@genspark/cli 1.0.7 → 1.0.8

package/skills/gsk-analyze-media/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: gsk-analyze-media
+version: 1.0.0
+description: Analyze various types of media content including images, audio, and video.
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk media-analyze --help
+---
+
+# gsk-analyze-media
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Analyze various types of media content including images, audio, and video.
+
+## Usage
+
+```bash
+gsk media-analyze [options]
+```
+
+**Aliases:** `analyze_media`, `media-analyze`
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `-i`, `--media_urls` | Yes | List of media file URLs or AI Drive paths to analyze (array) |
+| `--video_metadata` | No | Video-specific metadata for analysis (optional)Unless the user requires, it is not required to provide (object) |
+| `-r`, `--requirements` | No | Must in English, Detailed analysis requirements and goals. Please clearly describe: - What is the purpose of the analysis? - What information needs to be extracted from the media? - What information is most important to you? - How will these analysis results be used? - What are the clips that can be extracted from the video? What are their corresponding time ranges (in milliseconds) and descriptions? - ... (You can add more requirements here) - Specific requirements for different media types (images, audio, video)  For example: 'I need to analyze these materials for emotional tone, main content, use cases for a marketing campaign, other requirements...'  Note: This parameter is ignored when analyze_type='video_style_replication'. (string) |
+| `--analyze_type` | No | Type of analysis to perform. Options: - '' (empty/default): Standard content analysis based on requirements - 'video_style_replication': Analyze video's cinematography style, expression techniques, and production methods to enable replicating its visual language in new content. When this type is used, a specialized prompt guides the analysis to extract filmmaking craft, aesthetic decisions, and technical approaches that define the video's unique character. The output is suitable for guiding AI video generation systems to replicate similar styles. (string, one of: , video_style_replication) |
+
+## Local File Support
+
+Parameters that accept URLs (`--media_urls`) also accept local file paths. The CLI automatically uploads local files before sending to the API.
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

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

@@ -0,0 +1,52 @@
+---
+name: gsk-audio-generation
+version: 1.0.0
+description: Generate audio content including TTS, sound effects, and music.
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk audio --help
+---
+
+# gsk-audio-generation
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Generate audio content including TTS, sound effects, and music.
+
+## Usage
+
+```bash
+gsk audio [options]
+```
+
+**Aliases:** `audio_generation`, `audio`
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<query>` (positional) | No | For text-to-speech generation: - For google/gemini-2.5-pro-preview-tts: Can use script_url field or query field. When using multi-speaker, include speaker prefixes like 'Speaker1: Hello there! Speaker2: Hi back!' - For elevenlabs/v3-tts: Supports both single and multi-speaker generation. For multi-speaker, include speaker prefixes like 'Speaker 1: Hello there! Speaker 2: Hi back!' - For other TTS models (Minimax): Use plain text without character names (e.g., use 'That's not what she meant, fatass.' instead of 'STAN: That's not what she meant, fatass.' as the character name will be pronounced). For sound effects, provide a detailed description of the audio to generate (e.g., 'A keyboard typing sound, rain, wind, etc.').For background music, provide a detailed description of the music to generate.must be in English if choosing CassetteAI/music-generator music generation.(e.g., 'Smooth chill hip-hop beat with mellow piano melodies, deep bass, and soft drums, perfect for a night drive. Key: D Minor, Tempo: 90 BPM.'). (string) |
