菜单
Weekly entertainment refresh: pulls Trakt watch history, checks watchlist for releases, runs show + book recs, syncs Audible purchases. Triggers: 'entertainment sync', 'weekly entertainment', 'sync trakt audible recs', 'refresh entertainment'.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Fetch Trakt.tv watch history (shows, movies, ratings) for analysis and recommendation workflows. Use when the user asks for show recommendations, what to watch, wants to see their watch history, or wants suggestions based on their viewing habits.
Analyzes Baruch's viewing history and explicit ratings across netflix-history.csv, imdb-ratings.csv, and trakt-history.json to identify preferred genres, classify completed and abandoned shows, and rank unwatched titles by predicted interest. Generates targeted TV show recommendations with quality thresholds, searches for new releases, and tracks upcoming shows in watchlist.json. Use when Baruch asks for show recommendations, "что посмотреть", "что смотреть", or similar requests for what to watch next.
Back up new Audible audiobook purchases, decrypt to M4B, and append to books-library.csv. Use on "audible backup", "check new audiobooks", "sync audible library", or from weekly scheduled task.
Weekly fetch of recent comments on Baruch's YouTube channel; sends a per-video summary if new comments appear, silent otherwise. Triggers: 'check youtube comments', 'youtube comment check', 'fetch youtube comments', 'review channel comments'.
Checks tracked upcoming TV shows in watchlist.json and sends a Telegram notification message via MCP when any have been released. Use when running nightly release checks, monitoring streaming release dates, or checking whether new episodes or shows from a watchlist are now available to watch. Fires nightly via its own scheduled_tasks row (post-#404).
Recommend audiobooks based on Baruch's reading history and preferences. Analyzes reading patterns, filters unread titles by genre and rating, identifies series continuations, checks for new releases from favorite authors, and suggests similar authors or highly-rated unread titles from the Audible library JSON. Use when Baruch asks for book recommendations, "what to read next", wants something similar to a specific author, or asks about his unread queue.
| name | entertainment-sync |
| description | Weekly entertainment refresh: pulls Trakt watch history, checks watchlist for releases, runs show + book recs, syncs Audible purchases. Triggers: 'entertainment sync', 'weekly entertainment', 'sync trakt audible recs', 'refresh entertainment'. |
| cadence | 0 10 * * 0 |
| agentModel | claude-sonnet-4-6 |
| script | scripts/precheck-entertainment-sync.py |
Every step below is mandatory. Execute them in order. Do not skip, reorder, or abbreviate any step.
Run silently. Each inner skill handles its own surfacing. The wrapper adds no surfaces beyond cadence-cursor management.
Fire-time precheck (scripts/precheck-entertainment-sync.py) gates wake-ups by the weekly cadence cap. See references/cadence-rationale.md.
Run the in-container fetch script (routes through the OneCLI gateway, writes /workspace/group/trakt-history.json on success):
python3 /home/node/.claude/skills/tessl__trakt-watch-history/scripts/trakt-watch-history.py
Silent on success. Report on error (stdout {"error": ...} / non-zero exit) or total_shows: 0 (if sync hasn't run yet, skip silently).
If the script fails, surface its stdout/stderr verbatim via mcp__nanoclaw__send_message, then emit <internal>entertainment-sync exited step-1: fetch-fail</internal> as your final turn text and stop. Do NOT advance the cursor. Otherwise proceed to Step 2.
Invoke Skill(skill: "tessl__check-watchlist"). Inner skill notifies on released shows; silent otherwise.
If invocation fails, surface verbatim via mcp__nanoclaw__send_message, then emit <internal>entertainment-sync exited step-2: inner-skill-fail</internal> as your final turn text and stop. Do NOT advance the cursor. Otherwise proceed to Step 3.
Invoke Skill(skill: "tessl__recommend-shows"). Uses trakt-history.json from Step 1. Sends on good matches; silent otherwise.
If invocation fails, surface via mcp__nanoclaw__send_message, then emit <internal>entertainment-sync exited step-3: inner-skill-fail</internal> as your final turn text and stop. Otherwise proceed to Step 4.
Invoke Skill(skill: "tessl__audible-backup"). Inner skill reports new books or errors; silent otherwise.
If invocation fails, surface via mcp__nanoclaw__send_message, then emit <internal>entertainment-sync exited step-4: inner-skill-fail</internal> as your final turn text and stop. Otherwise proceed to Step 5.
Invoke Skill(skill: "tessl__recommend-books"). Sends on good matches; silent otherwise.
If invocation fails, surface via mcp__nanoclaw__send_message, then emit <internal>entertainment-sync exited step-5: inner-skill-fail</internal> as your final turn text and stop. Otherwise proceed to Step 6.
Reachable only if Steps 1-5 all succeeded. Run:
python3 /home/node/.claude/skills/tessl__entertainment-sync/scripts/stamp-cursor.py
Atomic-writes /workspace/group/state/entertainment-sync-cursor.json with {"schema_version": 1, "last_run": "<now UTC ISO Z>"}. Stdout: {"status": "stamped", "last_run": "<iso>", "cursor_path": "<path>"}. Proceed to Step 7.
Emit exactly one <internal> line so the post-fire silent-success watchdog can read task_run_logs.result directly. Either <internal>entertainment-sync ran <utc_date>: clean</internal> (no inner skill surfaced) or <internal>entertainment-sync ran <utc_date>: surfaced</internal> (at least one did). <utc_date> is today's UTC date in YYYY-MM-DD. The wrapper adds no user-facing output. Finish here.