@genspark/cli 1.14.2 → 1.15.1-beta.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (59) hide show
  1. package/README.md +43 -1
  2. package/dist/client.d.ts +6 -0
  3. package/dist/client.d.ts.map +1 -1
  4. package/dist/client.js +32 -6
  5. package/dist/client.js.map +1 -1
  6. package/dist/commands/aidrive-contract.generated.d.ts.map +1 -1
  7. package/dist/commands/aidrive-contract.generated.js +141 -4
  8. package/dist/commands/aidrive-contract.generated.js.map +1 -1
  9. package/dist/commands/aidrive-upload.js +2 -1
  10. package/dist/commands/aidrive-upload.js.map +1 -1
  11. package/dist/commands/sb-box-session.d.ts +128 -0
  12. package/dist/commands/sb-box-session.d.ts.map +1 -0
  13. package/dist/commands/sb-box-session.js +477 -0
  14. package/dist/commands/sb-box-session.js.map +1 -0
  15. package/dist/config.d.ts +43 -0
  16. package/dist/config.d.ts.map +1 -1
  17. package/dist/config.js +46 -0
  18. package/dist/config.js.map +1 -1
  19. package/dist/index.d.ts.map +1 -1
  20. package/dist/index.js +178 -31
  21. package/dist/index.js.map +1 -1
  22. package/dist/native-waf.d.ts +24 -0
  23. package/dist/native-waf.d.ts.map +1 -0
  24. package/dist/native-waf.js +183 -0
  25. package/dist/native-waf.js.map +1 -0
  26. package/dist/object-args.d.ts +4 -0
  27. package/dist/object-args.d.ts.map +1 -0
  28. package/dist/object-args.js +34 -0
  29. package/dist/object-args.js.map +1 -0
  30. package/dist/project-binding.d.ts.map +1 -1
  31. package/dist/project-binding.js +14 -2
  32. package/dist/project-binding.js.map +1 -1
  33. package/dist/types.d.ts +1 -0
  34. package/dist/types.d.ts.map +1 -1
  35. package/dist/updater.d.ts +5 -0
  36. package/dist/updater.d.ts.map +1 -1
  37. package/dist/updater.js +30 -3
  38. package/dist/updater.js.map +1 -1
  39. package/docs/skills.md +9 -7
  40. package/package.json +1 -1
  41. package/skills/gsk-aidrive/SKILL.md +241 -27
  42. package/skills/gsk-audio-generation/SKILL.md +1 -1
  43. package/skills/gsk-audio-transcribe/SKILL.md +5 -2
  44. package/skills/gsk-calendar-search/SKILL.md +42 -0
  45. package/skills/gsk-calendar-source/SKILL.md +44 -0
  46. package/skills/gsk-connector/SKILL.md +34 -7
  47. package/skills/gsk-create-task/SKILL.md +1 -1
  48. package/skills/gsk-genteam/SKILL.md +4 -2
  49. package/skills/gsk-github/SKILL.md +4 -3
  50. package/skills/gsk-google-drive/SKILL.md +6 -5
  51. package/skills/gsk-google-sheets/SKILL.md +1 -1
  52. package/skills/gsk-image-generation/SKILL.md +3 -1
  53. package/skills/gsk-meeting/SKILL.md +1 -1
  54. package/skills/gsk-notion/SKILL.md +2 -2
  55. package/skills/gsk-onedrive/SKILL.md +6 -4
  56. package/skills/gsk-second-brain/SKILL.md +2 -2
  57. package/skills/gsk-shared/SKILL.md +4 -3
  58. package/skills/gsk-sharepoint/SKILL.md +6 -5
  59. package/skills/gsk-video-generation/SKILL.md +2 -1
@@ -1,8 +1,8 @@
1
1
  ---
2
2
  name: gsk-google-drive
3
3
  version: 1.0.0
4
- description: 'Google Drive file operations. Actions: list, search, read, upload, share,
5
- trash.'
4
+ description: 'Google Drive file operations. Actions: list, search, read, get_readable_url,
5
+ upload, share, trash.'
6
6
  metadata:
7
7
  category: general
8
8
  generated_by: genspark_tool_cli/generate_skills.py
@@ -18,7 +18,7 @@ metadata:
18
18
 
19
19
  > **Note:** a unified `gsk connector` flow is rolling out (see `../gsk-connector/SKILL.md`: `gsk connector tools <id>` / `gsk connector call <id> -t <tool>`) and may not be enabled for every account yet. THIS command remains fully supported — use it directly, and it stays the fallback whenever `gsk connector` is unavailable.
20
20
 
21
- Google Drive file operations. Actions: list, search, read, upload, share, trash.
21
+ Google Drive file operations. Actions: list, search, read, get_readable_url, upload, share, trash.
22
22
 
23
23
  ## Usage
24
24
 
@@ -50,7 +50,7 @@ children, and file authorization cannot override a lack of permission to trash.
50
50
 