+| `-m`, `--model` | Yes | The model to use for audio generation. google/gemini-2.5-pro-preview-tts: Best, high-quality, realistic tone text-to-speech model. Supports one or multiple speakers in one generation with speaker prefixes (e.g., 'Speaker1: text, Speaker2: text').elevenlabs/v3-tts: Advanced multilingual text-to-speech model with multi-speaker dialogue support. Supports emotional tags like [excited], [whispers], [laughs]. Best for expressive content and conversations.fal-ai/elevenlabs/tts/multilingual-v2: High-quality multilingual text-to-speech model. For English, this is a preferred model.fal-ai/minimax/speech-2.8-hd: High-quality multilingual text-to-speech model. For Chinese, 'Chinese,Yue', Japanese, Korean, this is a preferred model. Note: Only one speaker can be used per generation. For multiple characters, please generate them one by one in sequence. elevenlabs/sound-effects: Sound effect generation model. Minimum duration is 0.1 seconds, maximum is 22 seconds.elevenlabs/music: ElevenLabs music generation model. Supports both instrumental music AND songs with vocals/singing. NOTE: Does NOT support custom lyrics - lyrics are auto-generated. Minimum duration is 10 seconds, maximum is 5 minutes (300 seconds). Professional music production quality.elevenlabs/voice-clone: ElevenLabs voice cloning model. Clone a voice from audio samples. Returns voice ID for use in TTS generation.elevenlabs/voice-changer: ElevenLabs voice changer model. Transform audio from one voice to another. Requires source audio and target voice ID.CassetteAI/music-generator: Background music generation model. minimum duration is 10 seconds, maximum is up to 180 seconds.mureka/song-generator: Professional song generation with lyrics. Supports style prompts, reference tracks, vocal and melody inputs. Generate full songs with vocals. Maximum duration is 180 seconds.mureka/instrumental-generator: Instrumental music generation. Create background music and instrumental tracks without vocals. Supports style prompts and reference tracks. Maximum duration is 180 seconds.fal-ai/lyria2: using Google's Lyria 2 text-to-music model. The model is good at generating music for sound effects and lyrics-free music.maximum duration is 30 seconds.fal-ai/minimax-music/v2.5: Song generation with lyrics using MiniMax Music 2.5. High-fidelity audio with humanized vocals. Supports markers (Verse), (Chorus), (Bridge), (Outro), (Instrumental intro). Requires both style prompt and lyrics. (string, one of: google/gemini-2.5-pro-preview-tts, fal-ai/elevenlabs/tts/multilingual-v2, elevenlabs/v3-tts, elevenlabs/sound-effects, elevenlabs/music, elevenlabs/voice-clone, elevenlabs/voice-changer, CassetteAI/music-generator, fal-ai/minimax/speech-2.8-hd, fal-ai/minimax-music/v2.5, mureka/song-generator, mureka/instrumental-generator, fal-ai/lyria2) |
+| `-r`, `--requirements` | No | Required parameters for TTS generation. If you know the speaker name, you can also pass it in the requirementsDetailed description of how the TTS should be generated, including voice characteristics, emotion, pacing, accent, tone, etc. For example: 'A calm, professional female voice with British accent reading at moderate pace'.or 'Speaker1: Algenib, Speaker2: Kore' if you want to use specific speakersThis will be used by the agent to determine the appropriate voice and style parameters (string) |
+| `--previous_audio_params` | No | Required parameters for TTS generation. The `generated_audios[].params` object from previous generation,get from previous tool call, when you need to fix the voice of a specific character, it will be useful. (object) |
+| `-d`, `--duration` | No | The desired duration of the generated audio in seconds. Only applicable for sound effects generation.Default is 0, which means the model will determine the appropriate duration.For background music generation, set default to 30 seconds. (number, default: `0`) |
+| `--custom_voice_id` | No | Custom voice ID for: 1. Minimax TTS - voice ID from voice cloning, 2. ElevenLabs Voice Changer - target voice ID to change to (string) |
+| `--voice_files` | No | URLs or paths to voice sample files for voice cloning. Multiple samples improve clone quality. Required for ElevenLabs voice cloning model. (array) |
+| `--source_audio_file` | No | URL or path to the source audio file for voice transformation. Required for ElevenLabs voice changer model. This is the audio that will be transformed to the target voice. (string) |
+| `--image_urls` | No | The URLs of the images to use as a reference for the audio generation.(default is [], if the task is based on one or more reference images, it is required) (array) |
+| `-l`, `--lyrics` | No | Lyrics for song generation. Required for Mureka song generator and MiniMax Music 2.5. The lyrics will be used to generate vocals for the song. (string) |
+
+## Local File Support
+
+Parameters that accept URLs (`--image_urls`) also accept local file paths. The CLI automatically uploads local files before sending to the API.
+
+## Output File
+
+Use `-o <path>` / `--output-file <path>` to download the generated result directly to a local file.
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-audio-transcribe/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: gsk-audio-transcribe
+version: 1.0.0
+description: Transcribe audio files to text with word-level timestamps.
