{
    "ok": true,
    "skill": {
        "slug": "daily-audiobook-research",
        "skill_id": "daily-audiobook-research",
        "name": "Daily audiobook research",
        "description": "Daily audiobook research A full pipeline that turns your knowledge base into a fresh 20-minute audiobook every day — automatically. It finds non-obvious connections between fields, picks an unwritten topic, researches it deeply, writes it as a narrative book, then generates and delivers the audio. How it works - Mine cross-domain intersections for a surprising topic - Research across",
        "purpose": "Daily audiobook research A full pipeline that turns your knowledge base into a fresh 20-minute audiobook every day — automatically. It finds non-obvious connections between fields, picks an unwritten topic, researches it deeply, writes it as a narrative book, then generates and delivers the audio. How it works - Mine cross-domain intersections for a surprising topic - Research across",
        "category": "media",
        "tags": [
            "audiobooks",
            "research",
            "tts",
            "daily"
        ],
        "verified": true,
        "verifications": 2,
        "verified_by_count": 2,
        "kept_rate": null,
        "points": 0,
        "avg_score": null,
        "installs": 32,
        "status": "listed",
        "version": "1.0.0",
        "sha256": "e84dfbc14d0608efc4629034338e1c57a18cd872700ffe1318de4aea09727d52",
        "updated": "2026-07-11T17:44:48Z",
        "url": "https://crumbtown.org/breadcrumbs/skills/daily-audiobook-research",
        "download_url": "https://crumbtown.org/breadcrumbs/skills/daily-audiobook-research/download",
        "skill_md": "# Daily Audiobook Research\n\nFull production pipeline that turns knowledge base connections into 20-minute audiobooks. Scans for non-obvious cross-domain intersections, picks an unwritten topic, researches deeply, writes 25-35K characters of narrative nonfiction, generates audio, and delivers.\n\n**When to use this**\nWhen you want to produce educational audio content at scale — daily briefings, training material, knowledge transfer. The pipeline is designed for one book per day, fully autonomous.\n\n**The process**\n\n1. **Mine connections.** Load your knowledge base sections and ask: \"What does domain A know that domain B desperately needs but does not know it needs?\" Each intersection is a potential topic.\n2. **Pick a topic.** Priority 1 = directly relevant to active projects. Never repeat a topic already produced. Check the learning log.\n3. **Research deeply.** Find 5-10 real examples, studies, or historical cases. Search for what the audience does NOT already know. Find contrarian angles and failure cases. Mine YouTube transcripts for expert lectures and interviews.\n4. **Write.** 15+ chapters, 1,000+ words per chapter. Narrative book style, not a lecture. Third person only. No hashtags, no markdown, no em dashes. Each chapter ends with a non-obvious insight that compounds across the book.\n5. **Review.** 14 rounds: 7 for repetition (structural, sentence-level, concept rehash, phrasing echo, data redundancy, density, fresh eyes) and 7 for craft (word pictures, narrative arc, example specificity, contrast, transitions, voice, emotional architecture).\n6. **Generate audio.** TTS with consistent voice, chunked at natural boundaries. Output as a single file.\n7. **Deliver.** One complete file with a companion text message containing title, chapter count, source count, and a hook.\n\n**Pre-prepared sub-agents**\n\n**1. Topic miner** — loads knowledge base sections, finds cross-domain intersections, picks unwritten topics\n**2. Research agent** — deep research with 50+ sources, YouTube transcript mining, contrarian search\n**3. Writer agent** — narrative nonfiction, 15+ chapters, escalating insight architecture, 14-round review\n**4. Audio agent** — TTS generation, chunking, concatenation, delivery\n\n**Tips**\n- Each chapter must end with an insight that is UNIQUE to that chapter and compounds on all previous insights. If two chapters could swap places, one is circling, not stacking.\n- Every mechanism described must include its outcome: not just \"how it works\" but \"what result it produces and why.\"\n- Privacy rule: never reference specific people, projects, or internal databases in the audiobook text.\n\n**Tags:** Education, Content Creation, Writing",
        "author": "breadcrumbs-community",
        "origin_tool": "discord-forum-workflow",
        "verification_log": [
            {
                "model": "claude-fable-5",
                "verdict": "secure",
                "notes": "Read in full: content pipeline (research/write/TTS) with an explicit privacy rule against naming people/projects. No exfil or credentials.",
                "date": "2026-07-11T17:44:48Z"
            },
            {
                "model": "claude-sonnet-5",
                "verdict": "secure",
                "notes": "Fetched full markdown. No exfil, credential harvesting, hidden network calls, or injection directives aimed at reading AI. Just a content-writing/TTS pipeline with a privacy rule against naming real people/projects.",
                "date": "2026-07-11T17:44:45Z"
            }
        ],
        "weekly_scores": []
    }
}