Update to Tailwind

{
  "description": "Audit how a connected Pinterest account's boards are organized through Tailwind — naming consistency, stale boards, board list coverage, dead list entries, and publishing timeslots, with optional public group board benchmarks. Use when the user asks for a board audit or wants to review their board setup.",
  "included_files": [],
  "name": "tailwind-pinterest-board-audit",
  "skill_md_contents": "---\nname: tailwind-pinterest-board-audit\ndescription: Audit how a connected Pinterest account's boards are organized through Tailwind — naming consistency, stale boards, board list coverage, dead list entries, and publishing timeslots, with optional public group board benchmarks. Use when the user asks for a board audit or wants to review their board setup.\n---\n\n# Pinterest board organization audit\n\nThis audit reports on how an account's boards are **organized**: what they are\ncalled, which ones are covered by a board list, which list entries point at\nboards that no longer exist, and whether a publishing schedule is configured.\n\nIt is read-only and consumes no credits.\n\nIt says nothing about whether a board is *good*. Board quality, topical\nrelevance, and performance are not visible here, and inventing them from board\nnames is the failure mode this audit is written to prevent.\n\n## Gather the data\n\n1. `list_accounts` — resolve the account. Ask which one if there are several.\n2. `list_boards` — every board, with `isSecret`, `isCollaborator`, its\n   description when it has one, `followerCount`, `pinCount`, and\n   `pinsModifiedAt` when Pinterest has one.\n3. `list_board_lists` — the account's board lists and their ordered entries.\n4. `list_timeslots` — the configured publishing schedule.\n\nIf `list_board_lists` returns nothing, no board list on the account holds any\nboards. That is a valid setup, not a finding on its own — report it as context.\nDo not report it as \"no board lists configured\": a list that exists but holds\nno boards is invisible to this endpoint, so an empty result cannot tell the two\napart.\n\n## The checks\n\nEvery check below is mechanical. Compute it, report the count, and stop. None\nof them requires a judgement about whether a board is worth having.\n\n**Inventory.** Total boards, split by `isSecret` and `isCollaborator`. Secret\nboards are private to the user and collaborator boards belong to someone else —\nboth are worth separating out, because advice that applies to a user's own\npublic boards often does not apply to either.\n\n**Naming consistency.** Bucket board names by case convention — all lowercase,\nTitle Case, ALL CAPS, and anything else — and report the counts. A single\ndominant convention with a few outliers is worth naming; an even spread is\nworth reporting as \"no consistent convention\". Report the outliers by name so\nthe user can act.\n\n**Duplicate names.** Report exact duplicates, and names that differ only by\ncase or whitespace. These are genuinely confusing when picking a board to\npublish to, and they are unambiguous to detect.\n\n**Missing descriptions.** Boards with no description. `list_boards` leaves\nthe field out entirely for those boards, so a missing field is the finding.\nReport them by name.\n\n**Pin counts.** Boards with a `pinCount` of zero. The count comes from a\ncached snapshot and can lag behind Pinterest, so treat it as a lower bound:\nsay a board *may* be empty, not that it is.\n\n**Stale boards.** Boards whose `pinsModifiedAt` is more than 90 days before\ntoday. `pinsModifiedAt` is when Pinterest last recorded a change to the\nboard's Pins (ISO 8601; the text output shows it as \"Pins last changed\").\nIt is a last-activity date, not the date of the newest Pin: Pinterest does\nnot say which changes move it. Ninety days is a heuristic, not a Pinterest\nrule, so say so, and report each stale board by name with its date. A board\nwith no `pinsModifiedAt` has unknown activity: count those separately and\nnever report them as stale.\n\n**Board list coverage.** Boards present in `list_boards` but absent from every\nboard list. These are boards no grouping publishes to.\n\n**Dead list entries.** Board ids inside a board list that do not appear in\n`list_boards`. These point at boards that have been deleted or are no longer\non the account, and they are a known cause of failed Pins — a user cannot see\nthem from the Pinterest side, which is why this check earns its place.