@genspark/cli 1.0.11 → 1.0.13

package/skills/gsk-onedrive/SKILL.md

@@ -0,0 +1,44 @@
+---
+name: gsk-onedrive
+version: 1.0.0
+description: 'OneDrive file operations. Actions: list, search, read.'
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk onedrive --help
+---
+
+# gsk-onedrive
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+OneDrive file operations. Actions: list, search, read.
+
+## Usage
+
+```bash
+gsk onedrive [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<action>` (positional) | Yes | Action to perform. 'list': List files in a folder; 'search': Search files; 'read': Read and extract content from a file (string, one of: list, search, read) |
+| `--onedrive_url` | No | [list] A OneDrive URL to list files from. Can be a sharing link, folder link, or any OneDrive URL. (string) |
+| `--folder_id` | No | [list] The folder item ID to list contents of. Get folder IDs from previous onedrive_list_files or onedrive_search results. (string) |
+| `--folder_path` | No | [list] The folder path relative to OneDrive root. Example: 'Documents/Projects' to list files in that subfolder. (string) |
+| `--limit` | No | [list] Maximum number of items to return (1-200). Default: 50 (integer) |
+| `--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) |
+| `--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. (string) |
+| `--question` | No | [read] The question to answer about the file content. (string) |
+
+## Local File Support
+
+Parameters that accept URLs (`--onedrive_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-outlook-calendar/SKILL.md

@@ -0,0 +1,53 @@
+---
+name: gsk-outlook-calendar
+version: 1.0.0
+description: 'Outlook Calendar operations. Actions: list, create, delete.'
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk outlook_calendar --help
+---
+
+# gsk-outlook-calendar
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Outlook Calendar operations. Actions: list, create, delete.
+
+## Usage
+
+```bash
+gsk outlook_calendar [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<action>` (positional) | Yes | Action to perform. 'list': List upcoming calendar events; 'create': Create a new calendar event; 'delete': Delete a calendar event (string, one of: list, create, delete) |
+| `--filter_query` | No | [list] Text to filter calendar events by subject. Empty for listing all events in the time range. (string) |
+| `--time_min` | No | [list] Optional. Start time for the calendar view (ISO 8601 timestamp). Defaults to 30 days ago. (string) |
+| `--time_max` | No | [list] Optional. End time for the calendar view (ISO 8601 timestamp). Defaults to 60 days from now. (string) |
+| `--from_account` | No | [list] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [delete] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. (string) |
+| `--summary` | No | [create] The title of the event (string) |
+| `--location` | No | [create] The location of the event (string) |
+| `--description` | No | [create] Description or details of the event. Supports restricted HTML formatting (safe subset rendered via Vue v-html): <a>, <b>, <strong>, <i>, <em>, <u>, <br>, <p>, <ul>, <ol>, <li>, <span>, <img>. Use for links, bold, italics, lists, line breaks, images. (string) |
+| `--time_zone` | No | [create] Time zone for the event (e.g., 'GMT-07:00') (string) |
+| `--time_zone_name` | No | [create] Time zone name for the event (e.g., 'America/Los_Angeles') (string) |
+| `--start_time` | No | [create] Start time of the event in ISO 8601 format, must include correct timezone offset (e.g., 'yyyy-mm-ddThh:mm:ss+hh:mm') (string) |
+| `--end_time` | No | [create] End time of the event in ISO 8601 format, must include correct timezone offset (e.g., 'yyyy-mm-ddThh:mm:ss-hh:mm') (string) |
+| `--attendees` | No | [create] List of email addresses of attendees (array) |
+| `--calendar_id` | No | [create] The calendar identifier. Use 'primary' for the user's primary calendar or provide a specific calendar email address (string) |
+| `--event_id` | No | [create] The event identifier. If the request is to modify an existing event, provide the event_id of the event to be modified. If the request is to create a new event, leave this field empty. \| [delete] The Outlook Calendar event ID to delete (string) |
+| `--recurrence` | No | [create] Recurrence pattern for the event (object) |
+| `--send_notifications` | No | [create] Whether to send email notifications to attendees (boolean) |
+| `--importance` | No | [create] Event importance (low, normal, high) (string) |
+| `--sensitivity` | No | [create] Event sensitivity (normal, personal, private, confidential) (string) |
+| `--show_as` | No | [create] Show as status (free, tentative, busy, oof, workingElsewhere, unknown) (string) |
+| `--delete_series` | No | [delete] If true and the event is recurring, delete the entire series. If false, only delete the single instance. Default is false. (boolean, default: `False`) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-outlook-contacts/SKILL.md

@@ -0,0 +1,36 @@
+---
+name: gsk-outlook-contacts
+version: 1.0.0
+description: 'Outlook Contacts operations. Actions: search.'
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk outlook_contacts --help
+---
+
+# gsk-outlook-contacts
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Outlook Contacts operations. Actions: search.
