io.github.linkedmash/linkedmash

Add a label to a FEW explicitly chosen posts (specific post_ids the user picked or is looking at). Either label_id or label_name must be provided. NEVER use this to label 'all posts matching a filter' (a date range, an author, a tag, unread…) — fetched lists are ONE PAGE, so labeling their ids silently misses the rest; use tag_bookmarks_by_filter instead, which labels EVERY match server-side in one call and returns matched/tagged counts.

ARCHIVE all bookmarks matching a filter in ONE server-side call (reversible — archived posts stay recoverable in the app's Archive). Use for 'archive all posts <filter>' style requests, even phrased as 'fetch then archive'. BEFORE calling: tell the user what will be archived (use get_bookmark_count with the same filter) and get an explicit yes — then call with confirm=true. Returns matched/affected counts: ALWAYS report them; if 'truncated' is true, say it stopped at the cap.

Cancel a scheduled post by its schedule id (from a get_queue entry). Requires a paid Creator/Lifetime plan.

Create a new LinkedIn post draft in the user's Content Studio. Put the post body text in 'content'. Returns the created draft (with its id) which can later be scheduled or published. Requires a paid Creator/Lifetime plan.

Create a smart folder (filtered view) — a saved filter/workflow over the user's saved posts. 'name' is required; 'base_query' is the filter query that defines which posts belong; 'triage_buckets' are optional tabs/stages inside the folder. Returns the created folder (with its slug).

DELETE all bookmarks matching a filter in ONE server-side call. Deletion is soft (recoverable from the app for a while) but MUST be treated as destructive: BEFORE calling, tell the user exactly what will be deleted (use get_bookmark_count with the same filter to state the number) and get an explicit yes in this conversation — only then call with confirm=true. NEVER delete on your own initiative. Returns matched/affected counts: ALWAYS report them; if 'truncated' is true, say it stopped at the cap and offer to run again with a narrower filter.

Delete (move to trash) a Content Studio draft by its id. Requires a paid Creator/Lifetime plan.

Delete a smart folder (filtered view) by its slug. This removes the saved filter/workflow itself — it does NOT delete any saved posts. Use list_smart_folders to find the slug.

Delete a durable user memory by its 'key' (optionally scoped to a 'kind'). Use this when the user asks you to forget something you remembered about them, or to correct an outdated preference/fact before re-adding it with remember.

Get the user's account-level LinkedIn analytics — impressions, reactions, comments, reshares, members reached and follower growth — over a time window (date_range like '7d', '30d', '90d'). Requires a paid Creator/Lifetime plan.

Get a single saved LinkedIn post (bookmark) by its post_id — full content, author, media and tags. Use this to read one specific saved post, e.g. before creating content based on it.

Get the count of bookmarks matching the given filters. Supports the SAME filters as list_bookmarks (dates, author, tag, media_type, unread, q, comment) and the count respects all of them, so it is always consistent with a list_bookmarks call using identical filters. Defaults match list_bookmarks: read + unread included, archived excluded. The result echoes applied_filters — check it matches what the user asked before reporting the number.

Get a single Content Studio post/draft by its id. Requires a paid Creator/Lifetime plan.

Get the user's GROWTH DIGEST — their positioning, content pillars, authority gaps, ranked what-to-do-next actions (with ready-to-use draft prompts), and this week's numbers (new saves, posts published). USE THIS whenever the user asks what they should post/do next, wants a growth plan or weekly review, or asks how to build authority — then walk them through the top next steps. Requires a paid Creator/Lifetime plan.

Get per-post LinkedIn analytics for the user's recently published posts (impressions, engagements, likes, comments, etc.) over a time window. Requires a paid Creator/Lifetime plan.

Get the user's recurring posting schedule — the weekly time-slot grid and timezone that drive 'next-slot' scheduling. Requires a paid Creator/Lifetime plan.

Get the next free posting slots from the user's recurring posting schedule (in their timezone). Use a returned slot's timestamp as publish_at when scheduling. Requires a paid Creator/Lifetime plan.

List the user's posting queue — scheduled and published LinkedIn posts, grouped by date. Optionally filter by status. Each entry includes its schedule id (use it to cancel/reschedule). Requires a paid Creator/Lifetime plan.

