `interact` → `add_annotations` + `get_screenshot`\n5. Show the user, ask for edits, iterate\n6. When done, remind them they can download the annotated PDF from the\n   viewer toolbar\n\n### Form filling (visual, not programmatic)\nUnlike headless form tools, this gives the user **live visual\nfeedback** and handles forms with cryptic\u002Funnamed fields where the\nlabel is printed on the page rather than in field metadata.\n\n1. `display_pdf` — inspect returned `formFields` (name, type, page,\n   bounding box)\n2. If field names are cryptic (`Text1`, `Field_7`), `get_screenshot`\n   the pages and match bounding boxes to visual labels\n3. Ask the user for values using the **visual** labels, or infer from\n   context\n4. `interact` → `fill_form`, then `get_screenshot` to show the result\n5. User confirms or edits directly in the viewer\n\nFor simple well-labeled forms, `display_pdf` with\n`elicit_form_inputs: true` prompts the user upfront instead.\n\n### Signing (visual, not certified)\n1. Ask for the signature\u002Finitials image path\n2. `display_pdf`, check `formFields` for signature-type fields or ask\n   which page\u002Fposition\n3. `interact` → `add_annotations` with `type: \"image\"` at the target\n   coordinates\n4. `get_screenshot` to confirm placement\n\n**Disclaimer:** This places a visual signature image. It is **not** a\ncertified or cryptographic digital signature.\n\n## Supported Sources\n\n- Local files (paths under client connector roots)\n- arXiv (`\u002Fabs\u002F` URLs auto-convert to PDF)\n- Any direct HTTPS PDF URL (bioRxiv, Zenodo, OSF, etc. — use the\n  direct PDF link, not the landing page)\n\n## Out of Scope\n\n- **Summarization \u002F text extraction** — use native Read instead\n- **Certified digital signatures** — image stamping only\n- **PDF creation** — this works on existing PDFs only\n","\u003C!-- Provenance: adapted from anthropics\u002Fknowledge-work-plugins (Apache-2.0, (c) Anthropic).\nOriginal skill: https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Ftree\u002Fmain\u002Fpdf-viewer\u002Fskills\u002Fview-pdf. Changes for Muse AI: Claude\u002FCowork product refs -> Muse AI; MCP -> connector; CLAUDE.md -> MUSE.md; ${CLAUDE_PLUGIN_ROOT} -> this skill's directory; \u002Fplugin:command refs -> skill refs. -->\n\n\n# PDF Viewer — Interactive Document Workflows\n\nYou have access to a local PDF server that renders documents in a live\nviewer and lets you annotate, fill forms, and place signatures with\nreal-time visual feedback.\n\n## When to use this skill\n\n**Use the PDF viewer when the user wants interactivity:**\n- \"Show me this contract\" \u002F \"Open this paper\"\n- \"Highlight the key terms and let me review\"\n- \"Help me fill out this form\"\n- \"Sign this on page 3\" \u002F \"Add my initials to each page\"\n- \"Stamp this CONFIDENTIAL\" \u002F \"Mark this as approved\"\n- \"Walk me through this document and annotate the important parts\"\n\n**Do NOT use the viewer for pure ingestion:**\n- \"Summarize this PDF\" → use the native Read tool directly\n- \"What does page 5 say?\" → use Read\n- \"Extract the table from section 3\" → use Read\n\nThe viewer's value is showing the user the document and collaborating\non markup — not streaming text back to you.\n\n## Tools\n\n### `list_pdfs`\nList available local PDFs and allowed local directories. No arguments.\n\n### `display_pdf`\nOpen a PDF in the interactive viewer. **Call once per document.**\n- `url` — local file path or HTTPS URL\n- `page` — initial page (optional, default 1)\n- `elicit_form_inputs` — if `true`, prompts the user to fill form\n  fields before displaying (use for interactive form-filling)\n\nReturns a `viewUUID` — pass this to every `interact` call. Calling\n`display_pdf` again creates a **separate** viewer; interact calls with\nthe new UUID won't reach the one the user is looking at.\n\nAlso returns `formFields` (name, type, page, bounding box) if the PDF\nhas fillable fields — use these coordinates for signature placement.\n\n### `interact`\nAll follow-up actions after `display_pdf`. Pass `viewUUID` plus one or\nmore commands. **Batch multiple commands in one call** via the\n`commands` array — they run sequentially. End batches with\n`get_screenshot` to verify changes visually.\n\n**Annotation actions:**\n- `add_annotations` — add markup (see types below)\n- `update_annotations` — modify existing (id + type required)\n- `remove_annotations` — delete by id array\n- `highlight_text` — auto-find text by query and highlight it\n  (preferred over manual rects for text markup)\n\n**Navigation actions:**\n- `navigate` (page), `search` (query), `find` (query, silent),\n  `search_navigate` (matchIndex), `zoom` (scale 0.5–3.0)\n\n**Extraction actions:**\n- `get_text` — extract text from page ranges (max 20 pages). Use for\n  reading content to decide what to annotate, NOT for summarization.\n- `get_screenshot` — capture a page as an image (verify your annotations)\n\n**Form action:**\n- `fill_form` — fill named fields: `fields: [{name, value}, ...]`\n\n## Annotation Types\n\nAll annotations need `id` (unique string), `type`, `page` (1-indexed).