[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79FD18ZXX9ZP3J3DKAAR6ZF":3,"skill-same:01M79FD18ZXX9ZP3J3DKAAR6ZF":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M79FD18ZXX9ZP3J3DKAAR6ZF","use-spark",null,"Use the spark CLI to access the user's Spark email data - list emails, search by topic, read threads, check calendar events, find availability, look up contacts, and view team info. Use when the user asks about their emails, calendar, contacts, meetings, or scheduling.","BumpyClock\u002Fagent-templates","BumpyClock","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1883824?v=4","01M79EW0FDP9MFXH1FKH800S7T","Aditya Sharma","01M79EW0G27TTKZWTFQ8W5HVB4",2,"MIT","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fuse-spark\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: use-spark\ndescription: >-\n  Use the spark CLI to access the user's Spark email data - list emails,\n  search by topic, read threads, check calendar events, find availability,\n  look up contacts, and view team info. Use when the user asks about their\n  emails, calendar, contacts, meetings, or scheduling.\nmetadata:\n  version: 1.1.0\n  requires:\n    bins:\n      - spark\n---\n\n# Using spark\n\n`spark` is a CLI for the Spark email client. Use it to query the user's mailbox, calendar, contacts, meetings, and team data.\n\n## Running spark\n\n```bash\nspark \u003Ccommand> [options]\n```\n\n**Environment:** `spark` is a thin client that talks over IPC to the user's running Spark macOS Desktop app - it does not ship its own mailbox, network stack, or credentials. Run it directly on the user's Mac against the live Spark Desktop process. Do not try to execute it inside a sandbox, container, CI runner, or any environment isolated from the user's desktop session - it will fail to connect. If Spark Desktop is not running, ask the user to launch it instead of retrying.\n\n## Commands\n\n| Command | Description |\n|---------|-------------|\n| `accounts` | List accounts, calendars, teams, shared inboxes, and access levels |\n| `folders` | List folders\u002Flabels with message counts |\n| `emails` | List emails with filters and pagination |\n| `search` | Hybrid keyword + semantic search with full bodies |\n| `thread` | Read full thread - headers, bodies, attachments |\n| `draft` | Create or edit an email draft (new, reply, forward) |\n| `comment` | Post a team comment on a thread |\n| `events` | List calendar events for a time range |\n| `availability` | Find free time slots, optionally with attendees |\n| `contacts` | Search contacts by name or email |\n| `team` | Show team info, members, shared inboxes, assignments |\n| `meetings` | List meeting transcripts |\n| `meeting` | Read a single meeting transcript |\n| `action` | Perform actions on emails (archive, pin, snooze, assign, etc.) |\n| `contact-action` | Perform actions on contacts (block, accept, categorize, etc.) |\n\n### accounts\n\nList all configured accounts with their calendars, teams, and shared inboxes. Each account and shared inbox shows its **access level** in parentheses, which controls what operations Spark can perform.\n\n```bash\nspark accounts\n```\n\nRun this first to discover what accounts, calendars, and teams are available, and to check their access levels.\n\n**Access levels:**\n\n| Level | Allowed operations |\n|-------|-------------------|\n| **read-only** | List, search, and read emails, threads, folders, events, contacts, meetings, teams |\n| **triage** | Everything in read-only plus all write operations: drafts, team comments, email actions (archive, move, pin, snooze, assign, etc.) and contact actions (block, accept, categorize, etc.) |\n\nAccess levels are configured separately for each account and each shared inbox in Spark Desktop under Settings -> AI Agents. Shared inboxes can have a different access level than the parent account - for example, a personal account may have triage access while a shared inbox under the same team is read-only or disabled.\n\nIf a command requires a higher access level than the account or shared inbox has, it returns an error with instructions on how to change the level.\n\n### folders\n\nList folders with message counts. Output includes folder identifiers in parentheses - use these as arguments to `emails` and `search`. Mailboxes backed by a Google account show `(Gmail labels)` on the **Email Account** or **Shared Inbox** header. Teams show the team name as a usable identifier for `emails`.\n\n```bash\nspark folders                        # all accounts\nspark folders user@example.com       # single account\n```\n\n### emails\n\nList emails with metadata (ID, From, Date, Subject, Flags). Supports pagination and Gmail-style filters.\n\n```bash\nspark emails                                                   # Unified Inbox\nspark emails user@example.com:Archive                          # specific folder\nspark emails \"My Team\"                                         # all shared threads in a team\nspark emails --filter \"from:alice@co.com is:unread\"             # filtered\nspark emails --filter \"newer_than:7d has:attachment\"            # recent with attachments\nspark emails --page 2 --page-size 20                           # pagination\nspark emails --order ascending                                 # oldest first\nspark emails --new-senders                                     # show only new sender emails\n```\n\n**GateKeeper filtering:** When viewing the Inbox with GateKeeper in explicit mode, new sender emails are automatically filtered out and a \"New Senders\" count is shown at the top. Use `--new-senders` to view those emails. Use `contact-action acceptContact \u003Cemail>` or `contact-action blockContact \u003Cemail>` to accept or block a sender.\n\n**Folder identifier formats** (run `folders` to see available ones):\n\n| Format | Example | Meaning |\n|--------|---------|---------|\n| Bare name | `Inbox`, `Archive` | Unified folder (cross-account) |\n| `email` | `user@example.com` | Account inbox shorthand |\n| `email:Folder` | `user@example.com:Archive` | Specific account folder |\n| `\"Team Name\"` | `\"My Team\"` | All shared threads in a team (quote if spaces) |\n| `shared@email:Folder` | `shared@co.com:Inbox` | Shared inbox folder |\n\n**Filter operators** (combinable, Gmail-style):\n\n| Operator | Example |\n|----------|---------|\n| `from:\u003Caddr>` | `from:alice@co.com` |\n| `to:\u003Caddr>` | `to:bob@co.com` |\n| `cc:\u003Caddr>` | `cc:team@co.com` |\n| `subject:\u003Ctext>` | `subject:\"quarterly report\"` |\n| `before:yyyy\u002FMM\u002Fdd` | `before:2026\u002F03\u002F01` |\n| `after:yyyy\u002FMM\u002Fdd` | `after:2026\u002F01\u002F01` |\n| `newer_than:Xd` | `newer_than:7d` (also `w`, `m`, `y`) |\n| `older_than:Xd` | `older_than:30d` |\n| `has:attachment` | also `document`, `spreadsheet`, `presentation`, `reminder` |\n| `is:unread` | also `read`, `starred`, `pinned`, `unreplied` |\n| `is:shared` | emails shared to any team (alias for `is:shared_email`) |\n| `is:shared_inbox_open` | open items in shared inbox |\n| `is:shared_inbox_done` | completed\u002Fclosed items in shared inbox |\n| `category:personal` | also `priority`, `notification`, `newsletter`, `invitation`, `invitation_response` |\n| `assigned_to:me` | emails assigned to current user |\n| `assigned_to:\u003Cemail>` | emails assigned to specific teammate |\n| `assigned_to:unassigned` | shared inbox items with no assignee |\n| `assigned_to:other` | emails assigned to someone else (not me) |\n| `assigned_by:me` | emails delegated by current user |\n| `filename:\u003Cname>` | `filename:report.pdf` |\n\n### search\n\nHybrid keyword + semantic search returning up to 20 emails with full bodies, sorted by relevance.