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk transcribe --help
+---
+
+# gsk-audio-transcribe
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Transcribe audio files to text with word-level timestamps.
+
+## Usage
+
+```bash
+gsk transcribe [options]
+```
+
+**Aliases:** `audio_transcribe`, `transcribe`
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `-i`, `--audio_urls` | Yes | List of audio file URLs to transcribe. Supports both web URLs and AI Drive paths. (array) |
+| `--prompt` | No | Optional custom prompt to improve transcription quality. Can include context, proper nouns, or technical terms that should be recognized correctly. For example: 'This is a discussion about artificial intelligence and machine learning.'If you already know the corresponding transcript text, provide this text as the prompt to make it easier for the model to understand. (string) |
+| `-m`, `--model` | No | Transcription model to use. Options: 'whisper-1' (default, supports timestamps), 'gemini-3-flash-preview' (no timestamp support), 'elevenlabs_scribe_v2' (supports word timestamps & entity detection). Note: gemini-3-flash-preview does not support word-level or segment-level timestamps. (string, one of: whisper-1, gemini-3-flash-preview, elevenlabs_scribe_v2, default: `whisper-1`) |
+| `--entity_detection` | No | Entity types to detect (elevenlabs_scribe_v2 only). Options: 'pii' for personally identifiable information, 'name', 'dob', 'credit_card', 'ssn' for specific entities, 'all' for all entity types. Example: ['pii'] or ['name', 'credit_card'] (array) |
+
+## Local File Support
+
+Parameters that accept URLs (`--audio_urls`) also accept local file paths. The CLI automatically uploads local files before sending to the API.
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-calendar-create/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: gsk-calendar-create
+version: 1.0.0
+description: Create a new calendar event in Google Calendar or Outlook.
+metadata:
+  category: calendar
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk calendar create --help
+---
+
+# gsk-calendar-create
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Create a new calendar event in Google Calendar or Outlook.
+
+## Usage
+
+```bash
+gsk calendar create [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `--summary` | Yes | Event title. (string) |
+| `--start_time` | Yes | Start time in ISO 8601 format (e.g. '2026-03-07T10:00:00-08:00'). (string) |
+| `--end_time` | Yes | End time in ISO 8601 format (e.g. '2026-03-07T11:00:00-08:00'). (string) |
+| `--description` | No | Event description. (string) |
+| `--location` | No | Event location. (string) |
+| `--attendees` | No | List of attendee email addresses. (array) |
+| `--time_zone` | No | Time zone name (e.g. 'America/Los_Angeles', 'UTC'). Default: UTC. (string) |
+| `-a`, `--from_account` | No | Calendar account to use if multiple accounts are connected. (string) |
+
+> **CAUTION:** This command performs a write/send operation. Double-check parameters before executing.
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-calendar-list/SKILL.md

@@ -0,0 +1,36 @@
+---
+name: gsk-calendar-list
+version: 1.0.0
+description: List upcoming calendar events from Google Calendar or Outlook.
+metadata:
+  category: calendar
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk calendar list --help
+---
+
+# gsk-calendar-list
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+List upcoming calendar events from Google Calendar or Outlook.
+
+## Usage
+
+```bash
+gsk calendar list [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `--filter_query` | No | Filter events by text (e.g. event title keywords). (string) |
+| `--time_min` | No | Start of time range in ISO 8601 format. Default: now. (string) |
+| `--time_max` | No | End of time range in ISO 8601 format. Default: 7 days from now. (string) |
+| `-a`, `--from_account` | No | Calendar account to use if multiple accounts are connected. (string) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-crawler/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: gsk-crawler
+version: 1.0.0
+description: Crawl and extract content from web pages. Supports HTML, PDF, and documents.
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk crawl --help
+---
+
+# gsk-crawler
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Crawl and extract content from web pages. Supports HTML, PDF, and documents.
+
+## Usage
+
+```bash
+gsk crawl [options]
+```
+
+**Aliases:** `crawler`, `crawl`
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<url>` (positional) | Yes | http/https url (string) |
+
+## Local File Support
+
+Parameters that accept URLs (`<url>`) also accept local file paths. The CLI automatically uploads local files before sending to the API.