\n\n**Ordering.** Report each list's entries in `order`. Report it verbatim. There\nis no correct order to compare against.\n\n**Timeslots.** Total configured slots, and which days of the week have none.\nAn account with no timeslots at all has no recurring schedule to publish into,\nwhich is a real finding — but do not report it as being unable to schedule\nPins. Scheduling accepts an explicit time regardless of whether any slot\nexists. Days with no slots are context, not a defect.\n\n## Optional: public benchmark context\n\nOnly when the user supplies target keywords. Call `list_group_boards` with a\nkeyword and **check `status` before reporting anything**:\n\n- `ready` — report the boards. An empty list means a completed search genuinely\n  found no public group boards for that keyword. Say that.\n- `warming` — a search is running and nothing is cached yet. Tell the user to\n  check back. Do **not** report this as \"no group boards found\".\n- `unavailable` — the search failed. Say the benchmark is unavailable for that\n  keyword and continue with the rest of the audit.\n\nThese are **other people's public boards**, scraped from Pinterest. They are\ncontext for how boards in a niche are named and sized. They are not the user's\nboards, and their board ids cannot be used for scheduling.\n\nGroup boards are not Tailwind Communities. Communities (formerly Tribes) has no\nMCP tool. Tailwind is replacing it with Turbo Groups, which has no tool either;\nthe user finds their Turbo Groups under My Groups in Turbo, in the Tailwind app.\nA request for either one is a missing capability that `request_capability`\nrecords; Pinterest group boards (`list_group_boards`) are a different feature\nand do not answer it.\n\nThe benchmark is optional in the strict sense: the audit must be complete and\nuseful without it. If the scrape path returns nothing at any keyword, produce\nthe full API-only report and note that benchmark context was unavailable.\n\n## Report structure\n\n1. **Audit scope and data sources** — the account audited, and which of the two\n   sources below each section draws on.\n2. **Healthy checks** — what is in good shape.\n3. **Findings and recommended actions** — ordered by consequence. Dead list\n   entries and no-timeslots come before naming inconsistency.\n4. **Public benchmark context** — only when requested and available.\n5. **Not available in this audit** — the section below.\n\nLabel every claim with its source. Two labels are in play here and they are not\ninterchangeable:\n\n- **Tailwind account data** — the user's own boards, lists, and timeslots.\n- **Public scraped context** — group boards from `list_group_boards`.\n\nA reader must never have to guess whether a number describes their account or\nsomebody else's. Never merge counts from the two sources into one figure.\n\n## Not available in this audit\n\nSay these explicitly:\n\n- **When the last Pin was added.** `pinsModifiedAt` is the last recorded\n  change to a board's Pins, not the newest Pin's date, so \"your last Pin here\n  was on this date\" cannot be stated. The benchmark section describes other\n  people's boards and says nothing about the user's.\n- **Actual posting cadence.** Timeslots are the *configured* schedule, not\n  observed publishing history. A full slot list does not mean Pins went out.\n- **Board lists holding no boards.** `list_board_lists` only returns lists with\n  boards in them, so an empty list is indistinguishable from one that was never\n  created. Never state that an account has no board lists configured.\n- **Private boards of other accounts.** The scrape path sees public boards only.\n- **Board-to-keyword relevance.** This audit does not score it, and it must\n  not be inferred from board names. `get_board_keyword_relevance` scores one\n  board's live Pins against a keyword, but each scored call spends a plan\n  credit, so offer it for the boards the user cares about rather than running\n  it as part of the audit.\n- **Performance.** Saves, impressions and clicks are not part of this audit.\n  `list_top_pins` returns each top Pin's `boardId`, which is how to compare\n  boards by performance when the user asks; it costs nothing.\n\nWhen the user asks for one of these, name the gap and stop. Do not answer it\nwith a proxy — \"you have 40 boards and only 12 in a list, so your reach is\nprobably suffering\" is an invented conclusion, and it is the specific failure\nthis section exists to prevent.\n"
}