\n\n```bash\nspark search \"quarterly report\"\nspark search \"API integration\" --filter \"from:alice@co.com\"\nspark search \"budget\" --in user@example.com:Archive\nspark search \"vacation\" --in user@example.com              # all folders in account\n```\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| `\u003Cabout>` | Yes | Search topic (positional) |\n| `--filter` | No | Gmail-style filter (same operators as `emails`) |\n| `--in` | No | Scope: account, team, folder, or shared inbox. All folders if omitted. |\n\n**Use `search` when the user asks about a topic.** It returns email bodies so you can answer questions about content. Use `emails` when listing\u002Fbrowsing by folder or filters without needing bodies.\n\n### thread\n\nPrint every message in a thread - headers, full plain-text bodies, and attachment info. After the thread summary line, lists **custom (non-system) folder labels** once for the whole thread, using qualified names like `account@domain.com:MyLabel` (same style as `folders`).\n\n```bash\nspark thread 1114                          # by message ID from emails\u002Fsearch output\nspark thread --download-attachments 1114   # also fetch attachments via IMAP\n```\n\nUse `emails` or `search` to find message IDs (the ID column), then `thread` to read the full conversation. Use `folders` to list valid label identifiers for `action attachLabel` \u002F `detachLabel`.\n\n### draft\n\n**Requires: triage** access level.\n\nCreate a new email draft or edit an existing one. The body is written in markdown and converted to HTML.\n\n```bash\nspark draft --to \"alice@example.com\" --subject \"Hello\" --body \"Hi Alice, ...\"\nspark draft --to \"alice@co.com\" --to \"bob@co.com\" --cc \"carol@co.com\" --subject \"Meeting\" --body \"...\"\nspark draft --edit 1234 --subject \"Updated subject\" --body \"Updated body\"\nspark draft --reply-to 5678 --body \"Thanks for the update!\"\nspark draft --forward 5678 --to \"manager@co.com\" --body \"FYI\"\nspark draft --account \"john@gmail.com\" --to \"alice@co.com\" --subject \"Hi\" --body \"...\"\nspark draft --to \"alice@co.com\" --subject \"Report\" --body \"See attached\" --attach \u002Fpath\u002Fto\u002Freport.pdf\nspark draft --to \"alice@co.com\" --subject \"Files\" --body \"Two files\" --attach \u002Fpath\u002Fto\u002Fa.pdf --attach \u002Fpath\u002Fto\u002Fb.xlsx\n```\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| `--to` | No | Recipient address (RFC822). Repeat for multiple. |\n| `--cc` | No | CC address. Repeat for multiple. |\n| `--bcc` | No | BCC address. Repeat for multiple. |\n| `--subject` | No | Subject line. |\n| `--body` | Yes (new) | Body content in markdown. Required for new drafts. |\n| `--edit` | No | Message ID of an existing draft to update. |\n| `--reply-to` | No | Message ID to reply to. |\n| `--forward` | No | Message ID to forward. |\n| `--account` | No | Account email to send from. Accepts a regular mail account, an alias, or a shared inbox email. |\n| `--attach` | No | Absolute path to a file to attach. Repeat for multiple. |\n\nUse `emails` to find message IDs for `--edit`, `--reply-to`, and `--forward`. Use `accounts` to find account emails for `--account` - both personal accounts and shared inboxes are listed there, and either can be used as the from address when the account has draft & comment access.\n\n### comment\n\n**Requires: triage** access level.\n\nPost a team comment (chat message) on a thread. If the thread is not yet shared, it will be shared automatically. Supports text comments, file attachments, or both. Use `--edit` to update an existing comment.\n\n```bash\nspark comment 1234 --body \"Looks good, let's proceed.\"\nspark comment 1234 --body \"Please review this\" --team \"Engineering\"\nspark comment 1234 --body \"FYI\" --team \"Engineering\" --user alice@co.com --user bob@co.com\nspark comment 1234 --attach \u002Fpath\u002Fto\u002Fscreenshot.png\nspark comment 1234 --body \"See attached\" --attach \u002Fpath\u002Fto\u002Freport.pdf --attach \u002Fpath\u002Fto\u002Fdata.csv\nspark comment --edit 5678 --body \"Updated comment text\"\n```\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| `\u003Cmessage-id>` | Yes (post) | Message ID of a message in the thread to comment on. |\n| `--body` | When no `--attach` | Comment text to post. Required when using `--edit`. |\n| `--attach` | When no `--body` | Absolute path to a file to attach. Repeat for multiple files. Each file is sent as a separate message. Cannot be used with `--edit`. |\n| `--edit` | No | Message ID of an existing comment to edit. Requires `--body`. |\n| `--team` | When >1 team | Team name. Required when you belong to multiple teams. |\n| `--user` | When team >2 members | Teammate email to share with. Repeat for multiple. Only used when auto-sharing an unshared thread. For teams with 2 or fewer members, the whole team is shared with automatically. |\n\nUse `emails` to find message IDs. Use `thread` to see comment IDs in a conversation. Use `team` to list teams and their members.\n\n### events\n\nList calendar events for a time range.\n\n```bash\nspark events                                          # today's remaining events\nspark events --tomorrow\nspark events --week\nspark events --week --in user@example.com             # specific account\nspark events --week --in user@example.com:Work        # specific calendar\nspark events --start 2026-03-16 --end 2026-03-20      # custom range\n```\n\nDate formats: `yyyy-MM-dd`, `dd\u002FMM\u002Fyyyy`, or `yyyy-MM-ddTHH:mm`.\n\nRun `accounts` to see available calendar accounts and calendar names.\n\n### availability\n\nFind free time slots. Without `--attendees`, shows the user's own availability. With `--attendees`, computes mutual free windows.\n\n```bash\nspark availability                                                        # today\nspark availability --tomorrow\nspark availability --week --attendees alice@co.com\nspark availability --start 2026-03-16 --end 2026-03-20 --attendees a@co.com,b@co.com\n```\n\nFree slots are within working hours (08:00-20:00), skip weekends, and ignore events marked \"free\".\n\n### contacts\n\nSearch contacts by name or email. Strict match first, then fuzzy fallback.\n\n```bash\nspark contacts \"john\"\nspark contacts \"example.com\"\n```\n\n### team\n\nShow team info - metadata, shared inboxes with members, full member list, assigned emails, assignment summary.\n\n```bash\nspark team                     # list available teams\nspark team \"Readdle\"           # specific team\n```\n\n### meetings\n\nList meeting transcripts with optional filters and pagination.\n\n```bash\nspark meetings\nspark meetings --filter \"newer_than:30d\"\nspark meetings --filter \"subject:standup\" --page-size 10\n```\n\nFilter operators: `subject:\u003Ctext>`, `before:yyyy\u002FMM\u002Fdd`, `after:yyyy\u002FMM\u002Fdd`, `newer_than:Xd`, `older_than:Xd`.\n\n### meeting\n\nRead a single meeting transcript's summary. Optionally include the full transcript and\u002For notes.