Get one smart folder (filtered view) by its slug — its name, description, filter query (base_query) and tabs (triage buckets). Use list_smart_folders first to find the slug. To read the posts inside, use get_smart_folder_posts.

List the saved LinkedIn posts inside a smart folder (filtered view). Pass the folder's slug (from list_smart_folders). Optionally pass 'bucket' to return only one tab/stage (triage bucket) of the folder; omit it for all posts in the folder. Paginate with 'cursor' (a numeric offset) and 'limit'.

List bookmarks with optional filtering and pagination. Defaults: read AND unread bookmarks are both included (set is_unread_only=true only if the user asks for unread); archived bookmarks are excluded (set hide_archived=false to include them). Only apply the filters the user actually asked for — do NOT add media_type, unread, or date filters unprompted. IMPORTANT: Use this tool (with the 'author' parameter) when the user asks to show posts by a specific author, find posts from someone, or filter by author name. The 'author' parameter supports fuzzy matching of author names.

List the user's Content Studio posts (drafts, scheduled and published LinkedIn posts they are authoring). Optionally filter by status. Requires a paid Creator/Lifetime plan.

List all user's labels/tags

List the user's smart folders (a.k.a. filtered views / triage views). A smart folder is a saved filter/workflow over their saved posts, optionally split into tabs (triage buckets/stages). Returns each folder's slug (use it with the other smart-folder tools), name, description, filter query and tabs.

Retrieve what you durably remember about the user (preferences, writing voice/style, facts, standing instructions) across conversations. Optionally pass a free-text 'query' to narrow the results; omit it to get the full memory digest. Use this when you need to recall the user's preferences or voice before answering or drafting.

Persist a DURABLE fact, preference, writing-style trait, or standing instruction about the user so it is remembered in FUTURE conversations (not just this one). Use this when the user states a lasting preference or instruction (e.g. 'always keep replies short', 'I write for early-stage founders', 'my timezone is IST', 'use a punchy tone'). kind = preference|style|fact|instruction; key = a short stable slug (reusing a key overwrites it); value = a concise phrase. Do NOT store secrets, passwords, tokens, payment details, or sensitive personal data. Optional mode: 'append' grows an existing note instead of overwriting. If a write is REFUSED (e.g. it would overwrite something the user set themselves, which takes precedence), you'll get an error explaining why — tell the user rather than retrying.

Remove labels from bookmarked posts. Either label_id or label_name must be provided.

REMOVE a label from ALL bookmarks matching a filter in ONE server-side call — the mirror of tag_bookmarks_by_filter. Use this — NOT list/search + remove_labels on page ids — whenever the user asks to remove/clear a label from many posts by date range, author, tag, media type, or unread status (even phrased as 'fetch all X and remove the label'). Provide label_name or label_id; matching is automatically scoped to posts that carry the label. Returns matched/removed/failed counts: ALWAYS report them ('Removed from X of Y matching posts'); if 'truncated' is true, say it stopped at the cap.

Schedule a Content Studio draft to publish to LinkedIn, or publish it immediately. Set publish_at to 'now' (publish right away), 'next-slot' (the next free slot in the user's posting schedule), or an ISO-8601 timestamp. A timezone (IANA, e.g. 'America/New_York') is required unless publish_at is 'now'. Requires a paid Creator/Lifetime plan.

Search through a user's LinkedIn bookmarks using either keyword (text) search or semantic (meaning-based) search. Supports all list_bookmarks filters, full-text search via the q field, and semantic search via the vector_search_term field for natural language or topic-based queries. IMPORTANT: At least one of 'q', 'vector_search_term', or 'author' must be provided. If the user asks to find posts by a specific author (e.g., 'Show posts by John Doe', 'Find posts from Suresh sambantham'), use the 'author' parameter instead of putting the author name in the 'q' field. Use 'q' for searching post content, not for filtering by author.

