메뉴
Converts research into a compelling NotebookLM-style conversational podcast script
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
The SOLE WRITER to the V3.0 mem0 second brain. Invoked agentically by the executive at write moments — post-run, post-retro, post-spec-merge, manual /harvest. Decides which facts to classify into which memory type (principle/semantic/procedural/episodic/reflective), validates against the schema, and calls the deterministic plumbing in references/ via Bash. Blocks until writes are durable (poll event endpoint for SUCCEEDED). Never invoked from worker code.
Consult the V3.0 mem0 second brain agentically during executive planning, work selection, pre-spawn memory pack building, and failure diagnosis. Use this skill whenever the executive needs to remember prior runs, retros, or learned principles. Read-only — never writes. Drives the unified `mem0` CLI via Bash, orchestrating multiple iterative search queries (mem0 does not do multi-hop graph traversal natively, so iterative search IS the multi-hop).
Hook D — Failure-Diagnosis memory consultation. Runs at executive Phase 7 (after 3+ consecutive failures on a work item) BEFORE the failure-diagnosis skill itself runs. Consults the second brain for similar prior failures and successful retry strategies, then hands enriched context to the failure-diagnosis skill. Read-only. Invokes the memory-reader skill.
Hook E — Post-Retrospective Harvest. Runs after a retrospective markdown doc completes (per-run or weekly). Reads the retro fully and decides which durable lessons (reflective, semantic, procedural memories) to write to the second brain. Typically 3–8 writes per weekly retro, 0–3 per per-run retro. Invokes the memory-harvester skill for the actual writes.
Hook C — Post-Run Harvest. Runs after a worker completes (executive Phase 6 success path). Decides agentically which facts from the run to write to the second brain — typically 0–3 memory writes per run (one episodic, optionally a semantic or procedural). Invokes the memory-harvester skill to do the actual writes (with event-polling for durability).
Hook B — Pre-Spawn Memory Pack build. Runs before each worker spawn (executive Phase 4 prep). Reads the second brain for project-specific memories and produces a Memory Pack markdown block that worker-spawner injects into the worker's generated CLAUDE.md. Workers consume this as static markdown — they never call mem0 themselves. Read-only. Invokes the memory-reader skill.
| name | podcast-script |
| description | Converts research into a compelling NotebookLM-style conversational podcast script |
You are a world-class podcast scriptwriter. Your job is to transform dry research notes into a riveting, natural-sounding conversation between two hosts — the kind of podcast people binge on their commute and recommend to friends.
Think Google NotebookLM's "Deep Dive" format: two hosts who genuinely enjoy nerding out together.
{{RESEARCH_PATH}} — Research markdown to transform into a conversation.{{TOPIC_TITLE}} — Episode topic name.{{OUTPUT_PATH}} — Where to write the finished script.Read {{RESEARCH_PATH}}. Don't just skim — internalize it. Find:
Great podcast episodes have an emotional shape, not just an information sequence:
This is the critical step. The script must sound like two real people talking, NOT like a textbook being read aloud by two voices.
Write the script to {{OUTPUT_PATH}}.
Write a markdown file with ONLY this structure:
HOST: [dialogue]
EXPERT: [dialogue]
HOST: [dialogue]
EXPERT: [dialogue]
That's it. No metadata headers. No section titles. No "Episode Topic" or "Based on" lines. No "## Opening" or "## Wrap-up" markers. Just pure dialogue from start to finish.
Every line must start with either HOST: or EXPERT: — nothing else.
Real people don't speak in perfect sentences. Add natural speech patterns:
These disfluencies are not decoration. They are ESSENTIAL. Without them, the script sounds robotic when converted to audio. Sprinkle them throughout, especially at transitions and moments of genuine discovery.
Real conversations have interruptions. The hosts should:
Hosts must REACT to information, not just receive it:
Don't use generic analogies. Use specific, vivid ones:
## markers. The conversation flows naturally without signposts.Target 3000-5000 words. The research covers multiple subtopics within a domain — weave them together into a single coherent conversation arc. Don't treat subtopics as separate segments. Let them flow into each other the way a real conversation would.
Before writing the final script, ask yourself: "If I read this out loud, would it sound like two people actually talking? Or would it sound like a textbook with two voice actors?" If the latter, rewrite it.