@genspark/cli 1.5.0 → 1.5.2

package/skills/gsk-task-continue/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: gsk-task-continue
 version: 1.0.0
-description: Continue an existing task project you previously created with create_task
-  by sending a follow-up instruction — use this to edit, revise, or extend an existing
-  deliverable (e.g. 'add a slide on pricing', 'shorten the intro') instead of create_task,
-  which mints and bills a brand-new task. Works for any create_task task type (slides,
-  docs, sheets, deep_research, website, ...). The project must belong to you or be
-  shared with you with edit (write) permission. Runs the agent to completion and returns
-  the task_url plus the updated result artifacts.
+description: Send a follow-up instruction to an existing task project — use this to
+  edit, revise, extend, or converse with a task's deliverable (e.g. 'add a slide on
+  pricing', 'shorten the intro') instead of `task create`, which mints and bills a
+  brand-new task. Works for any task type (slides, docs, sheets, deep_research, website,
+  super_agent, ...). The project must belong to you or be shared with you with edit
+  (write) permission. Submits and returns immediately by default (poll `task status`);
+  pass wait=true for the legacy blocking run.
 metadata:
   category: general
   requires:
@@ -20,7 +20,7 @@ metadata:
 
 **PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
 
-Continue an existing task project you previously created with create_task by sending a follow-up instruction — use this to edit, revise, or extend an existing deliverable (e.g. 'add a slide on pricing', 'shorten the intro') instead of create_task, which mints and bills a brand-new task. Works for any create_task task type (slides, docs, sheets, deep_research, website, ...). The project must belong to you or be shared with you with edit (write) permission. Runs the agent to completion and returns the task_url plus the updated result artifacts.
+Send a follow-up instruction to an existing task project — use this to edit, revise, extend, or converse with a task's deliverable (e.g. 'add a slide on pricing', 'shorten the intro') instead of `task create`, which mints and bills a brand-new task. Works for any task type (slides, docs, sheets, deep_research, website, super_agent, ...). The project must belong to you or be shared with you with edit (write) permission. Submits and returns immediately by default (poll `task status`); pass wait=true for the legacy blocking run.
 
 ## Usage
 
@@ -32,8 +32,11 @@ gsk task_continue [options]
 
 | Flag | Required | Description |
 |------|----------|-------------|
-| `<project_id>` (positional) | Yes | The project_id returned by create_task (data.project_id in its response). (string) |
-| `-m`, `--message` | Yes | The follow-up instruction to send to the task agent — state concretely what to change, add, or redo. The agent already has the project's own history, but embed any NEW material or file URLs the change needs. (string) |
+| `<project_id>` (positional) | Yes | The task's project_id — from `gsk task status <run_id>` once an async submit started executing, or data.project_id of a blocking (--wait true) run. (string) |
+| `-m`, `--message` | Yes | The follow-up instruction to send to the task agent — state concretely what to change, add, or redo. The agent already has the project's own history. For Design, pass NEW references in attachments (the CLI --image/--file flags build these automatically). (string) |
+| `-last-seen-revision`, `--last_seen_revision` | No | Optional optimistic-concurrency token from task_status. For Design projects the update is rejected when it is already stale before the continuation starts. (string) |
+| `--attachments` | No | Ordered new references for a Design continuation. They are appended only after last_seen_revision passes. (array) |
+| `--wait` | No | Default false: the follow-up is SUBMITTED to the durable runtime and this call returns immediately with its run_id — poll `gsk task status <run_id>`. Pass true to block until the turn completes and get the full result inline (legacy behavior; can take minutes, so set your shell timeout to 1800000 ms). (boolean) |
 
