Fix Plaud integration: use official connector, resolve file_id via list_files

Root cause found: the web app's recording URL slug is missing the 'of_'
prefix the API's real file_id requires — direct lookup by URL id always
404'd regardless of which connector or account. Fixed by resolving the id
via list_files(query=...) instead. Also: stop using the deprecated
'Plaud MCP' connector entirely, use the official 'Plaud' connector only.

Verified live: pulled the 09-16 meeting transcript for real via the
official connector, content matches the manually-uploaded transcript used
to build the first brief. Recap mode's live data path is now confirmed
working end-to-end, not just designed.

skills/internal-meeting-brief/SKILL.md

@@ -19,7 +19,16 @@ contract for what this skill's output actually contains.
 
 This skill uses, but does not own, the following connected tools — confirm they're
 reachable before starting, and degrade gracefully (see Hard Rules) if one isn't:
-- **Plaud** — meeting transcripts (recap: current meeting; agenda: previous meeting)
+- **Plaud** — meeting transcripts (recap: current meeting; agenda: previous meeting).
+  Use the official `Plaud` connector (`get_current_user`, `list_files`, `get_file`,
+  `get_transcript`, `get_note`) — **not** the older `Plaud MCP` connector, which
+  predates Plaud's own official one and should be treated as deprecated. Resolve a
+  recording's `file_id` via `list_files` (filter by `query`/`date_from`/`date_to`) —
+  never assume a Plaud web-app URL's slug is the API `file_id` directly; the API id
+  carries an `of_` prefix the web URL does not show. `get_transcript` paginates
+  (`next_cursor`) — loop until it's null before treating the transcript as complete.
+  `get_note` returns the AI summary/action items tab separately from the raw
+  transcript — worth pulling alongside `get_transcript`, not instead of it.
 - **Odoo** (MCP) — linked Project/tasks, Sales/Purchase Orders, Knowledge Base,
   Helpdesk tickets
 - **Google Workspace** (MCP) — Gmail, Google Chat, Drive, Sheets
@@ -122,15 +131,23 @@ person needs to actually see and review it, not just trust it happened.
   separate, deliberately not built yet. Don't attempt to stand up delivery
   infrastructure as part of running this skill.
 
-## Known limitation (open as of 2026-09-21)
+## Resolved limitation (was open 2026-09-21, fixed 2026-09-22)
 
-The Plaud MCP connector has failed on every attempt so far — first appeared to be an
-account/workspace mismatch, but a later attempt timed out with a message indicating it
-runs as a **local server via the Claude Desktop app**, not a cloud connector. Confirmed
-still broken after Bryan verified the connector's own settings looked correct. Treat
-Plaud as unreliable until this is resolved — the one real brief produced so far
-(2026-09-16 APTA meeting) used a manually uploaded transcript as a workaround, not a
-live pull. Don't assume this is fixed without testing it again.
+Earlier attempts to pull this skill's first real test recording failed for two
+compounding reasons, now both understood:
+1. The deprecated `Plaud MCP` connector's `list`/`search` tools returned empty results
+   or timed out regardless of parameters — root cause not fully diagnosed, but moot:
+   don't use that connector at all (see Prerequisites above).
+2. Direct lookup via the *official* `Plaud` connector's `get_file`/`get_transcript`
+   still 404'd, because the id taken from the Plaud web app's URL
+   (`b0df60b679f31383f770d91db6b5bf46`) was missing the `of_` prefix the API's real
+   `file_id` requires (`of_b0df60b679f31383f770d91db6b5bf46`). Resolving the id via
+   `list_files(query=...)` instead of reading it off a URL fixed this immediately.
+
+Verified 2026-09-22: a live pull via the official connector for this same recording
+returned content matching the manually-uploaded transcript used to build the first
+real brief, confirming both that the fix works and that the original brief's content
+was accurate. Recap mode's live data path is now confirmed working end-to-end.
 
 ## Provenance