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

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

@@ -0,0 +1,42 @@
+---
+name: gsk-create-task
+version: 1.0.0
+description: Create and execute tasks using specialized AI agents. Supports super_agent,
+  podcasts, docs, slides, deep_research, website, video_generation, audio_generation,
+  meeting_notes, cross_check.
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk task --help
+---
+
+# gsk-create-task
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Create and execute tasks using specialized AI agents. Supports super_agent, podcasts, docs, slides, deep_research, website, video_generation, audio_generation, meeting_notes, cross_check.
+
+## Usage
+
+```bash
+gsk task [options]
+```
+
+**Aliases:** `create_task`, `task`
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<task_type>` (positional) | Yes | The type of task to create: - super_agent: Create general super agent - podcasts: Create audio podcasts with AI characters - docs: Create and edit HTML/Markdown documents. Create a professional document with Word-like formatting as a single-file HTML. Perfect for reports, articles, academic papers, and formal documents. **Guidelines** 1. This tool can be directly called when user explicitly wants to create: - A document or report - An article or academic paper - A formal document with professional formatting - A document for print or PDF export  2. In situations other than those mentioned above, you need to ask the user first and only call this tool after getting permission when user wants to create: - A better formatted text, but hasn't explicitly mentioned creating a document - Content that needs professional document formatting  **Limitations** - Document styling resembles Microsoft Word format, not web page design - Usually takes time to generate, so please strictly follow the guidelines above - slides: Create presentation slides. Convert collected materials into a set of slides written in HTML format and display them. Limitation: a) It usually takes minutes. Ask the user whether they want to wait for a longer time before starting if they haven't explicitly indicated they want to generate a set of slides; - deep_research: Create deep research agent for task on a 'deep research' topic (e.g. 'deep research on Tesla', 'analyze Tesla in depth'). Also can handle user's 'continue deep research' request - website: Create a professional agent for building websites and web pages - video_generation: Large-scale batch video generation with complex inter-task dependencies. Best for workflows requiring coordinated, multi-step video pipelines where tasks depend on each other's outputs. Supports text-to-video, image-to-video (query should contain the image url), and merging multiple video clips. Can reuse agent. NOT recommended for small-scale, simple, or independent video tasks — for those, use <tool>video_generation</tool> directly instead. If there is a resource generation list, you can directly pass the resource list URL in the query, http(s):// or aidrive:// - audio_generation: Large-scale batch TTS (text-to-speech) generation with complex inter-task dependencies. Best for workflows requiring coordinated, multi-step TTS pipelines where tasks depend on each other's outputs. Supports text-to-speech, voiceovers, multi-speaker dialogues, and merging multiple audio clips. Can reuse agent. NOT recommended for small-scale, simple, or independent TTS tasks — for those, use <tool>audio_generation</tool> directly instead. If there is a resource generation list, you can directly pass the resource list URL in the query, http(s):// or aidrive:// - cross_check: Fact-check and verify claims or statements. Use when the user wants to verify whether a statement is true, check facts, or cross-reference claims against multiple sources. The agent systematically searches for evidence, evaluates source credibility, and provides a detailed verification report with supporting references. - sheets: Create spreadsheet. This tool can convert collected materials into a spreadsheet, use only when user is explicitly requesting you to create a spreadsheet or excel table. (string, one of: super_agent, podcasts, docs, slides, deep_research, website, video_generation, audio_generation, meeting_notes, cross_check, sheets) |
+| `--task_name` | Yes | Name for the task/project (string) |
+| `--query` | Yes | Query for the task. The ending should clearly state what needs to be done, such as generating a doc/slides etc. (string) |
+| `--instructions` | Yes | Detailed instructions for the task. This will be set as system prompt to the specialized agent. (string) |
+
+> **CAUTION:** This command performs a write/send operation. Double-check parameters before executing.
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-email-list/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: gsk-email-list
+version: 1.0.0
+description: List emails from a folder (inbox, sent, drafts, etc.).
+metadata:
+  category: email
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk email list --help
+---
+
+# gsk-email-list
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+List emails from a folder (inbox, sent, drafts, etc.).
