[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M736A7VPEP2THQZWZ55VDY9F":3,"skill-same:01M736A7VPEP2THQZWZ55VDY9F":56},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M736A7VPEP2THQZWZ55VDY9F","adobe-resize-photos-and-videos",null,"Resize photos and videos to exact pixel dimensions or aspect ratios using Adobe tools. Use this skill whenever a user wants to resize, scale, or change the dimensions of an image or video file — including phrases like \"resize this to 1920x1080\", \"make this 4K\", \"scale to 800x600\", \"change the aspect ratio to 16:9\", \"resize my video\", \"make the image smaller\", \"crop to square\", \"fit this to a specific size\", \"resize for print\", \"resize for web\", \"make it 300 DPI ready\", \"change canvas size\", \"resize a batch of photos\", or any request specifying target dimensions (W×H, ratio, or named size like \"4K\", \"HD\", \"A4\"). Also triggers for: \"make this fit a specific size\", \"resize to [any dimension]\", \"I need this at [WxH]\", \"scale my video down\", \"change resolution\", \"downscale\", \"upscale\". NOT for social media platform sets (use adobe-create-social-variations for that). Uses image_crop_and_resize for photos, video_resize for videos.","kalash33\u002Fkstack","kalash33","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F90259149?v=4","01M7365X8Q0B73NYHA730SMZWN","Kalash Poddar","01M7365X9D0JK47C3Q0YCCK9Z2",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fadobe-adobe-resize-photos-and-videos\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: adobe-resize-photos-and-videos\ndescription: >\n  Resize photos and videos to exact pixel dimensions or aspect ratios using Adobe tools.\n  Use this skill whenever a user wants to resize, scale, or change the dimensions of an image\n  or video file — including phrases like \"resize this to 1920x1080\", \"make this 4K\", \"scale\n  to 800x600\", \"change the aspect ratio to 16:9\", \"resize my video\", \"make the image smaller\",\n  \"crop to square\", \"fit this to a specific size\", \"resize for print\", \"resize for web\",\n  \"make it 300 DPI ready\", \"change canvas size\", \"resize a batch of photos\", or any request\n  specifying target dimensions (W×H, ratio, or named size like \"4K\", \"HD\", \"A4\").\n  Also triggers for: \"make this fit a specific size\", \"resize to [any dimension]\",\n  \"I need this at [WxH]\", \"scale my video down\", \"change resolution\", \"downscale\", \"upscale\".\n  NOT for social media platform sets (use adobe-create-social-variations for that).\n  Uses image_crop_and_resize for photos, video_resize for videos.\nlicense: Apache-2.0\nmetadata:\n  version: 1.0.1\n  visibility: public\n---\n\n# Adobe Resize Photos and Videos\n\nResizes images or videos to user-specified dimensions, aspect ratio, or named size.\nFor social media platform sets (Instagram, TikTok, etc.) → use the `adobe-create-social-variations` skill instead.\n\n---\n\n## Tool Reference\n\n| Step | Tool | Notes |\n|------|------|-------|\n| Open file picker | `asset_add_file` | Returns `presignedAssetUrl`, `assetId`, and `mediaType` |\n| Find asset in CC | `asset_search` | Re-stage result via `asset_add_file` for image; use `id` directly for video |\n| Render PSD\u002FAI | `document_render_vector` | Converts to JPEG before resize |\n| Resize image | `image_crop_and_resize` | One call per dimension; `reframe` by default |\n| Preview outputs | `asset_preview_file` | All outputs in a single call |\n| Upload to CC (start) | `asset_initialize_file_upload` | First call in block upload pipeline |\n| Upload to CC (finish) | `asset_finalize_file_upload` | Second call; returns presigned CC URL for board |\n| Create Firefly board | `create_firefly_board` | Pass `import_adobe_storage` with finalize URL |\n| Resize video | `video_resize` | Returns `statusId` for polling |\n| Poll video resize | `resizeVideoPoll` | Deferred tool — load before calling |\n\n---\n\n## Workflow\n\n### Step 0 — Initialize Adobe Tools\n\nCall `adobe_mandatory_init` first. This returns file handling rules and tool routing guidance required for the rest of the workflow.\n\n```json\n{ \"skill_name\": \"adobe-resize-photos-and-videos\", \"skill_version\": \"1.0.1\" }\n```\n\n---\n\n### Step 1 — Entitlement Check\n\nNow that `adobe_mandatory_init` confirmed that the \"Adobe for creativity\" connector is live, check which tools are available through the \"Adobe for creativity\" connector by cross checking against the **Tool Reference** table above.\n\n---\n\n## IMMEDIATE ACTION REQUIRED\n\n**Step 1:** If parameters are missing or ambiguous → run the multi-step intake (Step 2 below).\n**Step 2:** If no file is uploaded, run Step 3 (`asset_add_file({})`).\n**Step 3:** Detect image vs. video and route to the correct workflow (Step 5 Image\u002FVideo).\n\n---\n\n### Step 2 — Multi-Step Intake\n\nRun this when the user hasn't provided complete parameters (type + dimensions + fit mode).\nSkip entirely if the user's message already contains all three.\n\nUse `AskUserQuestion` to collect parameters step by step.\n\n#### Step 2a — Type\n\n```\nAskUserQuestion([{\n  question: \"Photo or video?