+
+## Usage
+
+```bash
+gsk outlook_contacts [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<action>` (positional) | Yes | Action to perform. 'search': Search Outlook contacts (string, one of: search) |
+| `--query` | No | [search] Search query to find contacts. Searches across names, email addresses, phone numbers, and notes. (string) |
+| `--limit` | No | [search] Maximum number of results to return (1-100). Default: 20 (integer) |
+| `--account_id` | No | [search] Optional. The Outlook account ID to search (e.g., 'outlook-user@example.com'). If not provided, uses the default Outlook account. (string) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

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

@@ -0,0 +1,82 @@
+---
+name: gsk-outlook-email
+version: 1.0.0
+description: 'Outlook Email operations. Actions: search, read, send, reply, reply_draft,
+  forward, delete, archive, move, mark_as_read, add_category, remove_category, get_attachment,
+  group_list, group_search, group_read, group_reply.'
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk outlook --help
+---
+
+# gsk-outlook-email
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Outlook Email operations. Actions: search, read, send, reply, reply_draft, forward, delete, archive, move, mark_as_read, add_category, remove_category, get_attachment, group_list, group_search, group_read, group_reply.
+
+## Usage
+
+```bash
+gsk outlook [options]
+```
+
+**Aliases:** `outlook`
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<action>` (positional) | Yes | Action to perform. 'search': Search emails by query; 'read': Read a specific email by ID; 'send': Compose and send an email; 'reply': Reply to an existing email; 'reply_draft': Create a reply draft without sending; 'forward': Forward an email to new recipients; 'delete': Delete an email; 'archive': Archive an email; 'move': Move an email to a different folder; 'mark_as_read': Mark an email as read or unread; 'add_category': Add a category to an email; 'remove_category': Remove a category from an email; 'get_attachment': Download an email attachment; 'group_list': List Microsoft 365 groups; 'group_search': Search group emails; 'group_read': Read a group email; 'group_reply': Reply to a group email (string, one of: search, read, send, reply, reply_draft, forward, delete, archive, move, mark_as_read, add_category, remove_category, get_attachment, group_list, group_search, group_read, group_reply) |
+| `--queryString` | No | [search] The search query using KQL (Keyword Query Language). Examples:\n- Simple: 'project meeting'\n- From Sender: 'from:boss@example.com'\n- With Subject: 'subject:"Weekly Report"'\n- Unread Emails: 'isRead=false'\n- Has Attachments: 'hasAttachments=true'\n- Cc Recipient: 'cc:user@example.com'\n- Important: 'importance:high'\n- Complex: 'from:admin@co.com AND (subject:urgent OR body:critical)'\nNote: Use after_date/before_date params for date filtering (recommended), or use KQL syntax like 'received:2024-06-01..2024-06-30' in queryString. (string) |
+| `--after_date` | No | [search] Filter emails received on or after this date (inclusive). Format: YYYY-MM-DD (e.g., '2024-01-01'). Works for both enterprise and personal accounts. (string) |
+| `--before_date` | No | [search] Filter emails received before this date (exclusive). Format: YYYY-MM-DD (e.g., '2024-01-31'). Works for both enterprise and personal accounts. (string) |
+| `--size` | No | [search] The number of results to return per page (default: 25, max: 1000). \| [group_search] The maximum number of results to return per group per page (default: 25). (integer, default: `25`) |
+| `--from_offset` | No | [search] The starting offset for pagination (used to get the next page of results). (integer, default: `0`) |
+| `--auto_paginate` | No | [search] If true, automatically fetches multiple pages until reaching max_total_results (default: 500). Returns ALL emails matching the query. \| [group_search] If true, automatically fetches multiple pages from each group until reaching max_total_results (default: 500). Returns ALL emails matching the query. (boolean) |
+| `--max_total_results` | No | [search] Maximum total results to fetch when auto_paginate is true. Default: 500, Maximum: 500. \| [group_search] Maximum total results to fetch across all groups when auto_paginate is true. Default: 500, Maximum: 500. (integer) |
+| `--folder` | No | [search] The mail folder to search in. Options:\n- 'inbox': Inbox folder (default)\n- 'junkemail' or 'spam': Junk/Spam folder\n- 'deleteditems' or 'trash': Deleted Items folder\n- 'drafts': Drafts folder\n- 'sentitems' or 'sent': Sent Items folder\n- 'archive': Archive folder\n- 'all': Search across all folders (uses Search API) (string) |
+| `--search_mode` | No | [search] Search mode to use:\n- 'auto' (default): Automatically choose best method\n- 'kql': Use Microsoft Search API with full KQL syntax (enterprise only, supports 'isread:false from:john subject:meeting')\n- 'filter': Use $filter for property filtering (supports 'isRead eq false', works with folder parameter) (string, one of: auto, kql, filter) |
+| `--from_account` | No | [search] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [read] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [send] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [reply] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [reply_draft] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [forward] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [delete] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [archive] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [move] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [mark_as_read] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [add_category] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [remove_category] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [get_attachment] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [group_list] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [group_search] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [group_read] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. \| [group_reply] Optional: Email address of the Outlook account to use. Use this when the user has multiple Outlook accounts connected. If not specified, uses the default Outlook account. (string) |