+
+## Usage
+
+```bash
+gsk email list [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<folder>` (positional) | No | Folder to list (inbox, sent, drafts, spam, trash). Default: inbox. (string) |
+| `-n`, `--limit` | No | Maximum number of emails to return. Default: 20. (integer) |
+| `--after_date` | No | Return emails after this date (YYYY-MM-DD). (string) |
+| `--before_date` | No | Return emails before this date (YYYY-MM-DD). (string) |
+| `--unread_only` | No | Set to true to return only unread emails. Default: false. (boolean) |
+| `-a`, `--from_account` | No | Email account to use if multiple accounts are connected. (string) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-email-read/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: gsk-email-read
+version: 1.0.0
+description: Read a specific email by its ID.
+metadata:
+  category: email
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk email read --help
+---
+
+# gsk-email-read
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Read a specific email by its ID.
+
+## Usage
+
+```bash
+gsk email read [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<id>` (positional) | Yes | The email ID to read. (string) |
+| `-a`, `--from_account` | No | Email account to use if multiple accounts are connected. (string) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-email-search/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: gsk-email-search
+version: 1.0.0
+description: Search emails using a query string. Works with Gmail (GQL) and Outlook
+  (KQL) accounts.
+metadata:
+  category: email
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk email search --help
+---
+
+# gsk-email-search
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Search emails using a query string. Works with Gmail (GQL) and Outlook (KQL) accounts.
+
+## Usage
+
+```bash
+gsk email search [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<query>` (positional) | Yes | Search query. Gmail: GQL (e.g. 'from:boss subject:report'). Outlook: KQL. (string) |
+| `--folder` | No | Restrict search to folder (inbox, sent, drafts, spam, trash). (string) |
+| `-n`, `--limit` | No | Maximum number of results to return. Default: 20. (integer) |
+| `--after_date` | No | Return emails after this date (YYYY-MM-DD). (string) |
+| `--before_date` | No | Return emails before this date (YYYY-MM-DD). (string) |
+| `-a`, `--from_account` | No | Email account to use if multiple accounts are connected. (string) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-email-send/SKILL.md

@@ -0,0 +1,41 @@
+---
+name: gsk-email-send
+version: 1.0.0
+description: Send a new email message via Gmail or Outlook.
+metadata:
+  category: email
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk email send --help
+---
+
+# gsk-email-send
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Send a new email message via Gmail or Outlook.
+
+## Usage
+
+```bash
+gsk email send [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `--to` | Yes | Recipient email address(es), comma-separated. (string) |
+| `--subject` | Yes | Email subject line. (string) |
+| `--body` | Yes | Email body content. (string) |
+| `--cc` | No | CC recipient(s), comma-separated. (string) |
+| `--bcc` | No | BCC recipient(s), comma-separated. (string) |
+| `--content_type` | No | Content type: text/plain or text/html. Default: text/plain. (string) |
+| `-a`, `--from_account` | No | Sender email account to use if multiple accounts are connected. (string) |
+
+> **CAUTION:** This command performs a write/send operation. Double-check parameters before executing.
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-get-service-url/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: gsk-get-service-url
+version: 1.0.0
+description: Get the public HTTPS URL for a service running on the sandbox. Use this
+  to access web servers, APIs, or applications from outside.
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk service-url --help
+---
+
+# gsk-get-service-url
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Get the public HTTPS URL for a service running on the sandbox. Use this to access web servers, APIs, or applications from outside.
+
+## Usage
+
+```bash
+gsk service-url [options]
+```
+
+**Aliases:** `get_service_url`, `service-url`
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `--port` | Yes | The port number where the HTTP service is running (e.g., 3000, 8080, 5000) (integer) |
+| `--sandbox_id` | No | Optional sandbox ID. If not provided, it will be looked up from the project_id in GSK CLI config. (string) |
+| `--service_name` | No | Optional descriptive name for the service (e.g., 'Express Server'). Used for logging. (string) |
+| `--health_path` | No | Optional health check endpoint path (e.g., '/health'). If provided, will be included in the response. (string) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

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

@@ -0,0 +1,48 @@
+---
+name: gsk-image-generation
+version: 1.0.0
+description: Generate images using AI models. Supports text-to-image and image editing.