\n\n```bash\nspark meeting 42                            # summary only\nspark meeting --transcript 42               # include transcript\nspark meeting --notes 42                    # include notes\nspark meeting --transcript --notes 42       # everything\n```\n\nUse `meetings` to find meeting IDs.\n\n### action\n\n**Requires: triage** access level.\n\nPerform an action on one or more emails. Supports standard email actions and team actions.\n\n```bash\nspark action \u003Caction-name> \u003Cmessage-id...> [options]\n```\n\nSupported actions:\n- `pin` - Pin the message to keep it at the top of the list\n- `unpin` - Remove the pin from the message\n- `mute` - Mute the thread to stop receiving notifications\n- `unmute` - Unmute a previously muted thread\n- `snooze` - Snooze the message until a specific date (requires `--date`)\n- `unsnooze` - Remove the snooze and return the message to the inbox\n- `changeReminder` - Set a follow-up reminder if no reply by the date (requires `--date`)\n- `clearReminder` - Remove the follow-up reminder from the message\n- `setAside` - Set the message aside for later review\n- `archive` - Archive the message, removing it from the inbox\n- `moveToInbox` - Move the message back to the inbox\n- `moveToTrash` - Move the message to trash\n- `moveToFolder` - Move the message to a specific folder (requires `--folder`)\n- `attachLabel` - Attach a Gmail or Spark Team label without removing other labels (requires `--folder`)\n- `detachLabel` - Remove a Gmail or Spark Team label from the message (requires `--folder`)\n- `markAsDone` - Mark the message as done\n- `markAsUndone` - Mark the message as not done\n- `markAsSeen` - Mark the message as read\n- `markAsUnseen` - Mark the message as unread\n- `markAsSpam` - Mark the message as spam\n- `markThreadAsPriority` - Mark the thread as priority\n- `unmarkThreadAsPriority` - Remove the priority mark from the thread\n- `unsubscribe` - Unsubscribe from the sender or mailing list\n- `changeCategoryPersonal` - Change the email category to Personal\n- `changeCategoryNotification` - Change the email category to Notification\n- `changeCategoryNewsletters` - Change the email category to Newsletter\n- `shareInTeam` - Share the thread with teammates (requires `--team` when multiple teams)\n- `assign` - Assign the email to a teammate (requires `--assignee`)\n- `delegationComplete` - Mark the delegation as complete\n- `delegationReopen` - Reopen a completed delegation\n\nOptions:\n- `--date` - required for `snooze` and `changeReminder`, optional for `assign` as due date (formats: `yyyy-MM-dd`, `dd\u002FMM\u002Fyyyy`, `yyyy-MM-ddTHH:mm`)\n- `--folder` - required for `moveToFolder`, `attachLabel`, and `detachLabel` (qualified name: `email@domain.com:FolderName`; use `folders` to list labels including shared inboxes)\n- `--team` - team name for team actions; required when you belong to multiple teams\n- `--user` - teammate email to share with for `shareInTeam`; repeat for multiple users; required when team has more than 2 members\n- `--assignee` - teammate email to assign the email to for `assign`\n- `--comment` - comment text for the `assign` action\n\n```bash\nspark action pin 12345                                          # pin a message\nspark action archive 100 200 300                                # archive multiple messages\nspark action markAsSeen 100 200                                 # mark as read\nspark action snooze 12345 --date 2026-04-10T09:00               # snooze until date\u002Ftime\nspark action snooze 12345 --date 2026-04-10                     # snooze until date\nspark action moveToFolder 12345 --folder \"user@example.com:Archive\"  # move to folder\nspark action attachLabel 12345 --folder \"user@gmail.com:MyLabel\"       # add Gmail\u002FTeam label\nspark action detachLabel 12345 --folder \"shared@company.com:SomeLabel\"  # remove label\nspark action changeReminder 12345 --date 2026-04-15             # set reminder\nspark action shareInTeam 1234 --team \"Engineering\" --user alice@co.com  # share with teammate\nspark action shareInTeam 1234 --user alice@co.com --user bob@co.com    # share with multiple\nspark action assign 1234 --assignee bob@co.com                  # assign to teammate\nspark action assign 1234 --assignee bob@co.com --date 2026-04-15 --comment \"Please review\"\nspark action delegationComplete 1234                            # mark delegation done\nspark action delegationComplete 100 200 300                     # complete multiple delegations\nspark action delegationReopen 1234                              # reopen delegation\n```\n\nUse the `emails` command to find message IDs. Use `folders` to resolve qualified names for `moveToFolder`, `attachLabel`, and `detachLabel`. Use `team` to list teams and members for team actions.\n\n### contact-action\n\n**Requires: triage** access level.\n\nPerform an action on one or more contacts by email address.\n\n```bash\nspark contact-action \u003Caction-name> \u003Cemail...>\n```\n\nSupported actions:\n\n| Action | Description |\n|--------|-------------|\n| `changeCategoryPersonal` | Change the contact's email category to Personal |\n| `changeCategoryNotification` | Change the contact's email category to Notification |\n| `changeCategoryNewsletters` | Change the contact's email category to Newsletter |\n| `groupEmailsFromContact` | Group emails from the contact by category |\n| `groupEmailsFromContactAndShowInInbox` | Group emails from the contact and show in inbox |\n| `ungroupEmailsFromContact` | Ungroup emails from the contact |\n| `markContactAsImportant` | Enable notifications for the contact |\n| `unmarkContactAsImportant` | Disable notifications for the contact |\n| `markContactAsPrimary` | Mark the contact as priority (auto-prioritize emails) |\n| `unmarkContactAsPrimary` | Remove priority mark from the contact |\n| `acceptContact` | Accept or unblock the contact (bypass Gatekeeper) |\n| `blockContact` | Block the contact |\n| `acceptDomain` | Accept or unblock the contact's entire domain |\n| `blockDomain` | Block the contact's entire domain |\n| `enableAutosummaryForContact` | Enable auto-summary for emails from the contact |\n| `disableAutosummaryForContact` | Disable auto-summary for emails from the contact |\n\nExamples:\n\n```bash\nspark contact-action blockContact spammer@example.com\nspark contact-action acceptContact alice@co.com bob@co.com\nspark contact-action changeCategoryPersonal alice@co.com\nspark contact-action markContactAsPrimary ceo@company.com\nspark contact-action enableAutosummaryForContact newsletter@example.com\n```\n\nUse the `contacts` command to look up email addresses.\n\n## Smart Categories\n\nSpark automatically classifies incoming email into six categories. Use the `category:` filter operator with `emails` and `search` to view mail by category, and use `action` \u002F `contact-action` to reclassify and tune.