+| `--id` | No | [read] The ID of the email to retrieve and read (string) |
+| `--title` | No | [read] The title of the email to retrieve and read \| [group_read] The title of the email thread to retrieve. (string) |
+| `--question` | No | [read] Question to answer guiding how to process the email content \| [group_read] Question to answer guiding how to process the email content (string) |
+| `--download_attachments` | No | [read] Whether need to download attachments from the email to analysis (boolean) |
+| `--aidrive_path` | No | [read] Path in AIDrive where attachments should be saved. Default is /outlook_attachments/ \| [get_attachment] The path in AIDrive to save the attachment. Default: /outlook_attachments/ (string) |
+| `--to` | No | [send] A list of email addresses for primary recipients. At least one recipient is required. \| [reply] Optional: A list of email addresses for primary recipients. If not provided, defaults to the original sender. By default (reply_all=true), all original recipients are included in CC. \| [reply_draft] Optional: A list of email addresses for primary recipients. If not provided, defaults to the original sender. By default (reply_all), all original recipients are included in CC. \| [forward] A list of email addresses for primary recipients to forward the email to. \| [group_reply] Optional list of recipient email addresses to add as new participants. These recipients will be notified about the reply. (array) |
+| `--subject` | No | [send] The email subject line. (string) |
+| `--body` | No | [send] The email body content. **IMPORTANT**: The format MUST match the content_type parameter: - If content_type='text': Use plain text - If content_type='html': Use HTML format with tags like <h1>, <p>, <ul>, etc. **Note**: Email clients DO NOT support Markdown. Convert Markdown to HTML if needed. \| [reply] The reply message body. **IMPORTANT**: The format MUST match the content_type parameter: - If content_type='text': Use plain text - If content_type='html': Use HTML format with tags like <h1>, <p>, <ul>, etc. **Note**: Email clients DO NOT support Markdown. Convert Markdown to HTML if needed. \| [reply_draft] The reply content in HTML format. Use HTML tags for formatting (e.g., <br>, <b>, <i>). \| [forward] Optional: Additional message to include above the forwarded content. This is your personal note to recipients. (string) |
+| `--cc` | No | [send] Optional: A list of email addresses for CC recipients. \| [reply] Optional: A list of email addresses for CC recipients. If not provided and 'reply_all' is true (default), includes original CC and TO recipients. If 'reply_all' is false, no CC recipients are added. \| [reply_draft] Optional: A list of email addresses for CC recipients. If not provided and 'reply_type' is 'reply_all' (default), includes original CC and TO recipients. If 'reply_type' is 'reply', no CC recipients are added. \| [forward] Optional: A list of email addresses for CC recipients. (array) |
+| `--bcc` | No | [send] Optional: A list of email addresses for BCC recipients. \| [reply] Optional: A list of email addresses for BCC recipients. \| [reply_draft] Optional: A list of email addresses for BCC recipients. \| [forward] Optional: A list of email addresses for BCC recipients. (array) |
+| `--from_mailbox` | No | [send] Optional: The email address to send from (e.g., team@company.com). If not specified, the email will be sent from the current user's mailbox. Requires 'Mail.Send.Shared' permission for shared/group mailboxes. \| [reply] Optional: The email address to send the reply from (e.g., team@genspark.ai). If not specified, the reply will be sent from the current user's mailbox. Requires 'Mail.Send.Shared' permission for shared/group mailboxes. \| [reply_draft] Optional: The email address to create the draft from (e.g., team@genspark.ai). If not specified, the draft will be created in the current user's mailbox. Requires 'Mail.Send.Shared' permission for shared/group mailboxes. \| [forward] Optional: The email address to send from (e.g., team@genspark.ai). If not specified, forwards from the current user's mailbox. Requires 'Mail.Send.Shared' permission for shared/group mailboxes. (string) |
+| `--content_type` | No | [send] Content type of the body. Default: text/html (recommended) **CRITICAL**: body field format MUST match this parameter: - 'text/plain': body should be plain text - 'text/html': body MUST be valid HTML (not Markdown) Always convert Markdown to HTML before passing to this tool. \| [reply] Content type of the reply body. Default: text/html (recommended) **CRITICAL**: body field format MUST match this parameter: - 'text/plain': body should be plain text - 'text/html': body MUST be valid HTML (not Markdown) Always convert Markdown to HTML before passing to this tool. \| [forward] Content type of the body. Default: text/html \| [group_reply] The format of the content. Use 'text/plain' for plain text or 'text/html' for HTML content. Default is 'text/plain'. (string, one of: text/plain, text/html) |