51
51
  | Flag | Required | Description |
52
52
  |------|----------|-------------|
53
- | `<action>` (positional) | Yes | Action to perform. 'list': List files directly inside a Google Drive folder; 'search': Search files by name, type, or owner; 'read': Read and extract content from a file; 'upload': Upload a new file to Google Drive, or overwrite an existing one in place by passing its file_id (the ID, link, and shares are preserved); 'share': Grant access to a file (specific emails or anyone-with-link; app-created/opened files only under drive.file). Confirmation-gated: on a CLI with client-side confirmation the command runs as a single call after the [y/N] prompt (or --yes).; 'trash': Move a file or folder to the trash (recoverable within 30 days; uses the same connector credentials as upload; app-created/opened files only under drive.file). Confirmation-gated: on a CLI with client-side confirmation the command runs as a single call after the [y/N] prompt (or --yes). (string, one of: list, search, read, upload, share, trash) |
53
+ | `<action>` (positional) | Yes | Action to perform. 'list': List files directly inside a Google Drive folder; 'search': Search files by name, type, or owner; 'read': Read and extract content from a file; 'get_readable_url': Temporary one-hour URL streaming a file's original bytes (Range supported), or a Google Doc, Sheet, Slides deck or Drawing as a whole DOCX, XLSX, PPTX or PNG export (no Range), for tools that fetch by URL, such as ffmpeg; not for people; 'upload': Upload a new file to Google Drive, or overwrite an existing one in place by passing its file_id (the ID, link, and shares are preserved); 'share': Grant access to a file (specific emails or anyone-with-link; app-created/opened files only under drive.file). Confirmation-gated: on a CLI with client-side confirmation the command runs as a single call after the [y/N] prompt (or --yes).; 'trash': Move a file or folder to the trash (recoverable within 30 days; uses the same connector credentials as upload; app-created/opened files only under drive.file). Confirmation-gated: on a CLI with client-side confirmation the command runs as a single call after the [y/N] prompt (or --yes). (string, one of: list, search, read, get_readable_url, upload, share, trash) |
54
54
  | `--folder_id` | No | [list] Google Drive folder ID or folder URL. \| [search] Search within a specific folder for 'search' action. Accepts a folder ID or Google Drive folder URL. \| [upload] Google Drive folder ID to upload to. Optional, uploads to root if not specified. Ignored when 'file_id' is set. (string) |
55
55
  | `--folder_url` | No | [list] Google Drive folder URL. \| [search] Google Drive folder URL to list/search within. (string) |
56
56
  | `--mime_type` | No | [list] Optional MIME type filter. \| [search] Filter by MIME type for 'search' (e.g., 'application/pdf'). \| [upload] The MIME type of the file (optional, will be auto-detected from file_name extension). Examples: 'text/plain', 'text/csv', 'application/json', 'image/png'. (string) |
@@ -58,8 +58,9 @@ children, and file authorization cannot override a lack of permission to trash.
58
58
  | `--all_pages` | No | [list] List every page in the selected folder. Use for complete programmatic inventory; default false. (boolean) |
59
59
  | `--query` | No | [search] Use keywords simply, terms will be combined into advanced search query in the later process.For example, if user ask for 'tax related documents', just use 'tax' as the query,DO NOT use advanced search query like 'name contains 'tax'' or 'fullText contains 'tax''. Use '*' to list all authorized files, especially when folder_id is supplied. (string) |
60
60
  | `--owner` | No | [search] Filter by file owner (email address) for 'search' action (string) |
61
- | `--file_id` | No | [read] The ID of the file to read from Google Drive. \| [upload] Existing Google Drive file ID to OVERWRITE in place instead of creating a new file (from google_drive search/list/upload results). The content is replaced while the file ID, link, and existing shares are preserved — use this when the user wants to update a document they already have, not get a new one. \| [share] Google Drive file ID to share (from google_drive search/list/upload results). \| [trash] Google Drive file or folder ID to move to the trash. (string) |
61
+ | `--file_id` | No | [read] The ID of the file to read from Google Drive. \| [get_readable_url] Google Drive file ID (from google_drive search/list results). \| [upload] Existing Google Drive file ID to OVERWRITE in place instead of creating a new file (from google_drive search/list/upload results). The content is replaced while the file ID, link, and existing shares are preserved — use this when the user wants to update a document they already have, not get a new one. \| [share] Google Drive file ID to share (from google_drive search/list/upload results). \| [trash] Google Drive file or folder ID to move to the trash. (string) |
62
62
  | `--question` | No | [read] The question to answer about the file content. (string) |
63
+ | `--raw_file` | No | [read] Return a short-lived download of the original file without extracting or summarizing it. Google Docs, Slides and Sheets export as DOCX, PPTX and XLSX. Mutually exclusive with raw_content; ignores question. (boolean) |
63
64
  | `--raw_content` | No | [read] Return the complete converted document text (markdown) without question-answering. For programmatic consumers that need full fidelity; ignores 'question'. (boolean) |
64
65
  | `--content` | No | [upload] Text content to create as a file. Use this for creating text-based files (e.g., .txt, .md, .csv, .json, .html). Provide exactly one of 'content', 'file_path', or 'file_url'. (string) |
65
66
  | `--file_path` | No | [upload] Local path on the CLI machine. The CLI uploads it and sends 'file_url' to the server. Direct API callers must use 'file_url' or 'content'; backend file paths are not accepted. (string) |
@@ -38,7 +38,7 @@ gsk sheets [options]
38
38
  | `--initial_data` | No | [create] Optional inline initial data for the first sheet, as a 2D array where each inner array is a row. Via the gsk CLI, pass the whole array as ONE JSON string: --initial_data '[["Name","Age"],["Alice","30"]]'. Mutually exclusive with from_sandbox_path / from_aidrive_path / from_url. Prefer the from_* options when the data already exists as a file (CSV/TSV/XLSX/JSON), since 'initial_data' must round-trip through the LLM context. (array) |
39
39
  | `--from_sandbox_path` | No | [create] Absolute path inside the workflow sandbox (e.g. '/home/user/result.csv'). When set, the file is read from the sandbox and parsed into a 2D array instead of using 'initial_data'. Supported formats: csv, tsv, xlsx, json. Legacy binary .xls (BIFF) is NOT supported — re-save as .xlsx first. Mutually exclusive with from_aidrive_path / from_url / initial_data. \| [write] Absolute path inside the workflow sandbox (e.g. '/home/user/result.csv'). When set, the file is read from the sandbox and parsed into a 2D array instead of using 'values'. Supported formats: csv, tsv, xlsx, json. Legacy binary .xls (BIFF) is NOT supported — re-save as .xlsx first. Mutually exclusive with from_aidrive_path / from_url / values. \| [append] Absolute path inside the workflow sandbox (e.g. '/home/user/result.csv'). When set, the file is read from the sandbox and parsed into a 2D array instead of using 'values'. Supported formats: csv, tsv, xlsx, json. Legacy binary .xls (BIFF) is NOT supported — re-save as .xlsx first. Mutually exclusive with from_aidrive_path / from_url / values. (string) |
40
40
  | `--from_aidrive_path` | No | [create] Absolute path inside the user's AI-Drive (e.g. '/reports/sales.xlsx'). Read directly via the AI-Drive backend; the file is NOT loaded into the LLM context. Mutually exclusive with from_sandbox_path / from_url / initial_data. \| [write] Absolute path inside the user's AI-Drive (e.g. '/reports/sales.xlsx'). Read directly via the AI-Drive backend; the file is NOT loaded into the LLM context. Mutually exclusive with from_sandbox_path / from_url / values. \| [append] Absolute path inside the user's AI-Drive (e.g. '/reports/sales.xlsx'). Read directly via the AI-Drive backend; the file is NOT loaded into the LLM context. Mutually exclusive with from_sandbox_path / from_url / values. (string) |
41
- | `--from_url` | No | [create] HTTPS URL of a CSV/TSV/XLSX/JSON file. Accepts AI-Drive readable URLs, file-wrapper URLs, or any HTTPS link. Plain http:// is rejected; redirects are not followed. Mutually exclusive with from_sandbox_path / from_aidrive_path / initial_data. \| [write] HTTPS URL of a CSV/TSV/XLSX/JSON file. Accepts AI-Drive readable URLs, file-wrapper URLs, or any HTTPS link. Plain http:// is rejected; redirects are not followed. Mutually exclusive with from_sandbox_path / from_aidrive_path / values. \| [append] HTTPS URL of a CSV/TSV/XLSX/JSON file. Accepts AI-Drive readable URLs, file-wrapper URLs, or any HTTPS link. Plain http:// is rejected; redirects are not followed. Mutually exclusive with from_sandbox_path / from_aidrive_path / values. (string) |
41
+ | `--from_url` | No | [create] HTTPS URL of a CSV/TSV/XLSX/JSON file. Accepts AI-Drive readable URLs, file-wrapper URLs, or any HTTPS link. Plain http:// is rejected; hosts on private or internal networks are refused. Mutually exclusive with from_sandbox_path / from_aidrive_path / initial_data. \| [write] HTTPS URL of a CSV/TSV/XLSX/JSON file. Accepts AI-Drive readable URLs, file-wrapper URLs, or any HTTPS link. Plain http:// is rejected; hosts on private or internal networks are refused. Mutually exclusive with from_sandbox_path / from_aidrive_path / values. \| [append] HTTPS URL of a CSV/TSV/XLSX/JSON file. Accepts AI-Drive readable URLs, file-wrapper URLs, or any HTTPS link. Plain http:// is rejected; hosts on private or internal networks are refused. Mutually exclusive with from_sandbox_path / from_aidrive_path / values. (string) |
42
42
  | `--sheet_name` | No | [create] For xlsx sources only: which sheet to read. Defaults to the first sheet if omitted. Ignored for csv/tsv/json sources. \| [write] For xlsx sources only: which sheet to read. Defaults to the first sheet if omitted. Ignored for csv/tsv/json sources. \| [append] For xlsx sources only: which sheet to read. Defaults to the first sheet if omitted. Ignored for csv/tsv/json sources. (string) |
43
43
  | `--spreadsheet_id` | No | [read] The ID of the spreadsheet to read from. \| [write] The ID of the spreadsheet to write to. \| [append] The ID of the spreadsheet to append to. \| [export] The ID of the Google Sheets spreadsheet to export. (string) |
44
44
  | `--range` | No | [read] The A1 notation range to read (e.g., 'Sheet1!A1:D10', 'A1:B5'). Default: reads first sheet entirely. \| [write] The A1 notation range to write to (e.g., 'Sheet1!A1:D10'). The range should match the size of the data. Only the cells inside this range are touched — pass the smallest sheet-qualified range that covers exactly the intended change, never a wider one 'to be safe'; a wider range is the only way this tool can overwrite a collaborator's untouched cells, formulas, or formatting on a shared spreadsheet. \| [append] The A1 notation of a range to search for data table. New rows will be appended after the last row in this table. Example: 'Sheet1!A:D' or 'Sheet1' (string) |
@@ -29,7 +29,9 @@ gsk img [options]
29
29
 