\n\n| Category | Filter | Typical Content |\n|----------|--------|-----------------|\n| Priority | `category:priority` | Auto-prioritized or manually marked as priority |\n| People | `category:personal` | Direct person-to-person email |\n| Notifications | `category:notification` | Service notifications, alerts, receipts |\n| Newsletters | `category:newsletter` | Subscriptions, digests, marketing |\n| Invites | `category:invitation` | Calendar invitations |\n| Invite Responses | `category:invitation_response` | RSVPs, accepts, declines |\n\n**Browse by category** (read-only):\n\n```bash\nspark emails Inbox --filter \"category:priority is:unread\"       # unread priority mail\nspark emails Inbox --filter \"category:personal is:unread\"       # unread people mail\nspark emails Inbox --filter \"category:invitation\"               # pending invites\nspark emails Inbox --filter \"category:notification is:unread\"   # unread notifications\nspark emails Inbox --filter \"category:newsletter newer_than:7d\" # recent newsletters\n```\n\n**Reclassify a message** (triage):\n\n```bash\nspark action changeCategoryPersonal \u003Cid>       # move to People\nspark action changeCategoryNotification \u003Cid>   # move to Notifications\nspark action changeCategoryNewsletters \u003Cid>    # move to Newsletters\n```\n\n**Tune per-contact category rules** (triage) - changes apply to all future mail from the sender:\n\n```bash\nspark contact-action changeCategoryPersonal sender@example.com         # reclassify as People\nspark contact-action changeCategoryNewsletters sender@example.com      # reclassify as Newsletters\nspark contact-action groupEmailsFromContact sender@example.com         # group by category\nspark contact-action markContactAsImportant vip@example.com            # enable notifications\nspark contact-action markContactAsPrimary ceo@example.com              # auto-prioritize\nspark contact-action enableAutosummaryForContact newsletter@example.com # AI summaries\n```\n\n**Category-first triage pattern:** Process inbox in priority order - priority first, then people, then invites, then notifications, then newsletters. This ensures the most important messages get attention first.\n\n## Typical Workflows\n\n**Answer a question about emails:**\n1. `spark search \"topic\"` - find relevant emails with bodies\n2. Read the output and answer the user's question\n\n**Find and read a specific email:**\n1. `spark emails --filter \"from:sender subject:keyword\"` - locate the email\n2. `spark thread \u003CID>` - read the full conversation\n\n**Draft a reply:**\n1. `spark emails --filter \"from:sender\"` - find the email\n2. `spark draft --reply-to \u003CID> --body \"Thanks for the update!\"`\n\n**Check someone's schedule for a meeting:**\n1. `spark availability --tomorrow --attendees alice@co.com,bob@co.com`\n2. Suggest a time from the free slots\n\n**Comment on a shared thread:**\n1. `spark emails --filter \"from:sender\"` - find the email\n2. `spark comment \u003CID> --body \"Looks good, approved!\"`\n\n**Get team workload overview:**\n1. `spark team \"Team Name\"` - see members and assigned emails\n\n**Look up a contact:**\n1. `spark contacts \"name or domain\"` - find their email address\n\n**Perform an action on emails:**\n1. `spark emails --filter \"from:sender\"` - find the email\n2. `spark action archive \u003CID>` - archive it (or pin, snooze, etc.)\n\n**Share an email with your team:**\n1. `spark emails --filter \"subject:keyword\"` - find the email\n2. `spark action shareInTeam \u003CID> --user alice@co.com` - share with a teammate\n\n**Delegate an email to a teammate:**\n1. `spark emails --filter \"subject:keyword\"` - find the email\n2. `spark action assign \u003CID> --assignee bob@co.com --date 2026-04-15 --comment \"Please handle this\"`\n\n**Mark delegated emails as done:**\n1. `spark emails --filter \"subject:keyword\"` - find the email(s)\n2. `spark action delegationComplete \u003CID1> \u003CID2>` - mark multiple as complete\n\n**Find unassigned shared inbox emails:**\n1. `spark emails shared@co.com:Inbox --filter \"assigned_to:unassigned\"` - list unassigned items\n2. `spark action assign \u003CID> --assignee bob@co.com` - assign to a teammate\n\n**Review what's assigned to a teammate:**\n1. `spark emails --filter \"assigned_to:bob@co.com\"` - see their assignments\n2. `spark emails --filter \"is:shared_inbox_open\"` - all open shared inbox items\n3. `spark emails --filter \"is:shared_inbox_done\"` - completed items\n\n**Manage a contact:**\n1. `spark contacts \"name or domain\"` - find the contact email\n2. `spark contact-action blockContact spammer@example.com` - block them (or accept, change category, etc.)\n\n## Keeping this skill up to date\n\nThe CLI and this skill share a single version (`metadata.version` in the front-matter above). New features in newer Spark Desktop releases ship with an updated embedded skill. Backward compatibility is guaranteed within a major version, so the commands and flags documented here keep working - but newly added features won't appear in this file until it is reinstalled.\n\nCheck for an update when - and only when - you hit one of these signals:\n\n- The user asks about a Spark feature, command, or flag that isn't documented here.\n- A `spark` command fails with an \"unknown command\" or \"unknown option\" error you didn't expect.\n- The user explicitly says they upgraded Spark or that the skill is out of date.\n\nIn those cases:\n\n```bash\nspark --version\n```\n\nIf the printed version is greater than `metadata.version` above, refresh this file before answering. `spark skill` prints SKILL.md to stdout - capture it and write it back over the file you're reading right now (the path is in your context). For example:\n\n```bash\nmkdir -p \u003Cparent-of-use-spark>\u002Fuse-spark\nspark skill > \u003Cparent-of-use-spark>\u002Fuse-spark\u002FSKILL.md\n```\n\n`\u003Cparent-of-use-spark>` is the directory containing the `use-spark\u002F` folder this `SKILL.md` lives in. If you have a file-write tool, you can also pipe `spark skill` output directly through it - the CLI itself does not write any files.\n\nDo not check on every session or before every command - this skill is the source of truth unless one of the signals above tells you otherwise.\n\n## Tips\n\n- Always quote multi-word arguments: `spark search \"project update\"`\n- Combine filter operators in a single `--filter` string: `--filter \"from:alice@co.com is:unread newer_than:7d\"`\n- Use `folders` to discover exact folder identifiers before passing them to `emails` or `search --in`\n- Use `accounts` to discover calendar names before passing them to `events --in`\n- The `search` command is best for topic-based queries; `emails` is best for browsing\u002Ffiltering by metadata\n- `thread` returns the full conversation - use it when you need the complete email text, not just metadata\n- Use `draft` to compose emails - it supports new drafts, replies, forwards, and editing existing drafts\n- Use `comment` to post team chat messages on threads - it auto-shares the thread if needed\n- Use `action` to perform email actions like pin, archive, snooze, move to folder, and more\n- Use `contact-action` to manage contacts - block, accept, change category, toggle auto-summary, and more","# Using spark\n\n`spark` is a CLI for the Spark email client. Use it to query the user's mailbox, calendar, contacts, meetings, and team data.\n\n## Running spark\n\n```bash\nspark \u003Ccommand> [options]\n```\n\n**Environment:** `spark` is a thin client that talks over IPC to the user's running Spark macOS Desktop app - it does not ship its own mailbox, network stack, or credentials. Run it directly on the user's Mac against the live Spark Desktop process. Do not try to execute it inside a sandbox, container, CI runner, or any environment isolated from the user's desktop session - it will fail to connect. If Spark Desktop is not running, ask the user to launch it instead of retrying.