\",\n  type: \"single_select\",\n  options: [\"Photo\", \"Video\"]\n}])\n```\n\n#### Step 2b — Dimensions\n\n**If Photo** (`multi_select` — user can pick one or more):\n```\nAskUserQuestion([{\n  question: \"Dimensions — select all you need\",\n  type: \"multi_select\",\n  options: [\n    \"1080 × 1080 — Instagram square\",\n    \"1080 × 1350 — Instagram portrait\",\n    \"1080 × 1920 — Stories \u002F Reels\",\n    \"1920 × 1080 — YouTube \u002F landscape\",\n    \"1280 × 720 — YouTube thumbnail\",\n    \"1200 × 675 — X \u002F Twitter post\",\n    \"1200 × 630 — Facebook \u002F OG image\",\n    \"1080 × 566 — LinkedIn post\",\n    \"2560 × 1440 — YouTube banner\",\n    \"3840 × 2160 — 4K \u002F UHD\",\n    \"400 × 400 — Profile \u002F avatar\",\n    \"2480 × 3508 — A4 print (300 dpi)\",\n    \"Custom — I'll type it\"\n  ]\n}])\n```\n\nIf user includes \"Custom\" → follow up: \"Enter your custom dimensions (e.g. 1500×800):\"\n\nIf user selects multiple presets → run `image_crop_and_resize` once per dimension,\nusing the same source URI and parameters each time. Preview all outputs together at the end.\n\n**If Video** (`multi_select` — user can pick one or more):\n```\nAskUserQuestion([{\n  question: \"Dimensions — select all you need\",\n  type: \"multi_select\",\n  options: [\n    \"1080 × 1920 — Reels \u002F TikTok \u002F Stories\",\n    \"1920 × 1080 — YouTube \u002F landscape\",\n    \"1080 × 1080 — Square post\",\n    \"1280 × 720 — YouTube 720p\",\n    \"3840 × 2160 — 4K \u002F UHD\",\n    \"854 × 480 — SD \u002F 480p\",\n    \"Custom — I'll type it\"\n  ]\n}])\n```\n\nIf user selects multiple video presets → submit a separate `video_resize` job per dimension,\npoll each to completion, preview all outputs together.\n\n#### Step 2c — Fit mode\n\n**If Photo** (`single_select`):\n```\nAskUserQuestion([{\n  question: \"Fit mode\",\n  type: \"single_select\",\n  options: [\n    \"Reframe — crop to fill\",\n    \"Pad — letterbox, no crop\",\n    \"Extract — isolate subject\"\n  ]\n}])\n```\n\n**If Video** (`single_select`):\n```\nAskUserQuestion([{\n  question: \"Fit mode\",\n  type: \"single_select\",\n  options: [\n    \"Letterbox — preserve ratio\",\n    \"Crop — fill, no bars\",\n    \"Stretch — force exact (distort)\"\n  ]\n}])\n```\n\n#### Step 2d — Smart focus (Photo only)\n\n```\nAskUserQuestion([{\n  question: \"Smart focus — where should the crop center?\",\n  type: \"single_select\",\n  options: [\n    \"Subject\",\n    \"Face \u002F portrait\",\n    \"Upper body\",\n    \"Center (geometric)\",\n    \"Named object — I'll describe it\"\n  ]\n}])\n```\n\nIf user selects \"Named object\" → follow up: \"Describe the object (e.g. 'the red car', 'the logo'):\"\n\n#### Step 2e — Options (Photo only)\n\n```\nAskUserQuestion([{\n  question: \"Any additional options?\",\n  type: \"multi_select\",\n  options: [\n    \"Batch — multiple images\",\n    \"Output: JPEG\",\n    \"Output: PNG\"\n  ]\n}])\n```\n\n#### Step 2f — Source (Video only)\n\n```\nAskUserQuestion([{\n  question: \"Where is the video?\",\n  type: \"single_select\",\n  options: [\n    \"Upload from device\",\n    \"From Creative Cloud\"\n  ]\n}])\n```\n\n---\n\n### Step 3 — Get the Source File\n\n**Critical — `\u002Fmnt\u002Fuser-data\u002Fuploads\u002F` paths are NOT usable URLs.**\nEven when the user has attached a file and it appears in context at a `\u002Fmnt\u002Fuser-data\u002Fuploads\u002F` path,\nyou cannot pass this path to any Adobe tool. Call `asset_add_file()` to stage the file — `\u002Fmnt\u002Fuser-data\u002Fuploads\u002F` paths are not fetchable by Adobe tools.\n\n```\nWRONG  ❌  imageURI: \"\u002Fmnt\u002Fuser-data\u002Fuploads\u002Fphoto.jpg\"\nWRONG  ❌  imageURI: \"file:\u002F\u002F\u002Fmnt\u002Fuser-data\u002Fuploads\u002Fphoto.jpg\"\nCORRECT ✅  call asset_add_file() → use presignedAssetUrl from picker context\n```\n\n**No file yet** → open the picker immediately:\n```javascript\nasset_add_file()\n```\n\nDetect type from returned `mediaType`:\n- `image\u002F*` → IMAGE WORKFLOW\n- `video\u002F*` → VIDEO WORKFLOW\n\n---\n\n### Step 4 — Resolve Target Dimensions\n\n| User says                    | Resolve to                                      |\n| ---------------------------- | ----------------------------------------------- |\n| `1920×1080`, `1920x1080`     | width: 1920, height: 1080                       |\n| `4K`                         | 3840 × 2160                                     |\n| `HD`, `1080p`                | 1920 × 1080                                     |\n| `720p`                       | 1280 × 720                                      |\n| `480p`                       | 854 × 480                                       |\n| `A4` print                   | 2480 × 3508 (300 DPI portrait)                  |\n| `Letter` print               | 2550 × 3300 (300 DPI portrait)                  |\n| `16:9`, `1:1`, `4:5`, `9:16` | ratio string → pass as `output: \"16:9\"`         |\n| `square`                     | `output: \"1:1\"`                                 |\n| Width only (`800px wide`)    | width: 800, use ratio string to maintain aspect |\n\nIf no target was specified in the form AND none in the user's message → ask:\n> \"What dimensions do you need? (e.g. 1920×1080, A4, 16:9)\"\n\n---\n\n## IMAGE WORKFLOW\n\n### Step 5 (Image) — Valid URI Sources\n\nOnly these work as `imageURI`:\n- `presignedAssetUrl` from `asset_add_file()` ✅\n- `outputUrl` from a prior tool call ✅\n- Public HTTPS URL provided by user ✅\n\nNot usable as `imageURI`:\n- `\u002Fmnt\u002Fuser-data\u002Fuploads\u002F` paths ❌\n- `renditionURL` from `asset_search` directly ❌\n- `file:\u002F\u002F` URIs ❌\n\n| Source            | Resolution                                                             |\n| ----------------- | ---------------------------------------------------------------------- |\n| Uploaded file     | `asset_add_file()` → `presignedAssetUrl`                               |\n| CC storage asset  | `asset_search` → re-stage via `asset_add_file()` → `presignedAssetUrl` |\n| Prior tool output | Use `outputUrl` directly                                               |\n| PSD \u002F AI file     | `document_render_vector` (JPEG, 300 DPI) → `outputPresignedUrl`        |\n\n---\n\n### Step 6 (Image) — Fit Mode\n\n| Intent                                   | Mode      | Notes                                                  |\n| ---------------------------------------- | --------- | ------------------------------------------------------ |\n| \"resize to WxH\" \u002F default                | `reframe` | Largest crop at target ratio, centered — no distortion |\n| \"no cropping\", \"letterbox\", \"fit inside\" | `pad`     | Fills empty space with white                           |\n| \"isolate subject\", \"tight crop\"          | `extract` | Tight crop around detected region                      |\n\n**Default: `reframe`.** Change only when user is explicit.\n\n> ⛔ `fit: \"extract\"` is incompatible with an explicit `{ width, height }` — it stretches the image. Use a ratio string or omit `output`.\n\n---\n\n### Step 7 (Image) — Call `image_crop_and_resize`\n\n```javascript\nimage_crop_and_resize({\n  imageURI: presignedAssetUrl,\n  options: {\n    output: { width: 1920, height: 1080 },  \u002F\u002F or \"16:9\"\n    fit: \"reframe\",\n    focus: \"subject\",  \u002F\u002F or \"face\", \"upper_body\", { prompt: \"the car\" }, { x:0.5, y:0.5 }\n    quality: 7\n  },\n  outputFileType: \"jpeg\"  \u002F\u002F or \"png\" if transparency needed\n})\n\u002F\u002F result.outputUrl → use for preview or chaining\n```\n\n**Focus guide:**\n- `\"subject\"` — default; full-body detection, landscapes, objects\n- `\"face\"` — portraits, headshots\n- `\"upper_body\"` — chest-up crops\n- `{ prompt: \"the logo\" }` — named object from user's form input\n- `{ x: 0.5, y: 0.5 }` — geometric center (no clear subject)\n\n---\n\n### Step 8 (Image) — Batch\n\nIf batch was selected in the form OR the user provided multiple files:\n1. Call `asset_add_file()` for each file to get individual presigned URLs\n2. Call `image_crop_and_resize` for each with the same parameters\n3. Collect all `outputUrl` values\n4. Call `asset_preview_file` with all outputs in a single call\n\n> Calls run sequentially in this environment. For >10 images, confirm with the user before starting.\n\n**Pagination across turns (batches >20):**\nFor large batches, the conversation context may fill before all images are processed,\ncausing Claude to pause mid-batch. This is expected — not an error. When it happens:\n- State how many have been completed and how many remain (e.g. \"20 \u002F 24 done — say 'continue' for the rest\")\n- Wait for the user to confirm before resuming\n- On resume, pick up from the next unprocessed image and continue to the end\n- Preview all outputs together only after the final image completes\n\n---\n\n### Step 9 (Image) — Preview + Deliver + Firefly Board\n\n```javascript\nasset_preview_file({\n  assets: [\n    { name: \"photo_1920x1080.jpg\", presignedAssetUrl: result.outputUrl },\n    \u002F\u002F all successful outputs\n  ]\n})\n```\n\n#### Save to CC + Create Firefly Board\n\nAfter preview, upload each output to CC storage using the block upload pipeline\n(`asset_initialize_file_upload` → PUT chunk → `asset_finalize_file_upload`).\n\nThen call the firefly board tool with the final output urls:\n\n```javascript\ncreate_firefly_board({\n  import_adobe_storage: [\n    final_output_url_1,\n    final_output_url_2,\n    \u002F\u002F ...\n  ]\n})\n```\n\n> ✅ **Confirmed working (Stage):** `import_adobe_storage` with presigned URLs from `asset_finalize_file_upload` successfully populates boards.\n>\n> ❌ **Does not work:** `import_generic_assets` with CC URNs (`urn:aaid:sc:US:...`) — USS indexing lag causes blank boards.\n>\n> If board creation fails or the URL is malformed, omit the board link (retrying does not help).\n\nPost the completion summary after the board step:\n\n```\n✅ Done! [N] image(s) resized and ready.\n\n📥 Download:\n• resized_1920x1080.jpg → \u003Ccc_storage_url>\n[list individually if N ≤ 3, or single folder link if N > 3]\n\n🎨 View in Firefly Board → \u003Cboard_url>   ← omit if board creation failed\n```\n\n---\n\n## VIDEO WORKFLOW\n\n### Step 5 (Video) — Get Asset ID\n\nVideo tools require `assetId`, not a URL.\n\n| Source                      | How                                                                   |\n| --------------------------- | --------------------------------------------------------------------- |\n| Upload via `asset_add_file` | Use returned `assetId`                                                |\n| CC storage                  | `asset_search` with `filters.mediaType: \"video\u002Fmp4\"` → use asset `id` |\n\n---\n\n### Step 6 (Video) — Common Targets\n\n| Name          | Dimensions  |\n| ------------- | ----------- |\n| 4K \u002F UHD      | 3840 × 2160 |\n| 1080p \u002F HD    | 1920 × 1080 |\n| 720p          | 1280 × 720  |\n| 480p          | 854 × 480   |\n| Vertical 9:16 | 1080 × 1920 |\n| Square 1:1    | 1080 × 1080 |\n\n---\n\n### Step 7 (Video) — Call `video_resize`\n\n> ⚠️ `resizeVideoPoll` is a **deferred tool** — load it first before attempting to poll.