30
30
  | Flag | Required | Description |
31
31
  |------|----------|-------------|
32
- | `-m`, `--model` | No | If this parameter is omitted, nano-banana-2-flash-lite is used. Pick ONLY a model described below; never pick an undescribed model name unless the user explicitly asks for it by name. gpt-image-2: GPT Image 2 - Latest OpenAI image model. Superior text rendering, editing, and face preservation. Supports text-to-image and image editing with multi-image input. nano-banana-pro: [GEMINI NANO BANANA PRO] State of the Art (SOTA) for both generation and image editing. Multi-image fusion: Combine different images into one seamless new visual. Character & style consistency: Maintain the same subject or visual style across multiple generations. Conversational editing: Edit images with simple, natural language instructions. Perfect for creative use cases, marketing, training, advertising. Supports up to 14 images as reference input. Supports high resolution output up to 2K/4K. nano-banana-2: [GEMINI NANO BANANA 2] Gemini 3.1 Flash Image. Fast and efficient with advanced reasoning. Multi-image fusion with up to 14 reference images. Supports 0.5K/1K/2K/4K resolution. Google Search grounding for real-time data. Best for high-volume, speed-optimized workflows. fal-ai/bytedance/seedream/v5/lite: Bytedance Seedream v5 Lite model for text-to-image, image-to-image (single and multiple image editing) generation with native 2K resolution and excellent text layout.fal-ai/bytedance/seedream/v5/pro: Bytedance Seedream 5.0 Pro - flagship photorealistic model for text-to-image and multi-image editing (up to 10 reference images). High-density text/infographic layout, region-precise edits, native text in 14 languages, up to 2K output. xai/grok-imagine-image: xAI Grok Imagine Image 2.0 - top-ranked text-to-image and image editing (up to 3 reference images). Strong photorealism and prompt adherence, up to 2K output. qwen-image-3: Qwen Image 3 - Alibaba's latest image model for text-to-image and reference-image editing (1-3 reference images). Superior Chinese & English text rendering, precise prompt adherence, identity-preserving edits. Best for posters, bilingual typography, and instruction-based edits. fal-ai/flux-2-pro: Flux 2 Pro model - higher quality version of Flux 2 with professional-grade output. Enhanced realism, superior text generation, and advanced editing capabilities. Ideal for high-quality realistic images and complex editing tasks.fal-ai/z-image/turbo: Z-Image Turbo model optimized for speed without sacrificing quality. Supports both text-to-image and image-to-image modes. Perfect for quick iterations, bulk generation, style transfer, and cost-effective projects.bbox-segment: A model for extracting subjects from images based on bbox region.fal-bria-rmbg: A model specialized for remove background from image. Should prioritize this tool if the user wants to remove background from image. fal-ai/recraft-clarity-upscale: A model specialized for upscale image. fal-ai/image-editing/text-removal: A specialized model for removing text and watermarks from images. Automatically detects and removes text while preserving the background and other visual elements. Use when users want to clean images, remove watermarks, or eliminate text overlays. flux-pro/outpaint: A model specialized for expand image to a specific aspect ratio. nano-banana-2-flash-lite: [GEMINI NANO BANANA 2 FLASH LITE] Fast, lightweight Gemini image model for text-to-image and image editing with multi-image input. Native 1K output. Best for speed-sensitive, high-volume workflows. (string, one of: gpt-image-2, nano-banana-pro, nano-banana-2, fal-ai/bytedance/seedream/v5/lite, fal-ai/bytedance/seedream/v5/pro, xai/grok-imagine-image, qwen-image-3, fal-ai/flux-2-pro, fal-ai/z-image/turbo, bbox-segment, fal-bria-rmbg, fal-ai/recraft-clarity-upscale, fal-ai/image-editing/text-removal, flux-pro/outpaint, nano-banana-2-flash-lite) |
32
+ | `-m`, `--model` | No | If this parameter is omitted, nano-banana-2-flash-lite is used. Pick ONLY a model described below; never pick an undescribed model name unless the user explicitly asks for it by name. gpt-image-2: GPT Image 2 - Latest OpenAI image model. Superior text rendering, editing, and face preservation. Supports text-to-image and image editing with multi-image input. gpt-image-2.5: GPT Image 2.5 - OpenAI's newest image model and the default for high-fidelity generations. Edits change only what you ask, keeping subject and composition; natural lighting, rich textures. Text-to-image and editing with multi-image input, 1k-4k output. Pick a tier with `tier` (flare = fast default arm, sunburst = precision edits; same price). Quality rungs low/medium/high/xhigh/max (auto = high): xhigh and max bill extra credits on non-Pro plans, so only use them when the user explicitly asks for that quality. fal-ai/bytedance/seedream/v5/lite: Bytedance Seedream v5 Lite model for text-to-image, image-to-image (single and multiple image editing) generation with native 2K resolution and excellent text layout.fal-ai/bytedance/seedream/v5/pro: Bytedance Seedream 5.0 Pro - flagship photorealistic model for text-to-image and multi-image editing (up to 10 reference images). High-density text/infographic layout, region-precise edits, native text in 14 languages, up to 2K output. xai/grok-imagine-image: xAI Grok Imagine Image 2.0 - top-ranked text-to-image and image editing (up to 3 reference images). Strong photorealism and prompt adherence, up to 2K output. qwen-image-3: Qwen Image 3 - Alibaba's latest image model for text-to-image and reference-image editing (1-3 reference images). Superior Chinese & English text rendering, precise prompt adherence, identity-preserving edits. Best for posters, bilingual typography, and instruction-based edits. fal-ai/flux-3: BFL FLUX 3 Image - newest Black Forest Labs model with native 2K/4K output, precise layout control and improved text rendering. Text-to-image and editing with up to 10 reference images. Ideal for posters, ads, infographics and layout-sensitive realistic images. fal-ai/z-image/turbo: Z-Image Turbo model optimized for speed without sacrificing quality. Supports both text-to-image and image-to-image modes. Perfect for quick iterations, bulk generation, style transfer, and cost-effective projects.bbox-segment: A model for extracting subjects from images based on bbox region.fal-bria-rmbg: A model specialized for remove background from image. Should prioritize this tool if the user wants to remove background from image. fal-ai/recraft-clarity-upscale: A model specialized for upscale image. fal-ai/image-editing/text-removal: A specialized model for removing text and watermarks from images. Automatically detects and removes text while preserving the background and other visual elements. Use when users want to clean images, remove watermarks, or eliminate text overlays. flux-pro/outpaint: A model specialized for expand image to a specific aspect ratio. nano-banana-2-flash-lite: [GEMINI NANO BANANA 2 FLASH LITE] Fast, lightweight Gemini image model for text-to-image and image editing with multi-image input. Native 1K output. Best for speed-sensitive, high-volume workflows. nano-banana-2.1: [GEMINI NANO BANANA 2.1] Google's newest Gemini image model: a quality step up from Nano Banana 2 for text-to-image and editing with up to 14 reference images, 1K/2K/4K output and a selectable thinking depth (thinking_level). Pick it when the user asks for it by name or wants the best Gemini result. (string, one of: gpt-image-2, gpt-image-2.5, fal-ai/bytedance/seedream/v5/lite, fal-ai/bytedance/seedream/v5/pro, xai/grok-imagine-image, qwen-image-3, fal-ai/flux-3, fal-ai/z-image/turbo, bbox-segment, fal-bria-rmbg, fal-ai/recraft-clarity-upscale, fal-ai/image-editing/text-removal, flux-pro/outpaint, nano-banana-2-flash-lite, nano-banana-2.1) |
33
+ | `--thinking_level` | No | nano-banana-2.1 only (ignored by other models): how much the model thinks before rendering. 'medium' is the default when omitted; 'minimal' is fastest; 'high' spends more reasoning on complex, multi-constraint prompts. Same price. (string, one of: minimal, medium, high) |
34
+ | `--tier` | No | gpt-image-2.5 only (ignored by other models): which arm of the model runs. 'flare' (default when omitted) is the fast arm for most work; 'sunburst' trades speed for tighter control across repeated edits. Same price. (string, one of: flare, sunburst) |
33
35
  | `<query>` (positional) | No | Detailed description of the image to generate. The prompt should be in English.However, any specific text that should appear within the image does not need to be translated.(e.g., 'A futuristic cityscape with flying cars and neon lights at night'). Omit when passing the prompt by `query_file` instead. (string) |
34
36
  | `--query_file` | No | Optional. Repo-relative path to a UTF-8 text file containing the prompt, used verbatim in place of `query` (lets you pass a long prompt by path instead of inlining it). Requires `repo_id`. When set, `query` may be omitted. (string) |
35
37
  | `--bbox` | No | BBox of the target object, for bbox segmentation modelFormat: [x1, y1, x2, y2], x1 and y1 are the top-left corner coordinates, x2 and y2 are the bottom-right corner coordinates. (array) |
@@ -36,8 +36,8 @@ gsk meeting [options]
36
36
  | `<action>` (positional) | Yes | Action to perform. 'list': List meeting notes by creation date; 'search': Search meeting notes by keyword; 'get': Get details of a specific meeting note (string, one of: list, search, get) |
37
37
  | `--page_size` | No | [list] Number of results per page. Default: 20. Max: 50. \| [search] Number of results per page. Default: 20. Max: 50. (integer) |
38
38
  | `--continuation_token` | No | [list] Token for fetching the next page of results. Returned from a previous list call. (string) |
39
+ | `--date_from` | No | [list] Only notes dated on or after this day (YYYY-MM-DD). Keep it unchanged while paging with continuation_token. \| [search] Filter meetings after this date (ISO format: YYYY-MM-DD). (string) |
39
40
  | `--keyword` | No | [search] Search term to find in meeting notes. (string) |
40
- | `--date_from` | No | [search] Filter meetings after this date (ISO format: YYYY-MM-DD). (string) |
41
41
  | `--date_to` | No | [search] Filter meetings before this date (ISO format: YYYY-MM-DD). (string) |
42
42
  | `--meeting_source` | No | [search] Filter by calendar source. (string, one of: google, outlook) |
43
43
  | `--sort_by` | No | [search] Sort order. 'relevance' for best match first, 'created_at' for newest first (default). (string, one of: created_at, relevance) |
@@ -29,9 +29,9 @@ gsk notion [options]
29
29
 