Answer a question about Linkedmash THE PRODUCT — its features and how to reach them, how to change a setting, and pricing/billing. Use this for questions like 'where do I manage my subscription', 'how do I schedule a post', 'how much is the Creator plan', 'how do I change Lina's writing rules', 'how do I import my LinkedIn saves', 'what does Smart Folders do'. It returns the most relevant sections of the Linkedmash help guide — answer the user in your own words from them and point them to the exact page (e.g. Settings → Billing). For live prices, direct the user to the pricing page (/pricing). This tool reads product documentation only, NOT the user's saved posts or account data.

Replace the user's recurring posting schedule (weekly time-slot grid + timezone). 'grid' is an array of slots like { time: '8:30 am', days: { Mon: true, Wed: true } }. These slots drive 'next-slot' scheduling. Requires a paid Creator/Lifetime plan.

Initialize the vector store for semantic search. CRITICAL: When vector/semantic search fails with 'Vector Store Not Setup' error and you offered the user options to either initialize or use keyword search, and the user responds with 'first', 'option 1', 'yes', 'initialize', 'set it up', 'init', 'setup', 'go ahead' or similar confirmation, you MUST immediately call this tool. ALWAYS check your previous message in the chat history to confirm the user is responding to your options. Do NOT re-run the search tool - just call this tool. After calling this tool, inform the user that setup has started and may take a few minutes. This is an async operation that may take a few minutes to complete for large bookmark collections.

Add a label to ALL bookmarks matching a filter in ONE server-side call. Use this — NOT list_bookmarks/search_bookmarks followed by add_labels — whenever the user asks to tag/label many posts by date range, author, tag, media type, or unread status (e.g. 'tag all posts older than March 2026 as Archive', 'label everything from John Doe as Hiring'). Date targeting: 'older than'/'before' DATE -> posted_to (or bookmarked_to); 'since'/'after' DATE -> posted_from (or bookmarked_from); use posted_* for when the post was published and bookmarked_* for when the user saved it; dates are ISO (YYYY-MM-DD). Provide label_name (created if it doesn't exist) or label_id. The tool returns matched/tagged/failed counts: ALWAYS tell the user how many posts were tagged; if 'truncated' is true, tell them it stopped at the cap and to narrow the date range to tag the rest; if 'failed' > 0, mention it. Never paginate or loop add_labels for bulk tagging — this one call handles the whole set.

Start exporting the user's saved LinkedIn posts to a CSV (spreadsheet) file. Use this when the user asks to export/download their saved posts as CSV or to a spreadsheet. By default it exports the WHOLE library; to scope it, pass post_ids for a specific selection, or a filter (search_query, filter+value e.g. author/label/type, tags, or author). This records the export — it does NOT return the file. ALWAYS tell the user the export has started and to open the Export Center link (returned in the message) to view and download it.

Start exporting the user's saved LinkedIn posts to a JSON file (a structured backup). Use this when the user asks to export/download/back up their saved posts as JSON. By default it exports the WHOLE library; to scope it, pass post_ids for a specific selection, or a filter (search_query, filter+value e.g. author/label/type, tags, or author). This records the export — it does NOT return the file. ALWAYS tell the user the export has started and to open the Export Center link (returned in the message) to view and download it.

Start exporting the user's saved LinkedIn posts to PDF. Use this when the user asks to export/download/back up their saved posts as a PDF (e.g. 'export all my saved posts to PDF', 'give me a PDF of my saved AI posts'). By default it exports the WHOLE library; to scope it, pass post_ids for a specific selection, or a filter (search_query for a keyword, filter+value e.g. author/label/type, tags, or author). This kicks off an async job — it does NOT return the file. ALWAYS tell the user the export has started and to open the Export Center link (returned in the message) to view and download it once ready; large exports can take up to a minute.

Update a Content Studio draft by id (partial — provide only the fields to change; 'content' is required for non-trash updates). Requires a paid Creator/Lifetime plan.

Update a smart folder (filtered view) by its slug. Provide only the fields to change: 'name', 'description', 'base_query' (the filter query), and/or 'triage_buckets' (the tabs/stages). Use list_smart_folders to find the slug.

Host an image, video, or PDF and get back a public URL to attach to a post (use the returned url as media_url, with the matching post_type). Provide a remote 'url' to re-host (recommended — the asset then stays available until a scheduled publish), or 'file_base64' (+ file_name) for raw bytes. Requires a paid Creator/Lifetime plan.