+| `--skip_confirmation` | No | [send] If true, skip user confirmation and send immediately. Default is false (require confirmation before sending). \| [reply] If true, skip user confirmation and send immediately. Default is false (require confirmation before sending). \| [forward] If true, skip user confirmation and send immediately. Default is false (require confirmation before sending). \| [delete] If true, skip user confirmation and delete immediately. Default is false (require confirmation before deleting). \| [move] If true, skip user confirmation and move immediately. Default is false (require confirmation before moving). (boolean, default: `False`) |
+| `--auto_skip_confirmation` | No | [send] Set to true ONLY if the workflow step has [AUTO_SKIP_CONFIRMATION] marker. This indicates the node is configured to always skip confirmation. \| [reply] Set to true ONLY if the workflow step has [AUTO_SKIP_CONFIRMATION] marker. This indicates the node is configured to always skip confirmation. \| [forward] Set to true ONLY if the workflow step has [AUTO_SKIP_CONFIRMATION] marker. This indicates the node is configured to always skip confirmation. \| [delete] Set to true ONLY if the workflow step has [AUTO_SKIP_CONFIRMATION] marker. This indicates the node is configured to always skip confirmation. \| [move] Set to true ONLY if the workflow step has [AUTO_SKIP_CONFIRMATION] marker. This indicates the node is configured to always skip confirmation. (boolean, default: `False`) |
+| `--message_id` | No | [reply] The Outlook message ID to reply to. \| [forward] The Outlook message ID to forward. \| [delete] The Outlook message ID to delete \| [archive] The Outlook message ID to archive \| [move] The Outlook message ID to move \| [mark_as_read] (Deprecated, use message_ids) A single Outlook message ID to mark \| [add_category] The Outlook message ID to add category to \| [remove_category] The Outlook message ID to remove category from \| [get_attachment] The Outlook message ID containing the attachment (string) |
+| `--reply_all` | No | [reply] Optional: If true (default), reply to all original recipients (TO and CC). If false, reply only to the original sender. (boolean, default: `True`) |
+| `--include_original` | No | [reply] Optional: Whether to include the original email content as a quote in the reply. Defaults to true. \| [reply_draft] Optional: Whether to include the original email content as a quote in the draft. Defaults to true. (boolean, default: `True`) |
+| `--original_email_id` | No | [reply_draft] The ID of the original email to reply to. Required to create a proper reply draft with quoted content. (string) |
+| `--reply_type` | No | [reply_draft] Type of reply: 'reply' sends only to the original sender, 'reply_all' sends to all recipients of the original email. Default: 'reply_all'. Used to determine default recipients if 'to'/'cc' are not provided. (string, one of: reply, reply_all) |
+| `--include_attachments` | No | [forward] Whether to include original email attachments in the forward. Default: true (boolean, default: `True`) |
+| `--permanent` | No | [delete] Whether to permanently delete the message. Default: false (move to Deleted Items) (boolean) |
+| `--folder_name` | No | [move] The target folder name. Can be a well-known folder (inbox, drafts, sentitems, deleteditems, archive, junkemail, outbox) or a custom folder name. Custom folders will be created if they don't exist. (string) |
+| `--create_if_not_exists` | No | [move] Whether to create the folder if it doesn't exist. Default: true (boolean) |
+| `--message_ids` | No | [mark_as_read] The Outlook message ID(s) to mark. Can be a single ID string or an array of IDs. |
+| `--is_read` | No | [mark_as_read] Set to true to mark as read, false to mark as unread. Default: true (boolean) |
+| `--category_name` | No | [add_category] The category name to add. Common categories include: Red category, Orange category, Yellow category, Green category, Blue category, Purple category \| [remove_category] The category name to remove (string) |
+| `--filename` | No | [get_attachment] The filename of the attachment to retrieve. Use '*' to get all attachments. (string) |
+| `--save_to_aidrive` | No | [get_attachment] Whether to save the attachment to AIDrive. Default: true (boolean) |
+| `--name_filter` | No | [group_list] Optional filter to search for groups by name or email. If provided, only groups matching this filter will be returned. (string) |
+| `--group_id` | No | [group_search] The ID of a specific group to search within. If provided, group_name_filter is ignored. \| [group_read] The ID of the group. \| [group_reply] The ID of the M365 group. Available from trigger data as 'group_id' or 'emails[0].group_id'. (string) |
+| `--group_name_filter` | No | [group_search] A search term to find groups by name (e.g., 'Marketing'). Used if group_id is not provided. (string) |
+| `--query` | No | [group_search] The search query for email subjects. Use an empty string to get recent emails. (string) |
+| `--thread_id` | No | [group_read] The ID of the email thread to retrieve. This is often the same as the conversationId. \| [group_reply] The ID of the email thread to reply to. Available from trigger data as 'thread_id' or 'emails[0].thread_id'. (string) |
+| `--conversation_id` | No | [group_reply] The ID of the conversation. Available from trigger data as 'conversation_id' or 'emails[0].conversation_id'. (string) |
+| `--content` | No | [group_reply] The reply content. Can be plain text or HTML. This will be posted as a new message in the group conversation. (string) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-salesforce/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: gsk-salesforce
+version: 1.0.0
+description: 'Salesforce DX CLI (`sf`) operations in a pre-authenticated sandbox.
+  Actions: run (forwards any `sf` subcommand).'
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk sf --help
+---
+
+# gsk-salesforce
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Salesforce DX CLI (`sf`) operations in a pre-authenticated sandbox. Actions: run (forwards any `sf` subcommand).