\n\n## Commands\n\n| Command | Description |\n|---------|-------------|\n| `accounts` | List accounts, calendars, teams, shared inboxes, and access levels |\n| `folders` | List folders\u002Flabels with message counts |\n| `emails` | List emails with filters and pagination |\n| `search` | Hybrid keyword + semantic search with full bodies |\n| `thread` | Read full thread - headers, bodies, attachments |\n| `draft` | Create or edit an email draft (new, reply, forward) |\n| `comment` | Post a team comment on a thread |\n| `events` | List calendar events for a time range |\n| `availability` | Find free time slots, optionally with attendees |\n| `contacts` | Search contacts by name or email |\n| `team` | Show team info, members, shared inboxes, assignments |\n| `meetings` | List meeting transcripts |\n| `meeting` | Read a single meeting transcript |\n| `action` | Perform actions on emails (archive, pin, snooze, assign, etc.) |\n| `contact-action` | Perform actions on contacts (block, accept, categorize, etc.) |\n\n### accounts\n\nList all configured accounts with their calendars, teams, and shared inboxes. Each account and shared inbox shows its **access level** in parentheses, which controls what operations Spark can perform.\n\n```bash\nspark accounts\n```\n\nRun this first to discover what accounts, calendars, and teams are available, and to check their access levels.\n\n**Access levels:**\n\n| Level | Allowed operations |\n|-------|-------------------|\n| **read-only** | List, search, and read emails, threads, folders, events, contacts, meetings, teams |\n| **triage** | Everything in read-only plus all write operations: drafts, team comments, email actions (archive, move, pin, snooze, assign, etc.) and contact actions (block, accept, categorize, etc.) |\n\nAccess levels are configured separately for each account and each shared inbox in Spark Desktop under Settings -> AI Agents. Shared inboxes can have a different access level than the parent account - for example, a personal account may have triage access while a shared inbox under the same team is read-only or disabled.\n\nIf a command requires a higher access level than the account or shared inbox has, it returns an error with instructions on how to change the level.\n\n### folders\n\nList folders with message counts. Output includes folder identifiers in parentheses - use these as arguments to `emails` and `search`. Mailboxes backed by a Google account show `(Gmail labels)` on the **Email Account** or **Shared Inbox** header. Teams show the team name as a usable identifier for `emails`.\n\n```bash\nspark folders                        # all accounts\nspark folders user@example.com       # single account\n```\n\n### emails\n\nList emails with metadata (ID, From, Date, Subject, Flags). Supports pagination and Gmail-style filters.\n\n```bash\nspark emails                                                   # Unified Inbox\nspark emails user@example.com:Archive                          # specific folder\nspark emails \"My Team\"                                         # all shared threads in a team\nspark emails --filter \"from:alice@co.com is:unread\"             # filtered\nspark emails --filter \"newer_than:7d has:attachment\"            # recent with attachments\nspark emails --page 2 --page-size 20                           # pagination\nspark emails --order ascending                                 # oldest first\nspark emails --new-senders                                     # show only new sender emails\n```\n\n**GateKeeper filtering:** When viewing the Inbox with GateKeeper in explicit mode, new sender emails are automatically filtered out and a \"New Senders\" count is shown at the top. Use `--new-senders` to view those emails. Use `contact-action acceptContact \u003Cemail>` or `contact-action blockContact \u003Cemail>` to accept or block a sender.\n\n**Folder identifier formats** (run `folders` to see available ones):\n\n| Format | Example | Meaning |\n|--------|---------|---------|\n| Bare name | `Inbox`, `Archive` | Unified folder (cross-account) |\n| `email` | `user@example.com` | Account inbox shorthand |\n| `email:Folder` | `user@example.com:Archive` | Specific account folder |\n| `\"Team Name\"` | `\"My Team\"` | All shared threads in a team (quote if spaces) |\n| `shared@email:Folder` | `shared@co.com:Inbox` | Shared inbox folder |\n\n**Filter operators** (combinable, Gmail-style):\n\n| Operator | Example |\n|----------|---------|\n| `from:\u003Caddr>` | `from:alice@co.com` |\n| `to:\u003Caddr>` | `to:bob@co.com` |\n| `cc:\u003Caddr>` | `cc:team@co.com` |\n| `subject:\u003Ctext>` | `subject:\"quarterly report\"` |\n| `before:yyyy\u002FMM\u002Fdd` | `before:2026\u002F03\u002F01` |\n| `after:yyyy\u002FMM\u002Fdd` | `after:2026\u002F01\u002F01` |\n| `newer_than:Xd` | `newer_than:7d` (also `w`, `m`, `y`) |\n| `older_than:Xd` | `older_than:30d` |\n| `has:attachment` | also `document`, `spreadsheet`, `presentation`, `reminder` |\n| `is:unread` | also `read`, `starred`, `pinned`, `unreplied` |\n| `is:shared` | emails shared to any team (alias for `is:shared_email`) |\n| `is:shared_inbox_open` | open items in shared inbox |\n| `is:shared_inbox_done` | completed\u002Fclosed items in shared inbox |\n| `category:personal` | also `priority`, `notification`, `newsletter`, `invitation`, `invitation_response` |\n| `assigned_to:me` | emails assigned to current user |\n| `assigned_to:\u003Cemail>` | emails assigned to specific teammate |\n| `assigned_to:unassigned` | shared inbox items with no assignee |\n| `assigned_to:other` | emails assigned to someone else (not me) |\n| `assigned_by:me` | emails delegated by current user |\n| `filename:\u003Cname>` | `filename:report.pdf` |\n\n### search\n\nHybrid keyword + semantic search returning up to 20 emails with full bodies, sorted by relevance.\n\n```bash\nspark search \"quarterly report\"\nspark search \"API integration\" --filter \"from:alice@co.com\"\nspark search \"budget\" --in user@example.com:Archive\nspark search \"vacation\" --in user@example.com              # all folders in account\n```\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| `\u003Cabout>` | Yes | Search topic (positional) |\n| `--filter` | No | Gmail-style filter (same operators as `emails`) |\n| `--in` | No | Scope: account, team, folder, or shared inbox. All folders if omitted. |\n\n**Use `search` when the user asks about a topic.** It returns email bodies so you can answer questions about content. Use `emails` when listing\u002Fbrowsing by folder or filters without needing bodies.\n\n### thread\n\nPrint every message in a thread - headers, full plain-text bodies, and attachment info. After the thread summary line, lists **custom (non-system) folder labels** once for the whole thread, using qualified names like `account@domain.com:MyLabel` (same style as `folders`).\n\n```bash\nspark thread 1114                          # by message ID from emails\u002Fsearch output\nspark thread --download-attachments 1114   # also fetch attachments via IMAP\n```\n\nUse `emails` or `search` to find message IDs (the ID column), then `thread` to read the full conversation. Use `folders` to list valid label identifiers for `action attachLabel` \u002F `detachLabel`.