\n> Direct calls without loading will fail with \"not loaded\" error.\n\n```javascript\nvideo_resize({\n  assetId: videoAssetId,\n  width: targetW,\n  height: targetH,\n  mode: \"letterbox\"  \u002F\u002F default; see mode table below\n})\n\u002F\u002F Returns { jobStatus: \"pending\", statusId }\n```\n\n**Mode — use exact API values (not user-facing labels):**\n| User says                            | API value     | Behavior                                   |\n| ------------------------------------ | ------------- | ------------------------------------------ |\n| \"fit\", \"preserve ratio\", \"letterbox\" | `\"letterbox\"` | Preserves ratio, adds black bars (default) |\n| \"fill\", \"crop to fill\", \"no bars\"    | `\"crop\"`      | Crops edges to fill target exactly         |\n| \"stretch\", \"force exact\"             | `\"stretch\"`   | Distorts to exact target                   |\n\n> ℹ️ **Auto-reframe for video is not available in Claude yet**, but new tools are being added all the time. If you need more control, try using Adobe Premiere.\n\n**Polling:** load the deferred tool `resizeVideoPoll` before calling it — direct calls fail with \"not loaded\".\n```javascript\n\u002F\u002F Step 1: load the deferred tool resizeVideoPoll\n\u002F\u002F Step 2: poll until complete\nresizeVideoPoll({ statusId })\n\u002F\u002F Repeat until jobStatus === \"completed\"\n\u002F\u002F Show progress % to user while waiting\n```\n\n---\n\n### Step 8 (Video) — Preview + Deliver + Firefly Board\n\nIf polling succeeds and returns `outputUrl`, upload to CC storage via the block upload pipeline\n(`asset_initialize_file_upload` → PUT → `asset_finalize_file_upload`) to get a presigned URL, then:\n\n```javascript\nasset_preview_file({\n  assets: [{ name: \"resized_video.mp4\", presignedAssetUrl: result.outputUrl }]\n})\n\ncreate_firefly_board({\n  import_adobe_storage: [ presignedAssetUrl_from_finalize ]\n})\n```\n\n> ✅ Pass `import_adobe_storage` with the finalize presigned URL. If board creation fails, omit the link.\n\n```\n✅ Done! Video resized to [WxH].\n\n📥 Download → \u003Ccc_storage_url>\n\n🎨 View in Firefly Board → \u003Cboard_url>   ← omit if board creation failed\n```\n\nIf polling is unavailable → skip preview, deliver the CC storage fallback message from Step 7.\n\n---\n\n## Error Handling\n\n| Error                                                | Action                                                                                            |\n| ---------------------------------------------------- | ------------------------------------------------------------------------------------------------- |\n| `\u002Fmnt\u002Fuser-data\u002Fuploads\u002F` or `file:\u002F\u002F` passed as URI | Stop. Call `asset_add_file()` first.                                                              |\n| Image too large after resize                         | Re-run with `quality: 5`                                                                          |\n| Video `assetId` not found                            | Re-upload via `asset_add_file`                                                                    |\n| Source too small for target                          | Warn user upscaling won't add detail; proceed if confirmed                                        |\n| Invalid `video_resize` mode                          | API only accepts `\"letterbox\"`, `\"crop\"`, or `\"stretch\"` — `\"fit\"` and `\"fill\"` will be rejected. |\n| `extract` + `{W,H}` → stretching                     | Switch to `reframe`                                                                               |\n| No dimensions given                                  | Render form or ask explicitly before calling any tool                                             |\n| Unsupported format                                   | Ask user to export as JPG\u002FPNG (images) or MP4 (video)                                             |\n| `resizeVideoPoll` not loaded \u002F unavailable           | Known gap in current connector. Skip polling. Tell user to check CC Files for output.             |\n\n---\n\n## Common Dimension Reference\n\n| Use Case                  | Dimensions  |\n| ------------------------- | ----------- |\n| Full HD \u002F web hero        | 1920 × 1080 |\n| 4K                        | 3840 × 2160 |\n| Web thumbnail             | 1280 × 720  |\n| Square                    | 1080 × 1080 |\n| A4 print (300 DPI)        | 2480 × 3508 |\n| US Letter print (300 DPI) | 2550 × 3300 |\n| Blog featured image       | 1200 × 630  |\n| Email header              | 600 × 200   |\n| Avatar \u002F profile          | 400 × 400   |\n| Instagram portrait        | 1080 × 1350 |\n| Stories \u002F Vertical        | 1080 × 1920 |\n\n---\n\n## Assets\n\n`assets\u002Fintake-form.html` — Interactive intake form for resize parameters.\nRender at the start of any resize workflow where parameters are missing or ambiguous.\nCovers photo (target size, fit mode, smart focus, batch, output format) and video (target size, fit mode, source).\n","# Adobe Resize Photos and Videos\n\nResizes images or videos to user-specified dimensions, aspect ratio, or named size.\nFor social media platform sets (Instagram, TikTok, etc.) → use the `adobe-create-social-variations` skill instead.