30
30
  | Flag | Required | Description |
31
31
  |------|----------|-------------|
32
- | `<action>` (positional) | Yes | Action to perform. 'search': Search pages and databases; 'read': Read content from a page; 'create': Create a new page (string, one of: search, read, create) |
32
+ | `<action>` (positional) | Yes | Action to perform. 'search': Search pages and databases; 'read': Read a page and its nested blocks. If content_complete is false, download raw_file.download_url and read it in chunks before summarizing; warnings identify content the API could not fully render.; 'create': Create a new page (string, one of: search, read, create) |
33
33
  | `--query` | No | [search] Query to search for in Notion pages. Leave empty or omit to list all available documents. (string) |
34
- | `--page_id` | No | [read] The ID of the Notion page to read and summarize. (string) |
34
+ | `--page_id` | No | [read] The ID of the Notion page to read. (string) |
35
35
  | `--title` | No | [create] The title of the new page. (string) |
36
36
  | `--content` | No | [create] The content of the page in markdown format. Supports headings, lists, code blocks, links, etc. (string) |
37
37
  | `--parent_id` | No | [create] The ID of the parent page or database where the new page will be created. Use notion_search to find available pages/databases first. (string) |
@@ -1,7 +1,8 @@
1
1
  ---
2
2
  name: gsk-onedrive
3
3
  version: 1.0.0
4
- description: 'OneDrive file operations. Actions: list, search, read, upload, share.'
4
+ description: 'OneDrive file operations. Actions: list, search, read, get_readable_url,
5
+ upload, share.'
5
6
  metadata:
6
7
  category: general
7
8
  generated_by: genspark_tool_cli/generate_skills.py
@@ -17,7 +18,7 @@ metadata:
17
18
 
18
19
  > **Note:** a unified `gsk connector` flow is rolling out (see `../gsk-connector/SKILL.md`: `gsk connector tools <id>` / `gsk connector call <id> -t <tool>`) and may not be enabled for every account yet. THIS command remains fully supported — use it directly, and it stays the fallback whenever `gsk connector` is unavailable.
19
20
 
20
- OneDrive file operations. Actions: list, search, read, upload, share.
21
+ OneDrive file operations. Actions: list, search, read, get_readable_url, upload, share.
21
22
 
22
23
  ## Usage
23
24
 
@@ -29,15 +30,16 @@ gsk onedrive [options]
29
30
 
30
31
  | Flag | Required | Description |
31
32
  |------|----------|-------------|
32
- | `<action>` (positional) | Yes | Action to perform. 'list': List files in a folder; 'search': Search files; 'read': Read and extract content from a file; 'upload': Upload a file (local path, file-wrapper URL, AI Drive path, or text content) to OneDrive; 'share': Create a sharing link (view/edit/embed; anonymous or organization scope) for a file or folder. Confirmation-gated: on a CLI with client-side confirmation the command runs as a single call after the [y/N] prompt (or --yes). (string, one of: list, search, read, upload, share) |
33
+ | `<action>` (positional) | Yes | Action to perform. 'list': List files in a folder; 'search': Search files; 'read': Read and extract content from a file; 'get_readable_url': Get a short-lived (at most 1 hour) pre-authenticated download URL for a file, for streaming it with HTTP Range requests and no auth header. Read-only; never print or share the URL; 'upload': Upload a file (local path, file-wrapper URL, AI Drive path, or text content) to OneDrive; 'share': Create a sharing link (view/edit/embed; anonymous or organization scope) for a file or folder. Confirmation-gated: on a CLI with client-side confirmation the command runs as a single call after the [y/N] prompt (or --yes). (string, one of: list, search, read, get_readable_url, upload, share) |
33
34
  | `--onedrive_url` | No | [list] A OneDrive URL to list files from. Can be a sharing link, folder link, or any OneDrive URL. (string) |
34
35
  | `--folder_id` | No | [list] The folder item ID to list contents of. Get folder IDs from previous onedrive_list_files or onedrive_search results. \| [upload] Target folder item ID (from onedrive_list_files or onedrive_search). If omitted, ``folder_path`` is used; if both are omitted, the upload goes to the OneDrive root. (string) |
35
36
  | `--folder_path` | No | [list] The folder path relative to OneDrive root. Example: 'Documents/Projects' to list files in that subfolder. \| [upload] Target folder path relative to the OneDrive root, e.g. 'Documents/Reports'. The folder must already exist. Ignored when ``folder_id`` is provided. (string) |
36
37
  | `--limit` | No | [list] Maximum number of items to return (1-200). Default: 50 (integer) |
37
38
  | `--all_pages` | No | [list] List every page in this folder. Use for complete programmatic inventory; default false. (boolean) |
38
39
  | `--query` | No | [search] The search query string. **Query Behavior**: • Spaces = AND: 'project report' finds files with BOTH terms • OR operator: 'project OR report' finds files with EITHER term • Empty string: '*' lists all files • Wildcards: 'report*' finds files starting with 'report' • Examples: 'budget.xlsx', 'meeting OR conference', '*.pdf', 'project 2024' (string) |
39
- | `--file_id` | No | [read] The ID of the file OR the OneDrive/SharePoint URL to read from OneDrive or SharePoint. Can be either a file ID (like '01W56PINYRO3...') or a full OneDrive/SharePoint URL (like 'https://domain-my.sharepoint.com/personal/user/Documents/file.pdf' or SharePoint driveItem IDs). For Teams attachments, use the 'file_id' value from Teams search results onedrive_file_params. \| [share] OneDrive item ID of the file or folder to share (from onedrive_list_files or onedrive_search). Mutually exclusive with ``file_path``. (string) |
40
+ | `--file_id` | No | [read] The ID of the file OR the OneDrive/SharePoint URL to read from OneDrive or SharePoint. Can be either a file ID (like '01W56PINYRO3...') or a full OneDrive/SharePoint URL (like 'https://domain-my.sharepoint.com/personal/user/Documents/file.pdf' or SharePoint driveItem IDs). For Teams attachments, use the 'file_id' value from Teams search results onedrive_file_params. \| [get_readable_url] The file ID or the file's OneDrive/SharePoint URL: the same forms the read action accepts. \| [share] OneDrive item ID of the file or folder to share (from onedrive_list_files or onedrive_search). Mutually exclusive with ``file_path``. (string) |
40
41
  | `--question` | No | [read] The question to answer about the file content. (string) |
42
+ | `--raw_file` | No | [read] Return a short-lived download of the original file without extracting or summarizing it. Google Docs, Slides and Sheets export as DOCX, PPTX and XLSX. Mutually exclusive with raw_content; ignores question. (boolean) |
41
43
  | `--raw_content` | No | [read] Return the complete converted document text (markdown) without question-answering. For programmatic consumers that need full fidelity; ignores 'question'. (boolean) |
42
44
  | `--file_path` | No | [upload] A Genspark file-wrapper URL, an AI Drive path (aidrive://, /aidrive/ or /mnt/aidrive/), or a local file uploaded automatically by the CLI. Direct API callers must upload local files first. \| [share] Path of the item relative to the OneDrive root, e.g. 'Documents/report.pdf'. Ignored when ``file_id`` is provided. (string) |
43
45
  | `--content` | No | [upload] Text content to upload as the file body (encoded as UTF-8). Useful for creating .txt/.md/.json/.csv files without a local copy. Mutually exclusive with ``file_path``. (string) |
@@ -208,7 +208,7 @@ Never change an entry's `general_access` (`link`, `org`) to hand out a link. The
208
208
  - **Every existing Office document** (`docx`, `xlsx`, `pptx`, in My Drive or shared): edit it through the `wo-peer` collaboration room on its source id. Never download, edit locally and overwrite it. An empty presence probe, a closed editor or `wo-peer close` does not make file replacement safe: room state can persist after users leave. Use the room for text, images, formatting, sheets and slides. If it is unavailable, return the proposed change as text and say the document was not updated.
209
209
  - **A shared Office document:** when using Drive, resolve the source first; in GenTeam use the card route below. `get_readable_url` returns `collaboration.file_id` and `collaboration.link_workspace_id`; use `wo-peer open <file_id> --context <context>` (`--link-workspace-id` is an alias). This joins the native file's room and preserves the permission context for saving. A shortcut ID is not a room ID; an editor token is not proof that an edit was acknowledged or persisted.
210
210
  - **In a GenTeam conversation** the room lane is `wo-peer` as well, on PATH when your creator is enabled for it (`gk_sb_collab_peer`): use `de channel-files` to get the card row's `link_target_id` as `<f_id>` (else the `<entry>` segment of its share link) and its `link_workspace_id`, then run `wo-peer open <f_id> --context <link_workspace_id>`. This card route does not require a creator-only `gsk drive` call. `wo-peer probe <f_id> --context <link_workspace_id>` is optional presence information, never a choice between room editing and overwrite. Omit `--context` only when the row shows none; `~/.gsk/skills/wo-peer/SKILL.md` has the GenTeam section. Two lanes, and the backend picks per call: on your creator's turn, any document your creator may edit; on a member's turn, only a card shared *editable* to this conversation — the room then acts as that member, with the authority they have in the browser. Every `wo-peer call` is re-checked for the current turn: `TOOL_OWNER_ONLY` means neither lane admits this turn (a teammate's turn on a document not shared editable here) — tell them, do not retry; "open under another person's authority" means run `open` again for this turn. Without `wo-peer` on PATH, existing Office files cannot be edited from here: say so and hand the change back as text in your reply.
211
- - **A Markdown file in Drive:** there is no live co-editing through `wo-peer`. Do not apply an edit by replacing the whole file with an upload; return the proposed text and explain that it has not been applied. This does not change Notes writes through `sb-git` with `expected_parent`.
211
+ - **A Markdown file in Drive:** Do not apply an edit by replacing the whole file with an upload. With `wo-peer` on PATH, edit it in the room on its entry id whether or not anyone has it open: when `doc_overview` shows `"writeback": true` or a person's editor in the room, the room lands the file, so edits are room edits and an explicit "overwrite / replace all" is `write_markdown` there. Finish with `wo-peer finish` and call it written only when that reports `saved`. With `"writeback": false` and nobody's editor in the room, or without `wo-peer`, there is no live co-editing: return the proposed text and explain that it has not been applied. This does not change Notes writes through `sb-git` with `expected_parent`.
212
212
  - **Replacing a standalone media or archive asset** (an image, audio/video file or ZIP): when the user explicitly asks to replace that exact asset, resolve its native source entry, record its id, and reuse that source's workspace/source/path with `gsk drive upload --local_file <replacement> --upload_path <resolved native path> --on-conflict overwrite`. This replaces the asset's bytes, subject to the existing write permissions and creator-turn gate. Never upload against a projection/alias path. Verify the returned `item.id` matches the original source id before claiming an in-place update; report a refusal or unexpected new id without retrying as a renamed copy. This lane excludes Office, Markdown, PDF and other documents; an image inside a document is edited through the document's room.
213
213
  - **Anything you cannot edit:** say why — this turn is not authorized, view-only grant, no room in this runtime, no editor for this type. Never create a new copy in place of the update.
214
214
 
@@ -234,7 +234,7 @@ explicitly requested history lookup. Product-specific memory workflows still app
234
234
 
235
235
  ## 9. Known limits, as of 2026-09-18
236
236
 
237
- - Drive Markdown has no live co-editing; whole-file upload can lose concurrent changes, so return proposed edits as text (§7).
237
+ - Drive Markdown is edited only through a `wo-peer` room that lands the file (§7); whole-file upload can lose concurrent changes, so without one return proposed edits as text.
238
238
  - A PDF is produced by exporting a paginated web document (`gsk doc export -f pdf`) and uploading it; PDF content cannot be edited in place from an agent. `download_file --file_url` can import one.
239
239
  - `upload` replies carry `url` and `item.id` since 2026-09-15; on an older runtime recover the id with `find`.
240
240
  - `doc-search` indexes My Drive only. It is switched on for internal accounts only.
@@ -235,6 +235,7 @@ needed tool or argument details are missing, or a call reports an unknown tool
235
235
  or schema mismatch. Respect connection and enablement hints, installed-ID
236
236
  instructions, and tool-specific safety requirements.
237
237
  Never assume a connector is missing without running `gsk connector search` first.
238
- The unified commands are rolling out behind a feature flag; if `gsk connector`
239
- is unavailable (unknown-command error), use the per-service commands from the
240
- `gsk-<service>` skills instead — they remain fully supported.
238
+ The `list` and `search` commands are available regardless of the unified
239
+ invocation rollout. If `guide`, `tools`, or `call` is unavailable
240
+ (unknown-command error), use the discovered binding through `gsk mcp tools`
241
+ / `gsk mcp call` or the per-service commands from the `gsk-<service>` skills.
@@ -2,7 +2,7 @@
2
2
  name: gsk-sharepoint
3
3
  version: 1.0.0
4
4
  description: 'SharePoint site, list, and file operations. Actions: list, list_items,
5
- search, read_content, read_file, upload.'
5
+ search, read_content, read_file, get_readable_url, upload.'
6
6
  metadata:
7
7
  category: general
8
8
  generated_by: genspark_tool_cli/generate_skills.py
@@ -18,7 +18,7 @@ metadata:
18
18
 
19
19
  > **Note:** a unified `gsk connector` flow is rolling out (see `../gsk-connector/SKILL.md`: `gsk connector tools <id>` / `gsk connector call <id> -t <tool>`) and may not be enabled for every account yet. THIS command remains fully supported — use it directly, and it stays the fallback whenever `gsk connector` is unavailable.
20
20
 
21
- SharePoint site, list, and file operations. Actions: list, list_items, search, read_content, read_file, upload.
21
+ SharePoint site, list, and file operations. Actions: list, list_items, search, read_content, read_file, get_readable_url, upload.
22
22
 