\n\n### draft\n\n**Requires: triage** access level.\n\nCreate a new email draft or edit an existing one. The body is written in markdown and converted to HTML.\n\n```bash\nspark draft --to \"alice@example.com\" --subject \"Hello\" --body \"Hi Alice, ...\"\nspark draft --to \"alice@co.com\" --to \"bob@co.com\" --cc \"carol@co.com\" --subject \"Meeting\" --body \"...\"\nspark draft --edit 1234 --subject \"Updated subject\" --body \"Updated body\"\nspark draft --reply-to 5678 --body \"Thanks for the update!\"\nspark draft --forward 5678 --to \"manager@co.com\" --body \"FYI\"\nspark draft --account \"john@gmail.com\" --to \"alice@co.com\" --subject \"Hi\" --body \"...\"\nspark draft --to \"alice@co.com\" --subject \"Report\" --body \"See attached\" --attach \u002Fpath\u002Fto\u002Freport.pdf\nspark draft --to \"alice@co.com\" --subject \"Files\" --body \"Two files\" --attach \u002Fpath\u002Fto\u002Fa.pdf --attach \u002Fpath\u002Fto\u002Fb.xlsx\n```\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| `--to` | No | Recipient address (RFC822). Repeat for multiple. |\n| `--cc` | No | CC address. Repeat for multiple. |\n| `--bcc` | No | BCC address. Repeat for multiple. |\n| `--subject` | No | Subject line. |\n| `--body` | Yes (new) | Body content in markdown. Required for new drafts. |\n| `--edit` | No | Message ID of an existing draft to update. |\n| `--reply-to` | No | Message ID to reply to. |\n| `--forward` | No | Message ID to forward. |\n| `--account` | No | Account email to send from. Accepts a regular mail account, an alias, or a shared inbox email. |\n| `--attach` | No | Absolute path to a file to attach. Repeat for multiple. |\n\nUse `emails` to find message IDs for `--edit`, `--reply-to`, and `--forward`. Use `accounts` to find account emails for `--account` - both personal accounts and shared inboxes are listed there, and either can be used as the from address when the account has draft & comment access.\n\n### comment\n\n**Requires: triage** access level.\n\nPost a team comment (chat message) on a thread. If the thread is not yet shared, it will be shared automatically. Supports text comments, file attachments, or both. Use `--edit` to update an existing comment.\n\n```bash\nspark comment 1234 --body \"Looks good, let's proceed.\"\nspark comment 1234 --body \"Please review this\" --team \"Engineering\"\nspark comment 1234 --body \"FYI\" --team \"Engineering\" --user alice@co.com --user bob@co.com\nspark comment 1234 --attach \u002Fpath\u002Fto\u002Fscreenshot.png\nspark comment 1234 --body \"See attached\" --attach \u002Fpath\u002Fto\u002Freport.pdf --attach \u002Fpath\u002Fto\u002Fdata.csv\nspark comment --edit 5678 --body \"Updated comment text\"\n```\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| `\u003Cmessage-id>` | Yes (post) | Message ID of a message in the thread to comment on. |\n| `--body` | When no `--attach` | Comment text to post. Required when using `--edit`. |\n| `--attach` | When no `--body` | Absolute path to a file to attach. Repeat for multiple files. Each file is sent as a separate message. Cannot be used with `--edit`. |\n| `--edit` | No | Message ID of an existing comment to edit. Requires `--body`. |\n| `--team` | When >1 team | Team name. Required when you belong to multiple teams. |\n| `--user` | When team >2 members | Teammate email to share with. Repeat for multiple. Only used when auto-sharing an unshared thread. For teams with 2 or fewer members, the whole team is shared with automatically. |\n\nUse `emails` to find message IDs. Use `thread` to see comment IDs in a conversation. Use `team` to list teams and their members.\n\n### events\n\nList calendar events for a time range.\n\n```bash\nspark events                                          # today's remaining events\nspark events --tomorrow\nspark events --week\nspark events --week --in user@example.com             # specific account\nspark events --week --in user@example.com:Work        # specific calendar\nspark events --start 2026-03-16 --end 2026-03-20      # custom range\n```\n\nDate formats: `yyyy-MM-dd`, `dd\u002FMM\u002Fyyyy`, or `yyyy-MM-ddTHH:mm`.\n\nRun `accounts` to see available calendar accounts and calendar names.\n\n### availability\n\nFind free time slots. Without `--attendees`, shows the user's own availability. With `--attendees`, computes mutual free windows.\n\n```bash\nspark availability                                                        # today\nspark availability --tomorrow\nspark availability --week --attendees alice@co.com\nspark availability --start 2026-03-16 --end 2026-03-20 --attendees a@co.com,b@co.com\n```\n\nFree slots are within working hours (08:00-20:00), skip weekends, and ignore events marked \"free\".\n\n### contacts\n\nSearch contacts by name or email. Strict match first, then fuzzy fallback.\n\n```bash\nspark contacts \"john\"\nspark contacts \"example.com\"\n```\n\n### team\n\nShow team info - metadata, shared inboxes with members, full member list, assigned emails, assignment summary.\n\n```bash\nspark team                     # list available teams\nspark team \"Readdle\"           # specific team\n```\n\n### meetings\n\nList meeting transcripts with optional filters and pagination.\n\n```bash\nspark meetings\nspark meetings --filter \"newer_than:30d\"\nspark meetings --filter \"subject:standup\" --page-size 10\n```\n\nFilter operators: `subject:\u003Ctext>`, `before:yyyy\u002FMM\u002Fdd`, `after:yyyy\u002FMM\u002Fdd`, `newer_than:Xd`, `older_than:Xd`.\n\n### meeting\n\nRead a single meeting transcript's summary. Optionally include the full transcript and\u002For notes.\n\n```bash\nspark meeting 42                            # summary only\nspark meeting --transcript 42               # include transcript\nspark meeting --notes 42                    # include notes\nspark meeting --transcript --notes 42       # everything\n```\n\nUse `meetings` to find meeting IDs.\n\n### action\n\n**Requires: triage** access level.\n\nPerform an action on one or more emails. Supports standard email actions and team actions.\n\n```bash\nspark action \u003Caction-name> \u003Cmessage-id...