 ## See Also
 

package/skills/gsk-task-info/SKILL.md

@@ -0,0 +1,36 @@
+---
+name: gsk-task-info
+version: 1.0.0
+description: 'Read a task''s execution output: recent activity (messages including
+  tool usage), current state, and extracted result artifacts — mid-run or after completion.
+  Use `task status` for cheap polling; use this when you need the content.'
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk task info --help
+---
+
+# gsk-task-info
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Read a task's execution output: recent activity (messages including tool usage), current state, and extracted result artifacts — mid-run or after completion. Use `task status` for cheap polling; use this when you need the content.
+
+## Usage
+
+```bash
+gsk task info [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<project_id>` (positional) | Yes | The task's project_id (from the blocking run's response, or from `gsk task status <run_id>` once an async submit started executing). (string) |
+| `-n`, `--limit` | No | How many recent activity entries to return (default 10, max 50). (integer) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-task-status/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: gsk-task-status
 version: 1.0.0
-description: 'Look up an existing task project previously created with create_task:
-  returns its status, page URL (task_url), and extracted result artifacts. Use this
-  — never a new create_task call — when you need the link or outcome of a task you
-  already created.'
+description: 'Look up an existing task: pass the run_id from an async submit (sb_task_run::…)
+  for its durable lifecycle state, or the project_id for status, page URL (task_url),
+  and extracted result artifacts. Use this — never a new create — when you need the
+  link or outcome of a task you already created.'
 metadata:
   category: general
   requires:
@@ -17,7 +17,7 @@ metadata:
 
 **PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
 
-Look up an existing task project previously created with create_task: returns its status, page URL (task_url), and extracted result artifacts. Use this — never a new create_task call — when you need the link or outcome of a task you already created.
+Look up an existing task: pass the run_id from an async submit (sb_task_run::…) for its durable lifecycle state, or the project_id for status, page URL (task_url), and extracted result artifacts. Use this — never a new create — when you need the link or outcome of a task you already created.
 
 ## Usage
 
@@ -29,7 +29,7 @@ gsk task_status [options]
 
 | Flag | Required | Description |
 |------|----------|-------------|
-| `<project_id>` (positional) | Yes | The project_id returned by create_task (data.project_id in its response). (string) |
+| `<project_id>` (positional) | Yes | The task's identifier: either the run_id from an async submit (sb_task_run::…) or the project_id from a finished/blocking run. (string) |
 
 ## See Also
 

package/skills/gsk-task-stop/SKILL.md

@@ -0,0 +1,35 @@
+---
+name: gsk-task-stop
+version: 1.0.0
+description: 'Stop a running task: pass the run_id from the submit response (preferred)
+  or the task''s project_id. Aborts the in-flight run; safe when nothing is running.
+  Requires edit (write) permission.'
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk task stop --help
+---
+
+# gsk-task-stop
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Stop a running task: pass the run_id from the submit response (preferred) or the task's project_id. Aborts the in-flight run; safe when nothing is running. Requires edit (write) permission.
+
+## Usage
+
+```bash
+gsk task stop [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<id>` (positional) | Yes | The run_id from the submit response (sb_task_run::…), or the task's project_id. (string) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-video-generation/SKILL.md