+
+## Usage
+
+```bash
+gsk sf [options]
+```
+
+**Aliases:** `sf`
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<action>` (positional) | Yes | Action to perform. 'run': Run an `sf` subcommand inside the pre-authenticated sandbox. Provide the subcommand and flags as you would type them after `sf`. (string, one of: run) |
+| `--args` | No | [run] The `sf` subcommand and its arguments (everything after `sf`). Example: `data query --query "SELECT COUNT() FROM Account"`. (string) |
+| `--timeout` | No | [run] Optional timeout in seconds. Default 120. Raise for long-running ops like bulk import. (integer, default: `120`) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-shared/SKILL.md

@@ -42,7 +42,7 @@ gsk me
 | `--base-url <url>` | `GSK_BASE_URL` | `https://www.genspark.ai` | API base URL |
 | `--project-id <id>` | `GSK_PROJECT_ID` | — | Project ID for access control |
 | `--debug` | — | `false` | Enable debug output |
-| `--timeout <ms>` | — | `300000` | Request timeout (5 min default) |
+| `--timeout <ms>` | — | `1800000` | Request timeout (30 min default) |
 | `--output <format>` | — | `json` | Output format: `json` or `text` |
 | `--refresh` | — | — | Force refresh cached tool schemas |
 

package/skills/gsk-sharepoint/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: gsk-sharepoint
+version: 1.0.0
+description: 'SharePoint site and file operations. Actions: list, search, read_content,
+  read_file.'
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk sharepoint --help
+---
+
+# gsk-sharepoint
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+SharePoint site and file operations. Actions: list, search, read_content, read_file.
+
+## Usage
+
+```bash
+gsk sharepoint [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<action>` (positional) | Yes | Action to perform. 'list': List files in a site or library; 'search': Search across sites; 'read_content': Read content from a list item or page; 'read_file': Read and extract content from a file (string, one of: list, search, read_content, read_file) |
+| `--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' (string) |
+| `--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. \| [read_content] Site ID from SharePoint search results siteInfo. Required for listItem content type. (string) |
+| `--drive_id` | No | [list] The document library (drive) ID. Use this to list files in a specific document library. (string) |
+| `--folder_id` | No | [list] The folder item ID within a drive. Use this with drive_id to navigate into subfolders. Get folder IDs from previous sharepoint_list_files results. (string) |
+| `--limit` | No | [list] Maximum number of items to return (1-200). Default: 50 (integer) |
+| `--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., '项目 project' → '项目 OR project') • Examples: 'budget 2024', 'meeting OR conference', 'from:john project', 'hasAttachment:true report' (string) |
+| `--entity_types` | No | [search] Types of SharePoint content to search. Defaults to all types. (array, default: `['site', 'listItem', 'list', 'driveItem']`) |
+| `--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) |
+| `--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) |
+| `--question` | No | [read_content] The question to answer about the SharePoint content. \| [read_file] The question to answer about the file content. (string) |
+| `--list_id` | No | [read_content] List ID from SharePoint search results siteInfo. Required for listItem content type. (string) |
+| `--list_item_id` | No | [read_content] List item ID from SharePoint search results siteInfo. Required for listItem content type. (string) |
+| `--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) |
+
+## Local File Support
+
+Parameters that accept URLs (`--sharepoint_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-slack/SKILL.md

@@ -0,0 +1,46 @@
+---
+name: gsk-slack
+version: 1.0.0
+description: 'Slack messaging operations. Actions: send, search, lookup.'
+metadata:
+  category: general
+  requires:
+    bins:
+    - gsk
+  cliHelp: gsk slack --help
+---
+
+# gsk-slack
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` for auth, global flags, and security rules.
+
+Slack messaging operations. Actions: send, search, lookup.
+
+## Usage
+
+```bash
+gsk slack [options]
+```
+
+## Flags
+
+| Flag | Required | Description |
+|------|----------|-------------|
+| `<action>` (positional) | Yes | Action to perform. 'send': Send a message to a channel or user; 'search': Search messages by keyword; 'lookup': Look up users, channels, or groups (string, one of: send, search, lookup) |
+| `--message` | No | [send] The message content to send. Supports Slack markdown formatting. (string) |
+| `--recipient` | No | [send] Optional recipient: 'self' (default), channel ID (e.g., 'C01234567'), or user ID (e.g., 'U01234567'). If not specified, sends to yourself. (string) |
+| `--title` | No | [send] Optional title for the message. If provided, creates a rich formatted message with a header. (string) |
+| `--fields` | No | [send] Optional array of field objects with 'title' and 'value' keys to create a structured message layout. (array) |
+| `--thread_ts` | No | [send] Optional thread timestamp to reply in a thread. (string) |
+| `--query` | No | [search] The search query. You can use modifiers like 'in:#channel', 'from:@user', 'has:link', 'before:yyyy-mm-dd'. (string) |
+| `--count` | No | [search] The maximum number of messages to return. Default is 100. (integer) |
+| `--sort` | No | [search] Sort order of results. 'score' for relevance or 'timestamp' for time. Default is 'score'. (string) |
+| `--question` | No | [search] A specific question to answer based on the search results. (string) |
+| `--lookup_type` | No | [lookup] What to look up: 'users' for team members, 'channels' for channels/conversations, 'all' for both. (string, one of: users, channels, all) |
+| `--search_query` | No | [lookup] Optional search query to filter results by name. Case-insensitive partial match on name, display name, or real name. (string) |
+| `--include_bots` | No | [lookup] Whether to include bot users in results. Default: false (boolean) |
+| `--limit` | No | [lookup] Maximum number of results to return. Default: 50 (integer) |
+
+## See Also
+
+- [gsk-shared](../gsk-shared/SKILL.md) — Authentication and global flags

package/skills/gsk-vd/SKILL.md

@@ -0,0 +1,228 @@
+---
+name: gsk-vd
+version: 1.0.0
+description: "Virtual Developer — drive a VD project (issues, VMs, templates, shell exec, GitHub) from the CLI / local OpenCode. Gated behind gk_vd_project_agent and requires vd_project_id to be configured."