> [options]\n```\n\nSupported actions:\n- `pin` - Pin the message to keep it at the top of the list\n- `unpin` - Remove the pin from the message\n- `mute` - Mute the thread to stop receiving notifications\n- `unmute` - Unmute a previously muted thread\n- `snooze` - Snooze the message until a specific date (requires `--date`)\n- `unsnooze` - Remove the snooze and return the message to the inbox\n- `changeReminder` - Set a follow-up reminder if no reply by the date (requires `--date`)\n- `clearReminder` - Remove the follow-up reminder from the message\n- `setAside` - Set the message aside for later review\n- `archive` - Archive the message, removing it from the inbox\n- `moveToInbox` - Move the message back to the inbox\n- `moveToTrash` - Move the message to trash\n- `moveToFolder` - Move the message to a specific folder (requires `--folder`)\n- `attachLabel` - Attach a Gmail or Spark Team label without removing other labels (requires `--folder`)\n- `detachLabel` - Remove a Gmail or Spark Team label from the message (requires `--folder`)\n- `markAsDone` - Mark the message as done\n- `markAsUndone` - Mark the message as not done\n- `markAsSeen` - Mark the message as read\n- `markAsUnseen` - Mark the message as unread\n- `markAsSpam` - Mark the message as spam\n- `markThreadAsPriority` - Mark the thread as priority\n- `unmarkThreadAsPriority` - Remove the priority mark from the thread\n- `unsubscribe` - Unsubscribe from the sender or mailing list\n- `changeCategoryPersonal` - Change the email category to Personal\n- `changeCategoryNotification` - Change the email category to Notification\n- `changeCategoryNewsletters` - Change the email category to Newsletter\n- `shareInTeam` - Share the thread with teammates (requires `--team` when multiple teams)\n- `assign` - Assign the email to a teammate (requires `--assignee`)\n- `delegationComplete` - Mark the delegation as complete\n- `delegationReopen` - Reopen a completed delegation\n\nOptions:\n- `--date` - required for `snooze` and `changeReminder`, optional for `assign` as due date (formats: `yyyy-MM-dd`, `dd\u002FMM\u002Fyyyy`, `yyyy-MM-ddTHH:mm`)\n- `--folder` - required for `moveToFolder`, `attachLabel`, and `detachLabel` (qualified name: `email@domain.com:FolderName`; use `folders` to list labels including shared inboxes)\n- `--team` - team name for team actions; required when you belong to multiple teams\n- `--user` - teammate email to share with for `shareInTeam`; repeat for multiple users; required when team has more than 2 members\n- `--assignee` - teammate email to assign the email to for `assign`\n- `--comment` - comment text for the `assign` action\n\n```bash\nspark action pin 12345                                          # pin a message\nspark action archive 100 200 300                                # archive multiple messages\nspark action markAsSeen 100 200                                 # mark as read\nspark action snooze 12345 --date 2026-04-10T09:00               # snooze until date\u002Ftime\nspark action snooze 12345 --date 2026-04-10                     # snooze until date\nspark action moveToFolder 12345 --folder \"user@example.com:Archive\"  # move to folder\nspark action attachLabel 12345 --folder \"user@gmail.com:MyLabel\"       # add Gmail\u002FTeam label\nspark action detachLabel 12345 --folder \"shared@company.com:SomeLabel\"  # remove label\nspark action changeReminder 12345 --date 2026-04-15             # set reminder\nspark action shareInTeam 1234 --team \"Engineering\" --user alice@co.com  # share with teammate\nspark action shareInTeam 1234 --user alice@co.com --user bob@co.com    # share with multiple\nspark action assign 1234 --assignee bob@co.com                  # assign to teammate\nspark action assign 1234 --assignee bob@co.com --date 2026-04-15 --comment \"Please review\"\nspark action delegationComplete 1234                            # mark delegation done\nspark action delegationComplete 100 200 300                     # complete multiple delegations\nspark action delegationReopen 1234                              # reopen delegation\n```\n\nUse the `emails` command to find message IDs. Use `folders` to resolve qualified names for `moveToFolder`, `attachLabel`, and `detachLabel`. Use `team` to list teams and members for team actions.\n\n### contact-action\n\n**Requires: triage** access level.\n\nPerform an action on one or more contacts by email address.\n\n```bash\nspark contact-action \u003Caction-name> \u003Cemail...>\n```\n\nSupported actions:\n\n| Action | Description |\n|--------|-------------|\n| `changeCategoryPersonal` | Change the contact's email category to Personal |\n| `changeCategoryNotification` | Change the contact's email category to Notification |\n| `changeCategoryNewsletters` | Change the contact's email category to Newsletter |\n| `groupEmailsFromContact` | Group emails from the contact by category |\n| `groupEmailsFromContactAndShowInInbox` | Group emails from the contact and show in inbox |\n| `ungroupEmailsFromContact` | Ungroup emails from the contact |\n| `markContactAsImportant` | Enable notifications for the contact |\n| `unmarkContactAsImportant` | Disable notifications for the contact |\n| `markContactAsPrimary` | Mark the contact as priority (auto-prioritize emails) |\n| `unmarkContactAsPrimary` | Remove priority mark from the contact |\n| `acceptContact` | Accept or unblock the contact (bypass Gatekeeper) |\n| `blockContact` | Block the contact |\n| `acceptDomain` | Accept or unblock the contact's entire domain |\n| `blockDomain` | Block the contact's entire domain |\n| `enableAutosummaryForContact` | Enable auto-summary for emails from the contact |\n| `disableAutosummaryForContact` | Disable auto-summary for emails from the contact |\n\nExamples:\n\n```bash\nspark contact-action blockContact spammer@example.com\nspark contact-action acceptContact alice@co.com bob@co.com\nspark contact-action changeCategoryPersonal alice@co.com\nspark contact-action markContactAsPrimary ceo@company.com\nspark contact-action enableAutosummaryForContact newsletter@example.com\n```\n\nUse the `contacts` command to look up email addresses.\n\n## Smart Categories\n\nSpark automatically classifies incoming email into six categories. Use the `category:` filter operator with `emails` and `search` to view mail by category, and use `action` \u002F `contact-action` to reclassify and tune.\n\n| Category | Filter | Typical Content |\n|----------|--------|-----------------|\n| Priority | `category:priority` | Auto-prioritized or manually marked as priority |\n| People | `category:personal` | Direct person-to-person email |\n| Notifications | `category:notification` | Service notifications, alerts, receipts |\n| Newsletters | `category:newsletter` | Subscriptions, digests, marketing |\n| Invites | `category:invitation` | Calendar invitations |\n| Invite Responses | `category:invitation_response` | RSVPs, accepts, declines |\n\n**Browse by category** (read-only):\n\n```bash\nspark emails Inbox --filter \"category:priority is:unread\"       # unread priority mail\nspark emails Inbox --filter \"category:personal is:unread\"       # unread people mail\nspark emails Inbox --filter \"category:invitation\"               # pending invites\nspark emails Inbox --filter \"category:notification is:unread\"   # unread notifications\nspark emails Inbox --filter \"category:newsletter newer_than:7d\" # recent newsletters\n```\n\n**Reclassify a message** (triage):\n\n```bash\nspark action changeCategoryPersonal \u003Cid>       # move to People\nspark action changeCategoryNotification \u003Cid>   # move to Notifications\nspark action changeCategoryNewsletters \u003Cid>    # move to Newsletters\n```\n\n**Tune per-contact category rules** (triage) - changes apply to all future mail from the sender:\n\n```bash\nspark contact-action changeCategoryPersonal sender@example.com         # reclassify as People\nspark contact-action changeCategoryNewsletters sender@example.com      # reclassify as Newsletters\nspark contact-action groupEmailsFromContact sender@example.com         # group by category\nspark contact-action markContactAsImportant vip@example.com            # enable notifications\nspark contact-action markContactAsPrimary ceo@example.com              # auto-prioritize\nspark contact-action enableAutosummaryForContact newsletter@example.com # AI summaries\n```\n\n**Category-first triage pattern:** Process inbox in priority order - priority first, then people, then invites, then notifications, then newsletters. This ensures the most important messages get attention first.