@@ -32,19 +32,22 @@ gsk video [options]
 | `<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. (string) |
 | `--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) |
 | `--file_name` | No | The name of the video to generate.  (string, null) |
-| `-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. Pro/Standard tiers (set via the tier parameter). 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. Duration: 8s. Supported ratios: 16:9, 9:16. Supports tier (standard \| fast) and hd_mode (1080p quality). gemini/veo3.1/reference-to-video: Gemini Veo 3.1 Reference-to-Video mode. Generate video using multiple reference images to guide the generation. Requires 1+ reference images. Duration: 8s. Supported ratios: 16:9, 9:16. Supports tier (standard \| fast) and hd_mode options. gemini/veo3.1/first-last-frame-to-video: Veo 3.1 First-Last Frame mode. Generate video by specifying first and last frames for precise transitions. Requires exactly 2 images. Duration: 8s. Supported ratios: 16:9, 9:16. Supports tier (standard \| fast) and hd_mode options.minimax/h3: MiniMax H3 next-generation 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: 2K. 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 both text-to-video and image-to-video generation. 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.  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; hd_mode renders native 1080p (~2.25x cost; fast/mini tiers stay 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 model for high-quality video generation. Supports both text-to-video and image-to-video generation. 720p HD output. Flexible duration 1-15 seconds. Supported ratios: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, 9:21. Duration: 1-15s. xai/grok-imagine-video/video-extension: xAI Grok Imagine Video Extension for extending existing videos. Requires video_url parameter with source video URL (MP4, 2-15s). 720p HD output. Duration: 2-10s. Ratios: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, 9:21.alibaba/happy-horse: Alibaba Happy Horse text-to-video model. High-quality video generation from text. 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.  (string, one of: kling/v3, gemini/veo3.1, gemini/veo3.1/reference-to-video, gemini/veo3.1/first-last-frame-to-video, minimax/h3, wan/v2.7, vidu/q3, runway/gen4_turbo, pixverse/v6, fal-ai/bytedance/seedance-2.0, fal-ai/bytedance-upscaler/upscale/video, xai/grok-imagine-video, xai/grok-imagine-video/video-extension, alibaba/happy-horse, alibaba/happy-horse/reference-to-video, alibaba/happy-horse/video-edit, gemini/omni-flash) |
+| `-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) and hd_mode (1080p quality). minimax/h3: MiniMax H3 next-generation 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: 2K. 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; hd_mode renders native 1080p (~2.25x cost; fast/mini tiers stay 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. 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, 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) |
 | `-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) |
-| `-r`, `--aspect_ratio` | No | The aspect ratio of the video to generate. For image-to-video (i2v) generation, this should match the aspect ratio of your input image(s). Ratios unsupported by the chosen model fall back to its default (5:4 and 4:5 are only supported by alibaba/happy-horse). OMIT this parameter for MiniMax H3's native adaptive framing (adaptive is not an enum value). (string, one of: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 5:4, 4:5) |
-| `-d`, `--duration` | No | The duration of the video to generate in seconds. (number, default: `5`) |
+| `-r`, `--aspect_ratio` | No | The aspect ratio of the video to generate. For image-to-video (i2v) generation, this should match the aspect ratio of your input image(s). Ratios unsupported by the chosen model fall back to its default (5:4 and 4:5 are only supported by alibaba/happy-horse; 3:2 and 2:3 by pixverse/c1 and grok-imagine-video). Use 'auto' (or omit this parameter) for FLUX 3. Omit it for MiniMax H3 native adaptive framing. (string, one of: auto, 16:9, 9:16, 1:1, 4:3, 3:4, 2:1, 3:2, 2:3, 21:9, 9:21, 5:4, 4:5) |
+| `-d`, `--duration` | No | The duration in seconds. (number, default: `5`) |
 | `-a`, `--audio_url` | No | Audio URL for audio integration in video generation. - Optional for Wan v2.5 model (custom audio: music or speech, WAV/MP3, 3-10s, up to 15MB) - Required for OmniHuman model (audio-driven animation) Leave empty if no audio is needed. (string, default: ``) |
-| `--video_url` | No | Source video URL for video extension. Required for Grok Imagine Video Extension (extend existing video). Supports both web URLs and AI Drive paths (starting with '/' or 'aidrive://') (string, default: ``) |
+| `--video_url` | No | Source video URL for video extension or video-to-video. On Grok Imagine Video and Gemini Veo 3.1 it switches to EXTENSION mode; on Kling O3 it switches to video-to-video (see video_mode). Supports both web URLs and AI Drive paths (starting with '/' or 'aidrive://') (string, default: ``) |
+| `--video_mode` | No | How video_url is used. Kling O3: 'reference' (default — motion/camera guide) or 'edit' (restyle inside the source footage); no extend. Gemini Veo 3.1 / Grok Imagine Video: 'extend' only. Ignored without video_url. (string, one of: reference, edit, extend) |
+| `--keep_audio` | No | Kling O3 video-to-video only: keep the source video's audio track in the output. (boolean) |
+| `--input_mode` | No | FLUX 3 Video only: explicitly use video_url as a reference video or a start video. Omit for all other models and for text/image input. (string, one of: reference_video, start_video) |
 | `--video_urls` | No | Reference video URLs for reference-to-video models. For Wan v2.7 and Seedance 2.0 reference-to-video: provide 1-3 reference videos and refer to them in the prompt as @Video1, @Video2, @Video3. Seedance 2.0 also needs reference_mode plus at least one image_url; combined video duration 2-15s. For MiniMax H3: up to 3 motion reference videos (each 2-15s, ≤15s combined), referred to in the prompt as 'Video 1' etc. (array, default: `[]`) |
 | `--audio_urls` | No | Reference audio URLs for reference-to-video models. For Seedance 2.0: provide up to 3 audio clips (MP3/WAV) and refer to them in the prompt as @Audio1, @Audio2, @Audio3 (e.g. to drive lip-sync or match a voice). Combined duration must not exceed 15s. Requires reference_mode plus at least one image_url (image_urls is what activates the seedance-2.0/ref route). For MiniMax H3: up to 3 audio references (each 2-15s, ≤15s combined; 'Audio 1' prompt style), must be paired with at least one reference image or video. Distinct from audio_url, the single-clip Wan v2.5 / OmniHuman field. (array, default: `[]`) |
 | `--repo_id` | No | Optional. Second Brain repo id (provided in the agent's system prompt). Required only when image_urls / audio_url / video_url / video_urls contain relative paths from a Second Brain project (e.g. 'assets/clip.mp4'). Absolute http(s) URLs and data: URLs do not need this parameter. (string) |
 | `--audio_enable` | No | Set true when the user wants audio, voiceover, or narration. kling/v3 outputs a SILENT video unless true (audio costs more per second). Omit to keep each model's default (kling: off; seedance/veo: on). (boolean) |
-| `--tier` | No | Model tier (options are model-specific — check get_model_info tier_options). Seedance 2.0: standard \| fast (quicker/cheaper, 720p cap) \| mini (cheapest, ~half the standard price, 720p cap). Veo 3 / Veo 3.1 family: standard \| fast (quicker, lower cost). Kling V3/O3/Motion Control: pro \| standard. Models without tiers ignore it. (string, one of: standard, fast, mini, pro) |
+| `--tier` | No | Model tier (options are model-specific — check get_model_info tier_options). Seedance 2.0: standard \| fast (quicker/cheaper, 720p cap) \| mini (cheapest, ~half the standard price, 720p cap). Veo 3 / Veo 3.1 family: standard \| fast (quicker, lower cost). Kling V3: pro \| standard \| turbo (fastest, no audio/frame control). Kling O3/Motion Control: pro \| standard. Vidu Q3: standard \| turbo (half price). Models without tiers ignore it. (string, one of: standard, fast, mini, pro, turbo) |
 | `--hd_mode` | No | Enable HD (1080p) mode for higher quality output. Applicable to Veo 3.1 (2x cost) and Seedance 2.0 standard/reference (~2.25x cost; fast tier stays 720p). Default: false. (boolean, default: `False`) |
-| `--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). Ignored on other models. Default: false. (boolean, default: `False`) |
+| `--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`) |
 