\n\n---\n\n## Tool Reference\n\n| Step | Tool | Notes |\n|------|------|-------|\n| Open file picker | `asset_add_file` | Returns `presignedAssetUrl`, `assetId`, and `mediaType` |\n| Find asset in CC | `asset_search` | Re-stage result via `asset_add_file` for image; use `id` directly for video |\n| Render PSD\u002FAI | `document_render_vector` | Converts to JPEG before resize |\n| Resize image | `image_crop_and_resize` | One call per dimension; `reframe` by default |\n| Preview outputs | `asset_preview_file` | All outputs in a single call |\n| Upload to CC (start) | `asset_initialize_file_upload` | First call in block upload pipeline |\n| Upload to CC (finish) | `asset_finalize_file_upload` | Second call; returns presigned CC URL for board |\n| Create Firefly board | `create_firefly_board` | Pass `import_adobe_storage` with finalize URL |\n| Resize video | `video_resize` | Returns `statusId` for polling |\n| Poll video resize | `resizeVideoPoll` | Deferred tool — load before calling |\n\n---\n\n## Workflow\n\n### Step 0 — Initialize Adobe Tools\n\nCall `adobe_mandatory_init` first. This returns file handling rules and tool routing guidance required for the rest of the workflow.\n\n```json\n{ \"skill_name\": \"adobe-resize-photos-and-videos\", \"skill_version\": \"1.0.1\" }\n```\n\n---\n\n### Step 1 — Entitlement Check\n\nNow that `adobe_mandatory_init` confirmed that the \"Adobe for creativity\" connector is live, check which tools are available through the \"Adobe for creativity\" connector by cross checking against the **Tool Reference** table above.\n\n---\n\n## IMMEDIATE ACTION REQUIRED\n\n**Step 1:** If parameters are missing or ambiguous → run the multi-step intake (Step 2 below).\n**Step 2:** If no file is uploaded, run Step 3 (`asset_add_file({})`).\n**Step 3:** Detect image vs. video and route to the correct workflow (Step 5 Image\u002FVideo).\n\n---\n\n### Step 2 — Multi-Step Intake\n\nRun this when the user hasn't provided complete parameters (type + dimensions + fit mode).\nSkip entirely if the user's message already contains all three.\n\nUse `AskUserQuestion` to collect parameters step by step.\n\n#### Step 2a — Type\n\n```\nAskUserQuestion([{\n  question: \"Photo or video?\",\n  type: \"single_select\",\n  options: [\"Photo\", \"Video\"]\n}])\n```\n\n#### Step 2b — Dimensions\n\n**If Photo** (`multi_select` — user can pick one or more):\n```\nAskUserQuestion([{\n  question: \"Dimensions — select all you need\",\n  type: \"multi_select\",\n  options: [\n    \"1080 × 1080 — Instagram square\",\n    \"1080 × 1350 — Instagram portrait\",\n    \"1080 × 1920 — Stories \u002F Reels\",\n    \"1920 × 1080 — YouTube \u002F landscape\",\n    \"1280 × 720 — YouTube thumbnail\",\n    \"1200 × 675 — X \u002F Twitter post\",\n    \"1200 × 630 — Facebook \u002F OG image\",\n    \"1080 × 566 — LinkedIn post\",\n    \"2560 × 1440 — YouTube banner\",\n    \"3840 × 2160 — 4K \u002F UHD\",\n    \"400 × 400 — Profile \u002F avatar\",\n    \"2480 × 3508 — A4 print (300 dpi)\",\n    \"Custom — I'll type it\"\n  ]\n}])\n```\n\nIf user includes \"Custom\" → follow up: \"Enter your custom dimensions (e.g. 1500×800):\"\n\nIf user selects multiple presets → run `image_crop_and_resize` once per dimension,\nusing the same source URI and parameters each time. Preview all outputs together at the end.\n\n**If Video** (`multi_select` — user can pick one or more):\n```\nAskUserQuestion([{\n  question: \"Dimensions — select all you need\",\n  type: \"multi_select\",\n  options: [\n    \"1080 × 1920 — Reels \u002F TikTok \u002F Stories\",\n    \"1920 × 1080 — YouTube \u002F landscape\",\n    \"1080 × 1080 — Square post\",\n    \"1280 × 720 — YouTube 720p\",\n    \"3840 × 2160 — 4K \u002F UHD\",\n    \"854 × 480 — SD \u002F 480p\",\n    \"Custom — I'll type it\"\n  ]\n}])\n```\n\nIf user selects multiple video presets → submit a separate `video_resize` job per dimension,\npoll each to completion, preview all outputs together.\n\n#### Step 2c — Fit mode\n\n**If Photo** (`single_select`):\n```\nAskUserQuestion([{\n  question: \"Fit mode\",\n  type: \"single_select\",\n  options: [\n    \"Reframe — crop to fill\",\n    \"Pad — letterbox, no crop\",\n    \"Extract — isolate subject\"\n  ]\n}])\n```\n\n**If Video** (`single_select`):\n```\nAskUserQuestion([{\n  question: \"Fit mode\",\n  type: \"single_select\",\n  options: [\n    \"Letterbox — preserve ratio\",\n    \"Crop — fill, no bars\",\n    \"Stretch — force exact (distort)\"\n  ]\n}])\n```\n\n#### Step 2d — Smart focus (Photo only)\n\n```\nAskUserQuestion([{\n  question: \"Smart focus — where should the crop center?\",\n  type: \"single_select\",\n  options: [\n    \"Subject\",\n    \"Face \u002F portrait\",\n    \"Upper body\",\n    \"Center (geometric)\",\n    \"Named object — I'll describe it\"\n  ]\n}])\n```\n\nIf user selects \"Named object\" → follow up: \"Describe the object (e.g. 'the red car', 'the logo'):\"\n\n#### Step 2e — Options (Photo only)\n\n```\nAskUserQuestion([{\n  question: \"Any additional options?\",\n  type: \"multi_select\",\n  options: [\n    \"Batch — multiple images\",\n    \"Output: JPEG\",\n    \"Output: PNG\"\n  ]\n}])\n```\n\n#### Step 2f — Source (Video only)\n\n```\nAskUserQuestion([{\n  question: \"Where is the video?\",\n  type: \"single_select\",\n  options: [\n    \"Upload from device\",\n    \"From Creative Cloud\"\n  ]\n}])\n```\n\n---\n\n### Step 3 — Get the Source File\n\n**Critical — `\u002Fmnt\u002Fuser-data\u002Fuploads\u002F` paths are NOT usable URLs.**\nEven when the user has attached a file and it appears in context at a `\u002Fmnt\u002Fuser-data\u002Fuploads\u002F` path,\nyou cannot pass this path to any Adobe tool. Call `asset_add_file()` to stage the file — `\u002Fmnt\u002Fuser-data\u002Fuploads\u002F` paths are not fetchable by Adobe tools.\n\n```\nWRONG  ❌  imageURI: \"\u002Fmnt\u002Fuser-data\u002Fuploads\u002Fphoto.jpg\"\nWRONG  ❌  imageURI: \"file:\u002F\u002F\u002Fmnt\u002Fuser-data\u002Fuploads\u002Fphoto.jpg\"\nCORRECT ✅  call asset_add_file() → use presignedAssetUrl from picker context\n```\n\n**No file yet** → open the picker immediately:\n```javascript\nasset_add_file()\n```\n\nDetect type from returned `mediaType`:\n- `image\u002F*` → IMAGE WORKFLOW\n- `video\u002F*` → VIDEO WORKFLOW\n\n---\n\n### Step 4 — Resolve Target Dimensions\n\n| User says                    | Resolve to                                      |\n| ---------------------------- | ----------------------------------------------- |\n| `1920×1080`, `1920x1080`     | width: 1920, height: 1080                       |\n| `4K`                         | 3840 × 2160                                     |\n| `HD`, `1080p`                | 1920 × 1080                                     |\n| `720p`                       | 1280 × 720                                      |\n| `480p`                       | 854 × 480                                       |\n| `A4` print                   | 2480 × 3508 (300 DPI portrait)                  |\n| `Letter` print               | 2550 × 3300 (300 DPI portrait)                  |\n| `16:9`, `1:1`, `4:5`, `9:16` | ratio string → pass as `output: \"16:9\"`         |\n| `square`                     | `output: \"1:1\"`                                 |\n| Width only (`800px wide`)    | width: 800, use ratio string to maintain aspect |\n\nIf no target was specified in the form AND none in the user's message → ask:\n> \"What dimensions do you need? (e.g. 1920×1080, A4, 16:9)\"\n\n---\n\n## IMAGE WORKFLOW\n\n### Step 5 (Image) — Valid URI Sources\n\nOnly these work as `imageURI`:\n- `presignedAssetUrl` from `asset_add_file()` ✅\n- `outputUrl` from a prior tool call ✅\n- Public HTTPS URL provided by user ✅\n\nNot usable as `imageURI`:\n- `\u002Fmnt\u002Fuser-data\u002Fuploads\u002F` paths ❌\n- `renditionURL` from `asset_search` directly ❌\n- `file:\u002F\u002F` URIs ❌\n\n| Source            | Resolution                                                             |\n| ----------------- | ---------------------------------------------------------------------- |\n| Uploaded file     | `asset_add_file()` → `presignedAssetUrl`                               |\n| CC storage asset  | `asset_search` → re-stage via `asset_add_file()` → `presignedAssetUrl` |\n| Prior tool output | Use `outputUrl` directly                                               |\n| PSD \u002F AI file     | `document_render_vector` (JPEG, 300 DPI) → `outputPresignedUrl`        |\n\n---\n\n### Step 6 (Image) — Fit Mode\n\n| Intent                                   | Mode      | Notes                                                  |\n| ---------------------------------------- | --------- | ------------------------------------------------------ |\n| \"resize to WxH\" \u002F default                | `reframe` | Largest crop at target ratio, centered — no distortion |\n| \"no cropping\", \"letterbox\", \"fit inside\" | `pad`     | Fills empty space with white                           |\n| \"isolate subject\", \"tight crop\"          | `extract` | Tight crop around detected region                      |\n\n**Default: `reframe`.** Change only when user is explicit.\n\n> ⛔ `fit: \"extract\"` is incompatible with an explicit `{ width, height }` — it stretches the image. Use a ratio string or omit `output`.\n\n---\n\n### Step 7 (Image) — Call `image_crop_and_resize`\n\n```javascript\nimage_crop_and_resize({\n  imageURI: presignedAssetUrl,\n  options: {\n    output: { width: 1920, height: 1080 },  \u002F\u002F or \"16:9\"\n    fit: \"reframe\",\n    focus: \"subject\",  \u002F\u002F or \"face\", \"upper_body\", { prompt: \"the car\" }, { x:0.5, y:0.5 }\n    quality: 7\n  },\n  outputFileType: \"jpeg\"  \u002F\u002F or \"png\" if transparency needed\n})\n\u002F\u002F result.outputUrl → use for preview or chaining\n```\n\n**Focus guide:**\n- `\"subject\"` — default; full-body detection, landscapes, objects\n- `\"face\"` — portraits, headshots\n- `\"upper_body\"` — chest-up crops\n- `{ prompt: \"the logo\" }` — named object from user's form input\n- `{ x: 0.5, y: 0.5 }` — geometric center (no clear subject)\n\n---\n\n### Step 8 (Image) — Batch\n\nIf batch was selected in the form OR the user provided multiple files:\n1. Call `asset_add_file()` for each file to get individual presigned URLs\n2. Call `image_crop_and_resize` for each with the same parameters\n3. Collect all `outputUrl` values\n4. Call `asset_preview_file` with all outputs in a single call\n\n> Calls run sequentially in this environment. For >10 images, confirm with the user before starting.