+metadata:
+  category: virtual-developer
+  requires:
+    bins:
+      - gsk
+  cliHelp: gsk vd --help
+---
+
+# gsk-vd — Virtual Developer CLI
+
+**PREREQUISITE:** Read `../gsk-shared/SKILL.md` first for auth, global flags, and output conventions.
+
+`gsk vd <subcmd>` drives an existing Virtual Developer project end-to-end from a shell. It exposes the exact same 21 tools the Web UI's `VdProjectAgentChat` agent uses (`backend/virtual_developer/project_agent/agent.py`) — issue CRUD + dispatch, VM lifecycle (start/stop/create/delete/save_snapshot), on-VM shell exec, OpenCode session inspection, GitHub App auth, and VM template management.
+
+Use this skill when you are **driving** an already-provisioned VD project as a CI-like agent (creating issues, dispatching work to VMs, inspecting PRs, running shell commands on the VM). **Do not** use it to create the VD project itself — that stays in the web UI.
+
+## Activation
+
+`gsk vd` is hidden by default. It becomes available only when **both** conditions hold:
+
+1. **Server-side:** the user has the `gk_vd_project_agent` gatekeeper flag (closed beta).
+2. **Client-side:** a `vd_project_id` is configured — either in the gsk config file or via `GSK_VD_PROJECT_ID` env.
+
+### Enable via config file
+
+Add to `~/.genspark-tool-cli/config.json`:
+
+```json
+{
+  "api_key": "gsk-...",
+  "base_url": "http://localhost:8582",
+  "vd_project_id": "vd-proj-abc123"
+}
+```
+
+### Enable via env var
+
+```bash
+export GSK_VD_PROJECT_ID=vd-proj-abc123
+```
+
+### Use an alternate config profile
+
+If you want to keep your default profile untouched (e.g. to drive a dev-backend VD project from the same machine that talks to prod for other gsk commands):
+
+```bash
+# Point gsk at a separate config file — also affects where tools-cache.json lives
+export GSK_CONFIG=/path/to/vd-profile/config.json
+# or per-command
+gsk --config /path/to/vd-profile/config.json vd list_vms
+```
+
+Once activated, every `gsk vd <subcmd>` command auto-injects the resolved `vd_project_id` as the default for its `--vd_project_id` flag. You can still override per-call with `--vd_project_id <other-id>`.
+
+## Conventions
+
+- All 21 commands accept `--vd_project_id <id>` but it is auto-defaulted from config; you rarely need to pass it.
+- All commands return an NDJSON response with `{version, status, message, data, session_state}`. Tool-specific payload is under `data`.
+- A tool that fails business-layer validation (wrong state, missing permission, not found) returns `status: "error"` with a human-readable `message`; this is **not** an infra error — inspect and retry with adjusted args.
+- Long-running operations (template snapshot, VM provisioning) return immediately with a `"creating" | "provisioning"` status. Poll via the corresponding Get / List tool until the status changes.
+
+## Tool catalog
+
+### Project & issues
+
+| Subcommand | Required flags | Purpose |
+|---|---|---|
+| `gsk vd get_project_overview` | — | Returns project metadata, repos, VMs (id + ready_state), and an `issues_summary` bucket count. Your first call in any workflow. |
+| `gsk vd list_issues` | `[--status <state>]` | List issues. Without `--status` you get all; with it, filter to one of: `pending`, `working`, `wait_human`, `waiting_code_review`, `testing`, `pending_user_confirm`, `completed`, `failed`, `cancelled`. |
+| `gsk vd get_issue_detail` | `--issue_id <id>` | Full issue record incl. `status`, `pr_url`, `assigned_vm_id`, `work_log` (state transitions with timestamps), `test_result`, `attempt_count`. |
+| `gsk vd issue_action` | `--issue_id <id> --action <verb>` | Move an issue through its lifecycle. `action` ∈ `continue`, `cancel`, `run_tests`, `confirm_merge`, `reject_merge`, `submit_review`, `retry`. `--reason` is optional text recorded in the work log. |
+| `gsk vd create_github_issue` | `--repo_id <id> --title <t> --body <md>` | Creates a new GitHub issue in the project's repo. The webhook handler will mirror it back as a VD issue shortly. Use after `get_project_overview` to read the `repo_id`. |
+| `gsk vd dispatch_issues` | — | One-shot scheduler trigger: pops the oldest `pending` issue and assigns it to the first idle VM. Returns `assigned: [{issue_id, vm_id}]`. Useful when you want to "push" without waiting for the periodic scheduler. |
+
+### VMs
+
+| Subcommand | Required flags | Purpose |
+|---|---|---|
+| `gsk vd list_vms` | — | List all VMs in the project with id, vm_name, ready_state, current_issue_id, public preview_url / domain. |
+| `gsk vd get_vm_status` | `--vm_id <id>` | Same fields as `list_vms` but single VM, plus public_ip. |
+| `gsk vd vm_action` | `--vm_id <id> --action <start\|stop>` | Start or stop a VM. These are synchronous (~10-60s). **Note:** other lifecycle actions (suspend/resume/save_snapshot/reset) are not exposed via this minimal wrapper — use the Web UI or direct API for those. |
+| `gsk vd create_vm` | — | Provision a new VM with project defaults. `--vm_size <lite\|standard\|high>` picks the tier (default `standard`): `lite` = 2C/4G Standard_B2s (64GB), `standard` = 2C/8G Standard_B2ms (64GB), `high` = 4C/16G Standard_B4ms (128GB). Returns immediately with `vm_id` + `status: "provisioning"`. Poll `get_vm_status` until `ready_state == "ready"` (~3-5 min). |
+| `gsk vd delete_vm` | `--vm_id <id>` | Delete a VM (soft delete; underlying Azure instance is also deleted). Confirm with user before calling. |
+| `gsk vd update_vm_startup_script` | `--vm_id <id> --startup_script <shell>` | Overwrite the VM's `startup_script` field. Typically a `#!/bin/bash` script that attaches to a tmux session on SSH login. |
+| `gsk vd reconfigure_vm` | `--vm_id <id>` | Re-run the full VM env setup: apt packages, opencode install, VS Code Remote profile, Caddy `:8443` reverse proxy, user SSH key, gsk token. **Use when a VM provisioned before a given config step existed is missing something** — e.g. preview URL at `:8443` returns CORS errors because Caddy was never configured. Idempotent. VM must be `ready` or `working`. Takes ~30-60s; briefly interrupts the preview URL during Caddy restart. Returns per-step status (`ok`/`failed`/`skipped`) for user-key and gsk-token injection. |
+| `gsk vd resize_vm` | `--vm_id <id> --vm_size <lite\|standard\|high>` | Resize a VM to a different tier. VM must be `ready` or `suspended`. Runs deallocate → Azure SKU change → optional disk grow → start (if it was running). Takes ~60-120s. **Disk can only grow, not shrink** — down-resize keeps the existing disk size. |
+
+### Exec / sessions
+
+| Subcommand | Required flags | Purpose |
+|---|---|---|
+| `gsk vd execute_command` | `--vm_id <id> --command <sh>` | Run a shell command on the VM via SSH. `--timeout <sec>` (default 30, max 120). Returns `{exit_code, stdout, stderr}`. VM must be `ready` (not `suspended`). |
+| `gsk vd get_session_messages` | `--vm_id <id> [--session_id <sid>]` | Without `--session_id`: list OpenCode sessions on that VM. With it: fetch message transcript. |
+| `gsk vd get_pr_info` | `--issue_id <id> [--include_diff]` | Fetch GitHub PR metadata (title, state, mergeable, review comments). `--include_diff` returns full diff (can be large). Issue must be past PR-creation phase. |
+
+### GitHub integration
+
+| Subcommand | Required flags | Purpose |
+|---|---|---|
+| `gsk vd check_github_auth` | `--repo_id <id>` | Verify the VD GitHub App installation for this repo can still acquire an installation token. Returns `ok`, `repo_full_name`, `installation_id`, `expires_at`. Use this when a VM reports 401s from git/GitHub API. |
+| `gsk vd refresh_vm_github_token` | `--vm_id <id> --repo_id <id>` | Re-issue a fresh installation token and inject it into the VM's `~/.netrc` / git credential helper. Run this if `check_github_auth` succeeds but the VM still sees auth errors (token expired inside VM). |
+| `gsk vd get_repo_github_token` | `--repo_id <id>` | Issue a GitHub App installation token and **return it to the caller** (not a VM) so local `gh` / `git` can act on the repo — merge PRs, push, clone from your laptop. Token inherits the App's installed permissions (repo read+write) and expires in ~1h (GitHub API cap); re-call for a fresh one. **WARNING**: treat response `data.token` as a secret — don't log, paste, or persist. gsk-only; not exposed in the web agent to avoid leakage via chat replays. |