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk img --help
+---
+
+# gsk-image-generation
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Generate images using AI models. Supports text-to-image and image editing.
+
+## Usage
+
+```bash
+gsk img [options]
+```
+
+**Aliases:** `image_generation`, `img`
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `-m`, `--model` | No | Default model: use nano-banana-2 fal-ai/gpt-image-1.5: GPT Image 1.5 - 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. imagen4: A latest model for generating high quality image, upgrade from Imagen 3. currently in preview mode.recraft-v3: A model for generating realistic image.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/flux-2: Flux 2 model for text-to-image and image editing with enhanced realism, crisp text generation, and native editing capabilities. Fast processing with flexible aspect ratios. Supports up to 3 images for edit mode.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.ideogram/V_3: [FACE CONSISTENCY] Character reference specialist with superior facial feature preservation, character consistency across styles/poses/scenes, natural language understanding, excellent text rendering.qwen-image: [CHINESE POSTER SPECIALIST] Outstanding Chinese poster creation, superior Chinese text rendering, cultural context mastery, exceptional Chinese understanding, cost efficient.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.  (string, one of: fal-ai/gpt-image-1.5, imagen4, recraft-v3, fal-ai/bytedance/seedream/v5/lite, fal-ai/flux-2, fal-ai/flux-2-pro, fal-ai/z-image/turbo, ideogram/V_3, qwen-image, bbox-segment, fal-bria-rmbg, fal-ai/recraft-clarity-upscale, fal-ai/image-editing/text-removal, flux-pro/outpaint, nano-banana-pro, nano-banana-2) |
+| `<query>` (positional) | Yes | 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'). (string) |
+| `--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) |
+| `-i`, `--image_urls` | No | The URLs of the images to use as a reference for the image generation or editing. (default is [], if the task is based on one or more reference images, it is required) (array) |
+| `-r`, `--aspect_ratio` | No | The aspect ratio of the image to generate. (string, one of: 1:1, 4:3, 16:9, 9:16, 3:4, 2:3, 3:2, auto) |
+| `-s`, `--image_size` | No | Image size resolution. Default is auto. (string, one of: auto, 0.5k, 1k, 2k, 3k, 4k) |
+
+## Local File Support
+
+Parameters that accept URLs (`--image_urls`) also accept local file paths. The CLI automatically uploads local files before sending to the API.
+
+## Output File
+
+Use `-o <path>` / `--output-file <path>` to download the generated result directly to a local file.
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-image-search/SKILL.md

@@ -0,0 +1,36 @@
+---
+name: gsk-image-search
+version: 1.0.0
+description: Search for images on the web. Returns image URLs, titles, and source
+  information.
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk img-search --help
+---
+
+# gsk-image-search
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Search for images on the web. Returns image URLs, titles, and source information.
+
+## Usage
+
+```bash
+gsk img-search [options]
+```
+
+**Aliases:** `image_search`, `img-search`
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<query>` (positional) | Yes | The specific image search terms (e.g., 'Eiffel Tower at sunset', 'Bengal tiger in the wild'). (string) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-meeting-get/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: gsk-meeting-get
+version: 1.0.0
+description: Get details of a specific meeting note.
+metadata:
+  category: meeting
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk meeting get --help
+---
+
+# gsk-meeting-get
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Get details of a specific meeting note.
+
+## Usage
+
+```bash
+gsk meeting get [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<task_id>` (positional) | Yes | The ID of the meeting note to retrieve. (string) |
+| `-d`, `--detail_level` | No | Level of detail to return. 'summary' = title + status + summary + user notes (default, saves tokens). 'full' = summary + complete transcription text. 'segments' = summary + segments with speaker labels. (string, one of: summary, full, segments) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-meeting-list/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: gsk-meeting-list
+version: 1.0.0
+description: List meeting notes ordered by creation date.
+metadata:
+  category: meeting
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk meeting list --help
+---
+
+# gsk-meeting-list
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+List meeting notes ordered by creation date.
+
+## Usage
+
+```bash
+gsk meeting list [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `-n`, `--page_size` | No | Number of results per page. Default: 20. Max: 50. (integer) |
+| `--continuation_token` | No | Token for fetching the next page of results. Returned from a previous list call. (string) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags