timeln-podcastlisted

# Timeln Podcast Turn **Timeln saves** into **one MP3** (Timeln Podcast). User listens; timeln-find is for reading. **Deliverable:** `{slug}.mp3` in the shell **working directory** when `render.sh` runs (default slug: `timeln-podcast-{YYYY-MM-DD}`). Report the absolute path in chat. **Requires shell** for `engine/setup.sh` and `render.sh` (not listed in `allowed-tools`). --- ## Setup (once) ```bash cd .agents/skills/thinking-os/timeln-podcast/engine && ./setup.sh ``` Needs: Python 3.11, espeak, ffmpeg. macOS: `brew install espeak`. --- ## Workflow (4 steps) ### 1 — Pull ``` whoami get_recent_docs(window="weekly") ``` - Default **lookup window:** 7 days (`weekly`). User may override (`monthly`, or stated range). - Filter noise, duplicates, corrupted ingests. Count saves → **N**. Optional: `query_knowledge` / `get_topic_entities` for connections. ### 2 — Connect (show file) **When N ≥ 5:** write a **show file** wherever the workspace implies (skill does not prescribe a path). Include: mermaid show bible, through-line, themed segments with bridges, graph bridge. Real saves only. **When N < 5 (thin week):** skip show file. Say so in the cold open. Go to step 3. ### 3 — Script (TTS) Write **TTS script** (workspace-implied path) as a **two-host NotebookLM-style conversation**. Template: `references/tts-script-template.md` — read it before drafting. **Format (non-negotiable):** - Every spoken line begins with `HOST_A:` or `HOST_B:`. - `HOST_A` = curious / reflec