+
+### VM templates
+
+| Subcommand | Required flags | Purpose |
+|---|---|---|
+| `gsk vd create_vm_template` | `--source_vm_id <id> --name <t>` | Snapshot a `ready` VM and register it as a reusable template. **Always confirm with the user before calling** — the snapshot runs 2-5 min in background. Returns `{template_id, status: "creating"}`. Poll `get_vm_template` until `status == "ready"`; `status == "failed"` surfaces the error in `error`. |
+| `gsk vd list_vm_templates` | — | List all templates in the project with id, name, status, size (raw Azure SKU), vm_size (tier `lite`/`standard`/`high`), region, env_configured, ctime. |
+| `gsk vd get_vm_template` | `--template_id <id>` | Full detail of a single template. |
+| `gsk vd delete_vm_template` | `--template_id <id>` | Soft-delete a template. **Always confirm with the user first**. The underlying Azure snapshot is NOT deleted (resource-group cleanup only). |
+
+## Common workflows
+
+### Audit project health
+
+```bash
+gsk vd get_project_overview
+gsk vd list_issues --status failed
+gsk vd list_issues --status waiting_code_review
+gsk vd list_vms
+```
+
+### Push a pending issue to an idle VM
+
+```bash
+# See what's pending
+gsk vd list_issues --status pending
+# See which VMs are idle (current_issue_id=null, ready_state=ready)
+gsk vd list_vms
+# Trigger scheduler once
+gsk vd dispatch_issues
+# Watch the assignment
+gsk vd list_issues --status working
+```
+
+### Investigate a failing issue
+
+```bash
+gsk vd get_issue_detail --issue_id <id>       # status, work_log, test_result, pr_url
+gsk vd get_pr_info --issue_id <id>            # PR state + review comments
+gsk vd get_session_messages --vm_id <vm_id>   # list OpenCode sessions on that VM
+gsk vd get_session_messages --vm_id <vm_id> --session_id <sid>   # full transcript
+```
+
+### Fix a VM whose preview URL / opencode session won't load
+
+Typical symptom: the Web UI shows CORS errors hitting
+`https://<domain>:8443/opencode/...`, or the VM's dev preview is
+unreachable from the browser. Root cause is usually that the VM was
+provisioned before the Caddy `:8443` reverse-proxy step existed, so
+`/etc/caddy/conf.d/vd-preview.caddy` is missing.
+
+```bash
+# VM must be running (not suspended)
+gsk vd get_vm_status --vm_id <id>
+# Re-run all env setup; idempotent, ~30-60s.
+gsk vd reconfigure_vm --vm_id <id>
+# Retry the preview URL in the browser.
+```
+
+### Fix a VM whose GitHub token expired
+
+```bash
+gsk vd check_github_auth --repo_id <repo>            # server-side token still valid?
+gsk vd refresh_vm_github_token --vm_id <vm> --repo_id <repo>   # re-inject into VM
+gsk vd execute_command --vm_id <vm> --command "cd /path/to/repo && git fetch"
+```
+
+### Merge a PR from your laptop (local `gh` without pre-existing auth)
+
+Use when your local `gh` CLI has no access to a private repo owned by
+the VD GitHub App.  Mints a short-lived installation token for that
+specific repo, authenticates `gh` with it, runs the merge, then the
+token expires in ~1h on its own.
+
+```bash
+# Mint a token and keep only the raw string in a shell variable
+TOKEN=$(gsk vd get_repo_github_token --repo_id <repo_id> | jq -r '.data.token')
+
+# Authenticate local gh with the token (reads from stdin)
+echo "$TOKEN" | gh auth login --with-token --hostname github.com
+
+# Now normal gh commands work against this repo
+gh pr merge 123 --merge --repo owner/repo
+
+# Token expires after ~1h; re-run `gsk vd get_repo_github_token` for a fresh one.
+unset TOKEN
+```
+
+**Safety**: the token is treated as a secret by the skill — don't
+echo it to stdout, don't paste it into chat, don't write it to a
+file on disk.  The `jq -r '.data.token'` extraction keeps it in a
+shell variable only.
+
+### Run a diagnostic command on a working VM
+
+```bash
+# VM must be ready, not suspended
+gsk vd get_vm_status --vm_id <id>
+gsk vd execute_command --vm_id <id> --command "git status && tmux ls" --timeout 10
+```
+
+### Save a configured VM as a template
+
+```bash
+# Always confirm with user first — takes 2-5 min in background
+gsk vd create_vm_template --source_vm_id <ready-vm> --name "my-dev-env"
+# Returns {template_id, status: "creating"}
+# Poll:
+gsk vd get_vm_template --template_id <tid>
+# When status=="ready", snapshot_id is populated and it's usable in create_vm
+```
+
+## Safety rules
+
+- **Confirm with the user before** calling `create_vm_template`, `delete_vm_template`, `delete_vm`, `vm_action --action stop`, `issue_action --action cancel/reject_merge/confirm_merge`, `update_vm_startup_script`, `create_github_issue`. These mutate state, produce user-visible side effects (PR merges, Azure resource churn, GitHub noise), or take minutes to complete.
+- **Never `execute_command`** with destructive args (`rm -rf`, `git reset --hard`, `kill -9`) without an explicit ask. The VM holds user work-in-progress.
+- **Before calling `refresh_vm_github_token`**, verify the VM is actually hitting 401s — do not rotate tokens pre-emptively; it invalidates any concurrent git operation on the VM.
+
+## See also
+
+- `../gsk-shared/SKILL.md` — auth, output conventions, global flags.
+- Web UI for the same functionality: `https://<host>/virtual-developer/project/<vd_project_id>` → Agent tab.