23
23
  ## Usage
24
24
 
@@ -30,7 +30,7 @@ gsk sharepoint [options]
30
30
 
31
31
  | Flag | Required | Description |
32
32
  |------|----------|-------------|
33
- | `<action>` (positional) | Yes | Action to perform. 'list': List files in a site or library; 'list_items': Read the rows of a SharePoint list (Microsoft Lists) with all columns expanded; 'search': Search across sites; 'read_content': Read content from a list item or page; 'read_file': Read and extract content from a file; 'upload': Upload a file to a site or library (string, one of: list, list_items, search, read_content, read_file, upload) |
33
+ | `<action>` (positional) | Yes | Action to perform. 'list': List files in a site or library; 'list_items': Read the rows of a SharePoint list (Microsoft Lists) with all columns expanded; 'search': Search across sites; 'read_content': Read content from a list item or page; 'read_file': Read and extract content from a file; 'get_readable_url': Get a short-lived (at most 1 hour) pre-authenticated download URL for a file, for streaming it with HTTP Range requests and no auth header. Read-only; never print or share the URL; 'upload': Upload a file to a site or library (string, one of: list, list_items, search, read_content, read_file, get_readable_url, upload) |
34
34
  | `--sharepoint_url` | No | [list] A SharePoint URL to list files from. Can be a site URL, document library URL (AllItems.aspx), or a folder URL. Example: 'https://company.sharepoint.com/sites/TeamSite/Shared Documents/Forms/AllItems.aspx' \| [upload] Target folder URL on SharePoint. Example: 'https://company.sharepoint.com/sites/Team/Shared Documents/Reports'. The tool resolves this to a drive + folder. (string) |
35
35
  | `--site_id` | No | [list] The SharePoint site ID. Use this to list the default document library of a specific site. Get site IDs from sharepoint_search results. \| [list_items] The SharePoint site ID that owns the list. Get it from sharepoint_search results. \| [read_content] Site ID from SharePoint search results siteInfo. Required for listItem content type. \| [upload] SharePoint site ID. The file is uploaded to the default document library; combine with ``folder_id`` to target a subfolder. (string) |
36
36
  | `--drive_id` | No | [list] The document library (drive) ID. Use this to list files in a specific document library. \| [upload] Document library (drive) ID. Combine with ``folder_id`` to target a specific folder. (string) |
@@ -39,13 +39,14 @@ gsk sharepoint [options]
39
39
  | `--all_pages` | No | [list] List every page in this folder. Use for complete programmatic inventory; default false. \| [list_items] Read every page of the list. Use for complete programmatic inventory; default false. (boolean) |
40
40
  | `--list_id` | No | [list_items] The list ID (GUID). Get it from sharepoint_search results of type 'list'. \| [read_content] List ID from SharePoint search results siteInfo. Required for listItem content type. (string) |
41
41
  | `--list_url` | No | [list_items] A SharePoint list URL such as 'https://company.sharepoint.com/sites/Team/Lists/Requests/AllItems.aspx'. Alternative to site_id + list_id. (string) |
42
- | `--query` | No | [search] The search query string using KQL syntax. **Query Behavior**: • Spaces = AND: 'project report' finds items with BOTH terms • OR operator: 'project OR report' finds items with EITHER term • Empty string: '*' returns all items • Mixed language: automatically optimized (e.g., 'プロジェクト project' → 'プロジェクト OR project') • Examples: 'budget 2024', 'meeting OR conference', 'from:john project', 'hasAttachment:true report' (string) |
42
+ | `--query` | No | [search] The search query string using KQL syntax. **Query Behavior**: • Spaces = AND: 'project report' finds items with BOTH terms • OR operator: 'project OR report' finds items with EITHER term • Empty string: '*' returns all items • Mixed language: a query mixing Chinese and English terms is rewritten as 'term OR term' before it is sent • Examples: 'budget 2024', 'meeting OR conference', 'from:john project', 'hasAttachment:true report' (string) |
43
43
  | `--entity_types` | No | [search] Types of SharePoint content to search. Defaults to all types. (array, default: `['site', 'listItem', 'list', 'driveItem']`) |
44
44
  | `--content_id` | No | [read_content] The ID of the SharePoint content to read. Can be a site ID, page ID, list ID, list item ID from SharePoint search results, or a SharePoint URL for direct file access. For Teams attachments, use the 'content_id' value from Teams search results onedrive_file_params. (string) |
45
45
  | `--content_type` | No | [read_content] The type of SharePoint content to read. Use 'driveItem' for SharePoint files, 'listItem' for SharePoint pages/list items. (string, one of: site, page, list, listItem, driveItem) |
46
46
  | `--question` | No | [read_content] The question to answer about the SharePoint content. \| [read_file] The question to answer about the file content. (string) |
47
47
  | `--list_item_id` | No | [read_content] List item ID from SharePoint search results siteInfo. Required for listItem content type. (string) |
48
- | `--file_id` | No | [read_file] The ID of the file OR the SharePoint URL to read from Microsoft OneDrive/SharePoint/Teams. Can be either a file ID (like '01W56PINYRO3...') or a full SharePoint URL (like 'https://domain.sharepoint.com/...'). (string) |
48
+ | `--file_id` | No | [read_file] The ID of the file OR the SharePoint URL to read from Microsoft OneDrive/SharePoint/Teams. Can be either a file ID (like '01W56PINYRO3...') or a full SharePoint URL (like 'https://domain.sharepoint.com/...'). \| [get_readable_url] The file ID or the file's OneDrive/SharePoint URL: the same forms the read_file action accepts. (string) |
49
+ | `--raw_file` | No | [read_file] Return a short-lived download of the original file without extracting or summarizing it. Google Docs, Slides and Sheets export as DOCX, PPTX and XLSX. Mutually exclusive with raw_content; ignores question. (boolean) |
49
50
  | `--raw_content` | No | [read_file] Return the complete converted document text (markdown) without question-answering. For programmatic consumers that need full fidelity; ignores 'question'. (boolean) |
50
51
  | `--file_path` | No | [upload] A Genspark file-wrapper URL, an AI Drive path (aidrive://, /aidrive/ or /mnt/aidrive/), or a local file uploaded automatically by the CLI. Direct API callers must upload local files first. (string) |
51
52
  | `--content` | No | [upload] Text content to upload as the file body (encoded as UTF-8). Useful for creating .txt/.md/.json/.csv files without a local copy. Mutually exclusive with ``file_path``. (string) |
@@ -33,7 +33,7 @@ gsk video [options]
33
33
  | `<query>` (positional) | No | Detailed, self-contained description of the video to generate, written in English. This text is sent to the video model verbatim as the generation prompt, so put all the visual detail here — but NEVER output settings: text like '16:9' or '4 seconds' in the prompt may be rendered literally into the scene. Pass aspect ratio via the `aspect_ratio` parameter and length via `duration`. duration is recommended to be 5 ~ 10 seconds. For image-to-image transitions (user provides start and end frames) e.g., 'A timelapse of a flower blooming in a garden'. Omit when passing the prompt by `query_file` instead. Or omit on a draft_task_id finalize (it reuses the draft's prompt). (string) |
34
34
  | `--query_file` | No | Optional. Repo-relative path to a UTF-8 text file containing the prompt, used verbatim in place of `query` (lets you pass a long prompt by path instead of inlining it). Requires `repo_id`. When set, `query` may be omitted. (string) |
35
35
  | `--file_name` | No | The name of the video to generate. (string, null) |
36
- | `-m`, `--model` | Yes | The model to use for video generation. kling/v3: Latest Kling V3. Supports native audio, but generates a SILENT video unless audio_enable=true. image_urls are frames, not references: 1 image = first frame (i2v); 2 images = first + last frame (the 2nd is the END frame). No reference mode (use kling/o3 with reference_mode for reference-driven generation). Pro/Standard/Turbo tiers (set via the tier parameter; turbo is the fastest arm but has no audio and no first/last-frame control). Supported ratios: 16:9, 9:16, 1:1. Duration: 3-15s. kling/o3: Kling O3. REQUIRES at least one input image or a video_url (no text-to-video). image_urls are frames (1 = first, 2 = first + last) unless reference_mode=true: style/character references, max 4 total including elements. video_url switches to video-to-video (video_mode 'reference' = motion guide, 'edit' = restyle in footage). Native audio via audio_enable. Pro/Standard tiers. Supported ratios: 16:9, 9:16, 1:1. Duration: 3-15s. gemini/veo3.1: Gemini Veo 3.1 - Latest version with enhanced quality and features. Supports text-to-video and image-to-video generation with improved quality. image_urls are frames unless reference_mode: 1 image = first frame, exactly 2 = first/last frame transition, 3 (or reference_mode=true) = style/character references (max 3, 8s only). video_url (MP4 source) = video EXTENSION mode: continues from the last frame, 7s, up to 1080p. Duration: 4s/6s/8s. Supported ratios: 16:9, 9:16. Supports tier (standard \| fast). Resolution: 720p, 1080p, 4k. minimax/h3: MiniMax H3 2K video model. Supports text-to-video, image-to-video with first/last frame control, and reference-to-video (up to 9 reference images, 3 reference videos, 3 reference audio clips — refer to them in the prompt as 'Image 1', 'Video 1', 'Audio 1', not @-style). Keyframes and references are mutually exclusive. Supported ratios: adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16. Duration: 5-15s. Resolution: 768p or 2K (default). minimax/h3-max: MiniMax H3 Max, a distinct post-trained model with faster generation, stronger prompt adherence, and improved aesthetics. Supports text, first/middle/last frame keyframes, and image/video/audio references — keyframes and references COMBINE on this model (set keyframes via first_frame_url/last_frame_url/middle_image_url + middle_frame_time; the middle frame needs an explicit first_frame_url AND last_frame_url — image_urls are all references here — native 480p/768p, and at least one reference). tier=turbo selects the faster, half-price text/image arm; reference and middle-frame inputs use standard. Duration: 5-15s. Resolution: 480p or 768p. Reference requests also incur a reference-token fee on top of the output charge — a reference video especially can cost more than the output itself. wan/v2.7: Wan v2.7 with enhanced motion smoothness and scene fidelity. Supports text-to-video, image-to-video, reference-to-video, and edit-video. Ratios: 16:9, 9:16, 1:1. Duration: 5s. Resolution: 480p, 720p vidu/q3: Vidu Q3 model with enhanced quality and audio generation. Supports text-to-video, image-to-video, and reference-to-video (reference_mode with 1-4 image_urls keeps subjects/scenes consistent; no turbo tier in reference mode). tier=turbo runs the faster turbo arm at half the price. Supported ratios: 16:9, 9:16, 4:3, 3:4, 1:1. Duration: 1-16s. Resolution: 720p, 1080prunway/gen4_turbo: A model for generate video with high quality, fast.Supported ratios: 5:3, 3:5. Only support i2v. Duration: 5s, 10spixverse/v6: PixVerse V6 latest model with lifelike motion, richer skin detail, real emotions. Full cinematic control including choreography and camera. Supports text-to-video, image-to-video, transition, and video extend generation. VFX, time-lapse, transformation scenes, product demos, 360° views, multi-shot storytelling. Extend: pass video_url to extend an existing video. Supported ratios: 16:9, 9:16, 4:3, 1:1, 3:4. Duration: 5s, 8s. pixverse/c1: PixVerse C1 with native audio (audio_enable=true), text-to-video, image-to-video, transitions (2 images = first/last frame) and reference-to-video (reference_mode with 1-7 image_urls; address them in the prompt as @image1..@image7). No video extend. Supported ratios: 16:9, 9:16, 4:3, 3:4, 1:1, 3:2, 2:3, 21:9. Duration: 1-15s. Resolution: 360p, 540p, 720p, 1080p. fal-ai/bytedance/seedance-2.0: Bytedance Seedance 2.0 model for highest quality video generation with native audio and lip-sync. Supports text-to-video and image-to-video with first/last frame control. Supported ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16. Duration: 4-15s. Resolution: 480p, 720p, or 1080p on the standard tier (~2.25x cost; fast/mini cap at 720p). tier picks the variant: standard, fast, or mini (cheapest, ~half the standard price). Also supports reference-to-video with up to 9 images, 3 videos, or 3 audio refs via settings.fal-ai/bytedance-upscaler/upscale/video: ByteDance Video Upscaler for enhancing video quality. Upscales videos to higher resolutions (2k) Requires video_url parameter. Does NOT generate new videos. Use when user wants to improve quality of existing videos.xai/grok-imagine-video: xAI Grok Imagine Video v1.5 for high-quality video generation. Supports text-to-video and image-to-video generation. 2+ image_urls (or reference_mode=true) = style/character references, up to 7 (reference mode caps at 720p). video_url (MP4, 2-15s source) = video EXTENSION mode: continues from the last frame, 2-10s extension, 720p. 480p/720p/1080p output. Supported ratios: 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16. Duration: 1-15s. alibaba/happy-horse: Alibaba Happy Horse video model. High-quality generation from text, or image-to-video from a single first-frame image (one image_url without reference_mode). Supported ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 5:4, 4:5. Duration: 3-15s. Resolution: 720p, 1080p.alibaba/happy-horse/reference-to-video: Alibaba Happy Horse reference-to-video. Generate video from 1-9 reference images; address subjects in the prompt as character1..character9 (order matches image_urls). Requires image_urls. Supported ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 5:4, 4:5. Duration: 3-15s. Resolution: 720p, 1080p.alibaba/happy-horse/video-edit: Alibaba Happy Horse video-edit. Edit a source video using a text prompt; optional 1-5 reference images addressed as @Image1..@Image5. Requires video_url (MP4/MOV, 3-60s). Output preserves source aspect ratio, capped at 15s. Resolution: 720p, 1080p.gemini/omni-flash: Google's multimodal video model with native audio. Supports text-to-video, image-to-video (1 image as first frame), reference-to-video (set reference_mode with image_urls to use images as subject/style references — even a single image; 2+ images are references by default), and video editing (pass video_url to edit an existing clip — restyle, restage, add objects). Bind image roles in the prompt with <FIRST_FRAME> / <IMAGE_REF_0>. Ratios: 16:9, 9:16. Duration: 3-10s. Resolution: 720p. bfl/flux-3-preview-high: BFL FLUX 3 video model with native audio. Supports text-to-video and 1-10 ordered keyframes, or continuation from one source video selected with input_mode=start_video. Ratios: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16. Duration: 5-20s. Resolution: 720p, 1080p. Only one input family may be used per request.fal-ai/bytedance/seedance-2.5: Bytedance Seedance 2.5 for native 30-second single-shot video with synchronized audio. Supports text-to-video and image-to-video with first/last frame control. No tier variants. Supported ratios: auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16. Duration: 4-30s, or 0 = auto (needs video refs). Resolution: 480p, 720p, or 1080p (~2.46x cost). Also supports reference-to-video (up to 30 images, 10 videos, 10 audio refs; no image required), video EDITING and EXTENSION — source in video_urls, the prompt describes the change or continuation.wan/v3.0: Alibaba Wan 3.0 — next-gen open-weight Wan with native audio and single-pass clips up to 30s. Supports text-to-video, image-to-video with first/last frame control, and reference-to-video (reference_mode with up to 10 reference images, 5 videos and 5 audio clips, each ref modality <=15s combined — address them positionally in the prompt as 'Image 1', 'Video 1', 'Audio 1'). tier=fast runs the accelerated Prime arm (~1.4x cost). Supported ratios: adaptive, 16:9, 4:3, 1:1, 3:4, 9:16. Duration: 2-30s. Resolution: 480p, 720p, 1080p. Duration ranges above are hard caps; out-of-range values are clamped to the nearest supported value. (string, one of: kling/v3, kling/o3, gemini/veo3.1, minimax/h3, minimax/h3-max, wan/v2.7, vidu/q3, runway/gen4_turbo, pixverse/v6, pixverse/c1, fal-ai/bytedance/seedance-2.0, fal-ai/bytedance-upscaler/upscale/video, xai/grok-imagine-video, alibaba/happy-horse, alibaba/happy-horse/reference-to-video, alibaba/happy-horse/video-edit, gemini/omni-flash, bfl/flux-3-preview-high, fal-ai/bytedance/seedance-2.5, wan/v3.0) |
36
+ | `-m`, `--model` | Yes | The model to use for video generation. kling/v3: Latest Kling V3. Supports native audio, but generates a SILENT video unless audio_enable=true. image_urls are frames, not references: 1 image = first frame (i2v); 2 images = first + last frame (the 2nd is the END frame). No reference mode (use kling/o3 with reference_mode for reference-driven generation). Pro/Standard/Turbo tiers (set via the tier parameter; turbo is the fastest arm but has no audio and no first/last-frame control). Supported ratios: 16:9, 9:16, 1:1. Duration: 3-15s. kling/o3: Kling O3. REQUIRES at least one input image or a video_url (no text-to-video). image_urls are frames (1 = first, 2 = first + last) unless reference_mode=true: style/character references, max 4 total including elements. video_url switches to video-to-video (video_mode 'reference' = motion guide, 'edit' = restyle in footage). Native audio via audio_enable. Pro/Standard tiers. Supported ratios: 16:9, 9:16, 1:1. Duration: 3-15s. gemini/veo3.1: Gemini Veo 3.1 - Latest version with enhanced quality and features. Supports text-to-video and image-to-video generation with improved quality. image_urls are frames unless reference_mode: 1 image = first frame, exactly 2 = first/last frame transition, 3 (or reference_mode=true) = style/character references (max 3, 8s only). video_url (MP4 source) = video EXTENSION mode: continues from the last frame, 7s, up to 1080p. Duration: 4s/6s/8s. Supported ratios: 16:9, 9:16. Supports tier (standard \| fast). Resolution: 720p, 1080p, 4k. minimax/h3: MiniMax H3 2K video model. Supports text-to-video, image-to-video with first/last frame control, and reference-to-video (up to 9 reference images, 3 reference videos, 3 reference audio clips — refer to them in the prompt as 'Image 1', 'Video 1', 'Audio 1', not @-style). Keyframes and references are mutually exclusive. Supported ratios: adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16. Duration: 5-15s. Resolution: 768p or 2K (default). minimax/h3-max: MiniMax H3 Max, a distinct post-trained model with faster generation, stronger prompt adherence, and improved aesthetics. Supports text, first/middle/last frame keyframes, and image/video/audio references — keyframes and references COMBINE on this model (set keyframes via first_frame_url/last_frame_url/middle_image_url + middle_frame_time; the middle frame needs an explicit first_frame_url AND last_frame_url — image_urls are all references here — native 480p/768p, and at least one reference). tier=turbo selects the faster, half-price text/image arm; reference and middle-frame inputs use standard. Duration: 5-15s. Resolution: 480p or 768p. Reference requests also incur a reference-token fee on top of the output charge — a reference video especially can cost more than the output itself. wan/v2.7: Wan v2.7 with enhanced motion smoothness and scene fidelity. Supports text-to-video, image-to-video, reference-to-video, and edit-video. Ratios: 16:9, 9:16, 1:1. Duration: 5s. Resolution: 480p, 720p vidu/q4: Vidu Q4, Vidu's next-generation flagship with native audio. REQUIRES an image (no text-to-video): 1 image_urls entry = first frame (image-to-video, framing follows the image); reference_mode (or 2+ images, or audio_urls) = reference-to-video with up to 12 reference images and 3 voice clips, addressed in the prompt as [@reference_image_1].. / [reference_audio_1].. No end frame, no tiers. Supported ratios (reference mode): 16:9, 9:16, 4:3, 3:4, 1:1. Duration: 3-16s. Resolution: 540p, 720p, 1080p, 2K, 4Krunway/gen4_turbo: A model for generate video with high quality, fast.Supported ratios: 5:3, 3:5. Only support i2v. Duration: 5s, 10spixverse/v6: PixVerse V6 latest model with lifelike motion, richer skin detail, real emotions. Full cinematic control including choreography and camera. Supports text-to-video, image-to-video, transition, and video extend generation. VFX, time-lapse, transformation scenes, product demos, 360° views, multi-shot storytelling. Extend: pass video_url to extend an existing video. Supported ratios: 16:9, 9:16, 4:3, 1:1, 3:4. Duration: 5s, 8s. pixverse/c1: PixVerse C1 with native audio (audio_enable=true), text-to-video, image-to-video, transitions (2 images = first/last frame) and reference-to-video (reference_mode with 1-7 image_urls; address them in the prompt as @image1..