 ## Local File Support
 

package/skills/gsk-youtube/SKILL.md

@@ -1,7 +1,8 @@
 ---
 name: gsk-youtube
 version: 1.0.0
-description: 'YouTube operations. Actions: search, transcript, comments.'
+description: 'YouTube operations. Actions: search (find videos by keyword), transcript
+  (read a video''s spoken content by video id), comments.'
 metadata:
   category: general
   requires:
@@ -14,7 +15,7 @@ metadata:
 
 **PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
 
-YouTube operations. Actions: search, transcript, comments.
+YouTube operations. Actions: search (find videos by keyword), transcript (read a video's spoken content by video id), comments.
 
 ## Usage
 
@@ -28,8 +29,8 @@ gsk yt [options]
 
 | Flag | Required | Description |
 |------|----------|-------------|
-| `<action>` (positional) | Yes | Action to perform. 'search': Search for YouTube videos by keyword; 'transcript': Extract transcript and metadata from a YouTube video; 'comments': Scrape comments from a YouTube video (string, one of: search, transcript, comments) |
-| `--query` | No | [search] The query to search video (string) |
+| `<action>` (positional) | Yes | Action to perform. 'search': Search YouTube videos by a keyword query; 'transcript': Get a video's transcript and metadata by video id — the video-understanding tool (subtitle text, no visual frames); 'comments': Scrape comments from a YouTube video (string, one of: search, transcript, comments) |
+| `--query` | No | [search] Keyword query to find videos (string) |
 | `--video_id` | No | [transcript] The video id of the youtube video. (string) |
 | `--provide_download_link` | No | [transcript] Whether to provide a download link for the video transcript. (boolean) |
 | `--video_url` | No | [comments] YouTube video URL. Supports youtube.com/watch?v=, youtu.be/, and youtube.com/shorts/ formats. (string) |