\nCoordinates are PDF points (1\u002F72 inch), origin **top-left**, Y increases\ndownward. US Letter is 612×792pt.\n\n| Type | Key properties | Use for |\n|------|----------------|---------|\n| `highlight` | `rects`, `color?`, `content?` | Mark important text |\n| `underline` | `rects`, `color?` | Emphasize terms |\n| `strikethrough` | `rects`, `color?` | Mark deletions |\n| `note` | `x`, `y`, `content`, `color?` | Sticky-note comments |\n| `freetext` | `x`, `y`, `content`, `fontSize?` | Visible text on page |\n| `rectangle` | `x`, `y`, `width`, `height`, `color?`, `fillColor?` | Box regions |\n| `circle` | `x`, `y`, `width`, `height`, `color?`, `fillColor?` | Circle regions |\n| `line` | `x1`, `y1`, `x2`, `y2`, `color?` | Draw lines\u002Farrows |\n| `stamp` | `x`, `y`, `label`, `color?`, `rotation?` | APPROVED, DRAFT, CONFIDENTIAL, etc. |\n| `image` | `imageUrl`, `x?`, `y?`, `width?`, `height?` | **Signatures, initials**, logos |\n\n**Image annotations** accept a local file path or HTTPS URL (no data:\nURIs). Dimensions auto-detected if omitted. Users can also drag & drop\nimages directly onto the viewer.\n\n## Interactive Workflows\n\n### Collaborative annotation (AI-driven)\n1. `display_pdf` to open the document\n2. `interact` → `get_text` on relevant page range to understand content\n3. Propose a batch of annotations to the user (describe what you'll mark)\n4. On approval, `interact` → `add_annotations` + `get_screenshot`\n5. Show the user, ask for edits, iterate\n6. When done, remind them they can download the annotated PDF from the\n   viewer toolbar\n\n### Form filling (visual, not programmatic)\nUnlike headless form tools, this gives the user **live visual\nfeedback** and handles forms with cryptic\u002Funnamed fields where the\nlabel is printed on the page rather than in field metadata.\n\n1. `display_pdf` — inspect returned `formFields` (name, type, page,\n   bounding box)\n2. If field names are cryptic (`Text1`, `Field_7`), `get_screenshot`\n   the pages and match bounding boxes to visual labels\n3. Ask the user for values using the **visual** labels, or infer from\n   context\n4. `interact` → `fill_form`, then `get_screenshot` to show the result\n5. User confirms or edits directly in the viewer\n\nFor simple well-labeled forms, `display_pdf` with\n`elicit_form_inputs: true` prompts the user upfront instead.\n\n### Signing (visual, not certified)\n1. Ask for the signature\u002Finitials image path\n2. `display_pdf`, check `formFields` for signature-type fields or ask\n   which page\u002Fposition\n3. `interact` → `add_annotations` with `type: \"image\"` at the target\n   coordinates\n4. `get_screenshot` to confirm placement\n\n**Disclaimer:** This places a visual signature image. It is **not** a\ncertified or cryptographic digital signature.\n\n## Supported Sources\n\n- Local files (paths under client connector roots)\n- arXiv (`\u002Fabs\u002F` URLs auto-convert to PDF)\n- Any direct HTTPS PDF URL (bioRxiv, Zenodo, OSF, etc. — use the\n  direct PDF link, not the landing page)\n\n## Out of Scope\n\n- **Summarization \u002F text extraction** — use native Read instead\n- **Certified digital signatures** — image stamping only\n- **PDF creation** — this works on existing PDFs only\n",{"name":5,"description":7},"main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-kw-view-pdf",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill view-pdf",{"tool":38,"command":39},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill view-pdf",{"tool":41,"command":42},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill view-pdf","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-kw-view-pdf\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"CONNECTORS.md","REFERENCE","参考文档",466,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-kw-view-pdf\u002FCONNECTORS.md",[53,60,68,75,82,89],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7EWYJR0J8DARY7E59Z6Y9MV","web-scrape","Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open\u002Ffetch fails on JS-heavy pages, or when you need clean markdown\u002Fstructured extraction from a site. Requires FIRECRAWL_API_KEY.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fweb-scrape\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":64,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7EWYBN5P6F2AJG3FR24T9BP","design-taste-frontend","tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML\u002FCSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, \"AI-made\", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7EWY8FQFNQ2GB7NZZWGSSDX","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-tdd\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7EWY5SHBFRH1HDHVWM9K7TV","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-debugging\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7EWY3NM0Z0JAKS7HDZ24K66","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-code-review\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7EWY0WRMWX4M9ZFY0WKC593","brainstorming","You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-brainstorming\u002FSKILL.md",[],[]]