@image7). No video extend. Supported ratios: 16:9, 9:16, 4:3, 3:4, 1:1, 3:2, 2:3, 21:9. Duration: 1-15s. Resolution: 360p, 540p, 720p, 1080p. fal-ai/bytedance/seedance-2.0: Bytedance Seedance 2.0 model for highest quality video generation with native audio and lip-sync. Supports text-to-video and image-to-video with first/last frame control. Supported ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16. Duration: 4-15s. Resolution: 480p, 720p, or 1080p on the standard tier (~2.25x cost; fast/mini cap at 720p). tier picks the variant: standard, fast, or mini (cheapest, ~half the standard price). Also supports reference-to-video with up to 9 images, 3 videos, or 3 audio refs via settings.fal-ai/topaz/upscale/video: Topaz Labs Video Upscaler, the preferred upscaler: 2x enhancement of an existing video (source up to 60s) with real detail recovery. Requires video_url parameter. Does NOT generate new videos. Use when user wants to improve quality of existing videos.fal-ai/bytedance-upscaler/upscale/video: ByteDance Video Upscaler for enhancing video quality. Upscales videos to higher resolutions (2k) Requires video_url parameter. Does NOT generate new videos. Use when user wants to improve quality of existing videos.xai/grok-imagine-video: xAI Grok Imagine Video v1.5 for high-quality video generation. Supports text-to-video and image-to-video generation. 2+ image_urls (or reference_mode=true) = style/character references, up to 7 (reference mode caps at 720p). video_url (MP4, 2-15s source) = video EXTENSION mode: continues from the last frame, 2-10s extension, 720p. 480p/720p/1080p output. Supported ratios: 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16. Duration: 1-15s. tier=lite runs the lightweight low-cost 1.5 Lite arm (text-to-video and image-to-video only — no references, no extension). alibaba/happy-horse: Alibaba Happy Horse video model. High-quality generation from text, or image-to-video from a single first-frame image (one image_url without reference_mode). Supported ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 5:4, 4:5. Duration: 3-15s. Resolution: 720p, 1080p.alibaba/happy-horse/reference-to-video: Alibaba Happy Horse reference-to-video. Generate video from 1-9 reference images; address subjects in the prompt as character1..character9 (order matches image_urls). Requires image_urls. Supported ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 5:4, 4:5. Duration: 3-15s. Resolution: 720p, 1080p.alibaba/happy-horse/video-edit: Alibaba Happy Horse video-edit. Edit a source video using a text prompt; optional 1-5 reference images addressed as @Image1..@Image5. Requires video_url (MP4/MOV, 3-60s). Output preserves source aspect ratio, capped at 15s. Resolution: 720p, 1080p.gemini/omni-flash: Google's multimodal video model with native audio. Supports text-to-video, image-to-video (1 image as first frame), reference-to-video (set reference_mode with image_urls to use images as subject/style references — even a single image; 2+ images are references by default), and video editing (pass video_url to edit an existing clip — restyle, restage, add objects). Bind image roles in the prompt with <FIRST_FRAME> / <IMAGE_REF_0>. Ratios: 16:9, 9:16. Duration: 3-10s. Resolution: 720p. bfl/flux-3-preview-high: BFL FLUX 3 video model with native audio. Supports text-to-video and 1-10 ordered keyframes, or continuation from one source video selected with input_mode=start_video. Ratios: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16. Duration: 5-20s. Resolution: 720p, 1080p. Only one input family may be used per request.fal-ai/bytedance/seedance-2.5: Bytedance Seedance 2.5 for native 30-second single-shot video with synchronized audio. Supports text-to-video and image-to-video with first/last frame control. No tier variants. Supported ratios: auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16. Duration: 4-30s, or 0 = auto (needs video refs). Resolution: 480p, 720p, or 1080p (~2.46x cost). Also supports reference-to-video (up to 30 images, 10 videos, 10 audio refs; no image required), video EDITING and EXTENSION — source in video_urls, the prompt describes the change or continuation.wan/v3.0: Alibaba Wan 3.0 — next-gen open-weight Wan with native audio and single-pass clips up to 30s. Supports text-to-video, image-to-video with first/last frame control, and reference-to-video (reference_mode with up to 10 reference images, 5 videos and 5 audio clips, each ref modality <=15s combined — address them positionally in the prompt as 'Image 1', 'Video 1', 'Audio 1'). tier=fast runs the accelerated Prime arm (~1.4x cost). Supported ratios: adaptive, 16:9, 4:3, 1:1, 3:4, 9:16. Duration: 2-30s. Resolution: 480p, 720p, 1080p. Duration ranges above are hard caps; out-of-range values are clamped to the nearest supported value. (string, one of: kling/v3, kling/o3, gemini/veo3.1, minimax/h3, minimax/h3-max, wan/v2.7, vidu/q4, runway/gen4_turbo, pixverse/v6, pixverse/c1, fal-ai/bytedance/seedance-2.0, fal-ai/topaz/upscale/video, fal-ai/bytedance-upscaler/upscale/video, xai/grok-imagine-video, alibaba/happy-horse, alibaba/happy-horse/reference-to-video, alibaba/happy-horse/video-edit, gemini/omni-flash, bfl/flux-3-preview-high, fal-ai/bytedance/seedance-2.5, wan/v3.0) |
37
37
  | `-i`, `--image_urls` | No | The URLs of the images to use as reference key frames for the video generation. For single image models, provide 1 image. For multi-image models (like kling/v1.6/pro/elements), provide 1-4 images in sequence order. For start-end models (like vidu, pixverse), provide exactly 2 images (start and end frames). (default is [], if the task is based on one or more reference images, it is required) IMPORTANT: without reference_mode, the first image becomes the video's literal opening frame — identity markers visible in it (flags, jerseys, text, logos, faces) persist in the output and the text prompt CANNOT override them. When generating a batch of subject-specific clips (per-country / per-person / per-product), each clip needs an image matching its own subject — never reuse another subject's image. (array) |
38
38
  | `--first_frame_url` | No | MiniMax H3 Max keyframe control: image URL the video opens on exactly, ALONGSIDE reference_mode references (the output canvas follows this image). Without reference_mode the first image_urls entry already is the first frame; in reference_mode (including any middle-frame request) it is REQUIRED, because image_urls entries are all subject references. H3 Max only: other models ignore it, and base minimax/h3 rejects it (frames there come from image_urls). (string) |
39
39
  | `--middle_image_url` | No | MiniMax H3 Max keyframe control: image the video passes through at middle_frame_time. Requires an explicit first frame (first_frame_url) AND last frame (last_frame_url) — a middle frame forces reference mode, where every image_urls entry is a subject reference — plus native 480p/768p and at least one reference image/video/audio. H3 Max only: other models ignore it, and base minimax/h3 rejects it. (string) |
@@ -54,6 +54,7 @@ gsk video [options]
54
54
  | `--video_size` | No | Output resolution. 'auto' uses the model default (usually 720p). MiniMax H3 defaults to 2K with a cheaper 768p tier; MiniMax H3 Max uses 480p or 768p. Values a model does not publish fall back to its default. Higher tiers bill more per second — see each model's Resolution line. Default: auto. (string, one of: auto, 480p, 720p, 768p, 1080p, 2K, 4k, default: `auto`) |
55
55
  | `--draft` | No | Seedance 2.5 only: render a 480p draft (billed at the 480p rate) to check structure, motion and prompt fit before the full render. Ignored on other models. (boolean, default: `False`) |
56
56
  | `--draft_task_id` | No | task_id of a successful Seedance 2.5 draft (within 7 days): renders its final 1080p video, reusing the draft's prompt, references, duration and ratio. Send no other inputs and no draft flag with it; bills the 1080p rate. (string) |
57
+ | `--estimate` | No | Dry run: return the credit estimate for exactly these settings (model, duration, resolution, tier, audio, draft) and generate nothing - nothing is billed. Run it with the same flags before a paid render when you must decide whether to confirm the spend first. (boolean, default: `False`) |
57
58
  | `--reference_mode` | No | Enable reference-to-video mode: provided images guide character/style rather than being used as the first frame. Requires image_urls. For Seedance 2.0: routes to seedance-2.0/ref (combinable with the fast/mini tiers, supports up to 9 reference images plus optional reference video/audio). For Veo 3.1 base model: upgrades to veo3.1/reference-to-video. For MiniMax H3: treats images as subject/style references instead of keyframes (any video_urls/audio_urls also force reference mode). For Vidu Q3: routes to the reference-to-video mix endpoint (1-4 reference images). For PixVerse C1: 1-7 subject references (@image1..@image7 in the prompt). For Grok Imagine Video: 1-7 references (2+ images switch automatically; caps output at 720p). For Kling O3: 1-4 references incl. elements (3+ images switch automatically). Ignored on other models. Default: false. (boolean, default: `False`) |
58
59
 
59
60
  ## Local File Support