\n\n**Pagination across turns (batches >20):**\nFor large batches, the conversation context may fill before all images are processed,\ncausing Claude to pause mid-batch. This is expected — not an error. When it happens:\n- State how many have been completed and how many remain (e.g. \"20 \u002F 24 done — say 'continue' for the rest\")\n- Wait for the user to confirm before resuming\n- On resume, pick up from the next unprocessed image and continue to the end\n- Preview all outputs together only after the final image completes\n\n---\n\n### Step 9 (Image) — Preview + Deliver + Firefly Board\n\n```javascript\nasset_preview_file({\n  assets: [\n    { name: \"photo_1920x1080.jpg\", presignedAssetUrl: result.outputUrl },\n    \u002F\u002F all successful outputs\n  ]\n})\n```\n\n#### Save to CC + Create Firefly Board\n\nAfter preview, upload each output to CC storage using the block upload pipeline\n(`asset_initialize_file_upload` → PUT chunk → `asset_finalize_file_upload`).\n\nThen call the firefly board tool with the final output urls:\n\n```javascript\ncreate_firefly_board({\n  import_adobe_storage: [\n    final_output_url_1,\n    final_output_url_2,\n    \u002F\u002F ...\n  ]\n})\n```\n\n> ✅ **Confirmed working (Stage):** `import_adobe_storage` with presigned URLs from `asset_finalize_file_upload` successfully populates boards.\n>\n> ❌ **Does not work:** `import_generic_assets` with CC URNs (`urn:aaid:sc:US:...`) — USS indexing lag causes blank boards.\n>\n> If board creation fails or the URL is malformed, omit the board link (retrying does not help).\n\nPost the completion summary after the board step:\n\n```\n✅ Done! [N] image(s) resized and ready.\n\n📥 Download:\n• resized_1920x1080.jpg → \u003Ccc_storage_url>\n[list individually if N ≤ 3, or single folder link if N > 3]\n\n🎨 View in Firefly Board → \u003Cboard_url>   ← omit if board creation failed\n```\n\n---\n\n## VIDEO WORKFLOW\n\n### Step 5 (Video) — Get Asset ID\n\nVideo tools require `assetId`, not a URL.\n\n| Source                      | How                                                                   |\n| --------------------------- | --------------------------------------------------------------------- |\n| Upload via `asset_add_file` | Use returned `assetId`                                                |\n| CC storage                  | `asset_search` with `filters.mediaType: \"video\u002Fmp4\"` → use asset `id` |\n\n---\n\n### Step 6 (Video) — Common Targets\n\n| Name          | Dimensions  |\n| ------------- | ----------- |\n| 4K \u002F UHD      | 3840 × 2160 |\n| 1080p \u002F HD    | 1920 × 1080 |\n| 720p          | 1280 × 720  |\n| 480p          | 854 × 480   |\n| Vertical 9:16 | 1080 × 1920 |\n| Square 1:1    | 1080 × 1080 |\n\n---\n\n### Step 7 (Video) — Call `video_resize`\n\n> ⚠️ `resizeVideoPoll` is a **deferred tool** — load it first before attempting to poll.\n> Direct calls without loading will fail with \"not loaded\" error.\n\n```javascript\nvideo_resize({\n  assetId: videoAssetId,\n  width: targetW,\n  height: targetH,\n  mode: \"letterbox\"  \u002F\u002F default; see mode table below\n})\n\u002F\u002F Returns { jobStatus: \"pending\", statusId }\n```\n\n**Mode — use exact API values (not user-facing labels):**\n| User says                            | API value     | Behavior                                   |\n| ------------------------------------ | ------------- | ------------------------------------------ |\n| \"fit\", \"preserve ratio\", \"letterbox\" | `\"letterbox\"` | Preserves ratio, adds black bars (default) |\n| \"fill\", \"crop to fill\", \"no bars\"    | `\"crop\"`      | Crops edges to fill target exactly         |\n| \"stretch\", \"force exact\"             | `\"stretch\"`   | Distorts to exact target                   |\n\n> ℹ️ **Auto-reframe for video is not available in Claude yet**, but new tools are being added all the time. If you need more control, try using Adobe Premiere.\n\n**Polling:** load the deferred tool `resizeVideoPoll` before calling it — direct calls fail with \"not loaded\".\n```javascript\n\u002F\u002F Step 1: load the deferred tool resizeVideoPoll\n\u002F\u002F Step 2: poll until complete\nresizeVideoPoll({ statusId })\n\u002F\u002F Repeat until jobStatus === \"completed\"\n\u002F\u002F Show progress % to user while waiting\n```\n\n---\n\n### Step 8 (Video) — Preview + Deliver + Firefly Board\n\nIf polling succeeds and returns `outputUrl`, upload to CC storage via the block upload pipeline\n(`asset_initialize_file_upload` → PUT → `asset_finalize_file_upload`) to get a presigned URL, then:\n\n```javascript\nasset_preview_file({\n  assets: [{ name: \"resized_video.mp4\", presignedAssetUrl: result.outputUrl }]\n})\n\ncreate_firefly_board({\n  import_adobe_storage: [ presignedAssetUrl_from_finalize ]\n})\n```\n\n> ✅ Pass `import_adobe_storage` with the finalize presigned URL. If board creation fails, omit the link.\n\n```\n✅ Done! Video resized to [WxH].\n\n📥 Download → \u003Ccc_storage_url>\n\n🎨 View in Firefly Board → \u003Cboard_url>   ← omit if board creation failed\n```\n\nIf polling is unavailable → skip preview, deliver the CC storage fallback message from Step 7.\n\n---\n\n## Error Handling\n\n| Error                                                | Action                                                                                            |\n| ---------------------------------------------------- | ------------------------------------------------------------------------------------------------- |\n| `\u002Fmnt\u002Fuser-data\u002Fuploads\u002F` or `file:\u002F\u002F` passed as URI | Stop. Call `asset_add_file()` first.                                                              |\n| Image too large after resize                         | Re-run with `quality: 5`                                                                          |\n| Video `assetId` not found                            | Re-upload via `asset_add_file`                                                                    |\n| Source too small for target                          | Warn user upscaling won't add detail; proceed if confirmed                                        |\n| Invalid `video_resize` mode                          | API only accepts `\"letterbox\"`, `\"crop\"`, or `\"stretch\"` — `\"fit\"` and `\"fill\"` will be rejected. |\n| `extract` + `{W,H}` → stretching                     | Switch to `reframe`                                                                               |\n| No dimensions given                                  | Render form or ask explicitly before calling any tool                                             |\n| Unsupported format                                   | Ask user to export as JPG\u002FPNG (images) or MP4 (video)                                             |\n| `resizeVideoPoll` not loaded \u002F unavailable           | Known gap in current connector. Skip polling. Tell user to check CC Files for output.             |\n\n---\n\n## Common Dimension Reference\n\n| Use Case                  | Dimensions  |\n| ------------------------- | ----------- |\n| Full HD \u002F web hero        | 1920 × 1080 |\n| 4K                        | 3840 × 2160 |\n| Web thumbnail             | 1280 × 720  |\n| Square                    | 1080 × 1080 |\n| A4 print (300 DPI)        | 2480 × 3508 |\n| US Letter print (300 DPI) | 2550 × 3300 |\n| Blog featured image       | 1200 × 630  |\n| Email header              | 600 × 200   |\n| Avatar \u002F profile          | 400 × 400   |\n| Instagram portrait        | 1080 × 1350 |\n| Stories \u002F Vertical        | 1080 × 1920 |\n\n---\n\n## Assets\n\n`assets\u002Fintake-form.html` — Interactive intake form for resize parameters.\nRender at the start of any resize workflow where parameters are missing or ambiguous.\nCovers photo (target size, fit mode, smart focus, batch, output format) and video (target size, fit mode, source).\n",{"name":5,"license":15,"metadata":24,"description":27},{"version":25,"visibility":26},"1.0.1","public","Resize photos and videos to exact pixel dimensions or aspect ratios using Adobe tools. Use this skill whenever a user wants to resize, scale, or change the dimensions of an image or video file — including phrases like \"resize this to 1920x1080\", \"make this 4K\", \"scale to 800x600\", \"change the aspect ratio to 16:9\", \"resize my video\", \"make the image smaller\", \"crop to square\", \"fit this to a specific size\", \"resize for print\", \"resize for web\", \"make it 300 DPI ready\", \"change canvas size\", \"resize a batch of photos\", or any request specifying target dimensions (W×H, ratio, or named size like \"4K\", \"HD\", \"A4\"). Also triggers for: \"make this fit a specific size\", \"resize to [any dimension]\", \"I need this at [WxH]\", \"scale my video down\", \"change resolution\", \"downscale\", \"upscale\". NOT for social media platform sets (use adobe-create-social-variations for that). Uses image_crop_and_resize for photos, video_resize for videos.\n","main","b30820b3248f6676d5389f0ccabd4e5250c9c536","skills\u002Fadobe-adobe-resize-photos-and-videos","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack","https:\u002F\u002Fgithub.com\u002Fkalash33","kalashpoddar.me","Tech-savvy Full Stack Developer 🚀 | Cybersecurity enthusiast 🔒 | Passionate about innovation and securing the digital world 🌐 | Let's code securely! 💻🔐","2026-05-20 04:11:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add kalash33\u002Fkstack --skill adobe-resize-photos-and-videos",{"tool":42,"command":43},"bunx","bunx skills add kalash33\u002Fkstack --skill adobe-resize-photos-and-videos",{"tool":45,"command":46},"pnpm","pnpm dlx skills add kalash33\u002Fkstack --skill adobe-resize-photos-and-videos","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fadobe-adobe-resize-photos-and-videos\u002FSKILL.md",true,[50],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"assets\u002Fintake-form.html","ASSET","资产文件",16558,"https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fadobe-adobe-resize-photos-and-videos\u002Fassets\u002Fintake-form.html",[57,65,72,79,86,93],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M73CFERCR43JCAP606E41EFB","zustand-store-ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reacti...","MIT","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M73CFCMFVTAQEMTZ5HR10X8V","zoom-automation","Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-automation\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M73CFAA7EBWXJVXDQ1X555MB","zoho-crm-automation","Automate Zoho CRM tasks via Rube MCP (Composio): create\u002Fupdate records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzoho-crm-automation\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M73CF80XCM9K81567MJ8QZFW","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M73CF4YPMF3RA8ZJDXZSMD93","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M73CF2S25EN3XNAMKY47XHPS","zendesk-automation","Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzendesk-automation\u002FSKILL.md",[],[]]