\n\n## Typical Workflows\n\n**Answer a question about emails:**\n1. `spark search \"topic\"` - find relevant emails with bodies\n2. Read the output and answer the user's question\n\n**Find and read a specific email:**\n1. `spark emails --filter \"from:sender subject:keyword\"` - locate the email\n2. `spark thread \u003CID>` - read the full conversation\n\n**Draft a reply:**\n1. `spark emails --filter \"from:sender\"` - find the email\n2. `spark draft --reply-to \u003CID> --body \"Thanks for the update!\"`\n\n**Check someone's schedule for a meeting:**\n1. `spark availability --tomorrow --attendees alice@co.com,bob@co.com`\n2. Suggest a time from the free slots\n\n**Comment on a shared thread:**\n1. `spark emails --filter \"from:sender\"` - find the email\n2. `spark comment \u003CID> --body \"Looks good, approved!\"`\n\n**Get team workload overview:**\n1. `spark team \"Team Name\"` - see members and assigned emails\n\n**Look up a contact:**\n1. `spark contacts \"name or domain\"` - find their email address\n\n**Perform an action on emails:**\n1. `spark emails --filter \"from:sender\"` - find the email\n2. `spark action archive \u003CID>` - archive it (or pin, snooze, etc.)\n\n**Share an email with your team:**\n1. `spark emails --filter \"subject:keyword\"` - find the email\n2. `spark action shareInTeam \u003CID> --user alice@co.com` - share with a teammate\n\n**Delegate an email to a teammate:**\n1. `spark emails --filter \"subject:keyword\"` - find the email\n2. `spark action assign \u003CID> --assignee bob@co.com --date 2026-04-15 --comment \"Please handle this\"`\n\n**Mark delegated emails as done:**\n1. `spark emails --filter \"subject:keyword\"` - find the email(s)\n2. `spark action delegationComplete \u003CID1> \u003CID2>` - mark multiple as complete\n\n**Find unassigned shared inbox emails:**\n1. `spark emails shared@co.com:Inbox --filter \"assigned_to:unassigned\"` - list unassigned items\n2. `spark action assign \u003CID> --assignee bob@co.com` - assign to a teammate\n\n**Review what's assigned to a teammate:**\n1. `spark emails --filter \"assigned_to:bob@co.com\"` - see their assignments\n2. `spark emails --filter \"is:shared_inbox_open\"` - all open shared inbox items\n3. `spark emails --filter \"is:shared_inbox_done\"` - completed items\n\n**Manage a contact:**\n1. `spark contacts \"name or domain\"` - find the contact email\n2. `spark contact-action blockContact spammer@example.com` - block them (or accept, change category, etc.)\n\n## Keeping this skill up to date\n\nThe CLI and this skill share a single version (`metadata.version` in the front-matter above). New features in newer Spark Desktop releases ship with an updated embedded skill. Backward compatibility is guaranteed within a major version, so the commands and flags documented here keep working - but newly added features won't appear in this file until it is reinstalled.\n\nCheck for an update when - and only when - you hit one of these signals:\n\n- The user asks about a Spark feature, command, or flag that isn't documented here.\n- A `spark` command fails with an \"unknown command\" or \"unknown option\" error you didn't expect.\n- The user explicitly says they upgraded Spark or that the skill is out of date.\n\nIn those cases:\n\n```bash\nspark --version\n```\n\nIf the printed version is greater than `metadata.version` above, refresh this file before answering. `spark skill` prints SKILL.md to stdout - capture it and write it back over the file you're reading right now (the path is in your context). For example:\n\n```bash\nmkdir -p \u003Cparent-of-use-spark>\u002Fuse-spark\nspark skill > \u003Cparent-of-use-spark>\u002Fuse-spark\u002FSKILL.md\n```\n\n`\u003Cparent-of-use-spark>` is the directory containing the `use-spark\u002F` folder this `SKILL.md` lives in. If you have a file-write tool, you can also pipe `spark skill` output directly through it - the CLI itself does not write any files.\n\nDo not check on every session or before every command - this skill is the source of truth unless one of the signals above tells you otherwise.\n\n## Tips\n\n- Always quote multi-word arguments: `spark search \"project update\"`\n- Combine filter operators in a single `--filter` string: `--filter \"from:alice@co.com is:unread newer_than:7d\"`\n- Use `folders` to discover exact folder identifiers before passing them to `emails` or `search --in`\n- Use `accounts` to discover calendar names before passing them to `events --in`\n- The `search` command is best for topic-based queries; `emails` is best for browsing\u002Ffiltering by metadata\n- `thread` returns the full conversation - use it when you need the complete email text, not just metadata\n- Use `draft` to compose emails - it supports new drafts, replies, forwards, and editing existing drafts\n- Use `comment` to post team chat messages on threads - it auto-shares the thread if needed\n- Use `action` to perform email actions like pin, archive, snooze, move to folder, and more\n- Use `contact-action` to manage contacts - block, accept, change category, toggle auto-summary, and more",{"name":5,"metadata":24,"description":7},{"version":25,"requires":26},"1.1.0",{"bins":27},[28],"spark","main","e24b64bdac040ad169ed16b14853eff1b20cd726","skills_archive\u002Fuse-spark",0,"https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates","https:\u002F\u002Fgithub.com\u002FBumpyClock","2026-11-14 03:12:06",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add BumpyClock\u002Fagent-templates --skill use-spark",{"tool":42,"command":43},"bunx","bunx skills add BumpyClock\u002Fagent-templates --skill use-spark",{"tool":45,"command":46},"pnpm","pnpm dlx skills add BumpyClock\u002Fagent-templates --skill use-spark","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fuse-spark\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M79FEE6E257MWVEBY43X0NVN","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M79FEB8GTJC6ZHDK67T40R20","workflow-from-chats","Extract preferences from agent chats → skills, rules, workflow docs. For learning preferences, mining feedback, personalizing workflows.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fworkflow-from-chats\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M79FE7TMNGVZZ0M8NV4N0X6N","winui3-csharp-app","WinUI 3 \u002F Windows App SDK desktop apps in C#\u002FXAML. MVVM, bindings, navigation, Mica\u002FAcrylic, windowing, packaging, performance.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwinui3-csharp-app\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M79FE31HY46BHN67CQGB7MVJ","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M79FE0N7MGWDG8SCD60FWTV5","what-did-i-get-done","Summarize authored commits over a user-specified time period into a concise status update.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fwhat-did-i-get-done\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M79FDYBJG9QNCQC0MMVBDT80","weekly-review","Produce a short weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work.","https:\u002F\u002Fgithub.com\u002FBumpyClock\u002Fagent-templates\u002Fblob\u002Fmain\u002Fskills_archive\u002Fweekly-review\u002FSKILL.md",[],[]]