read-podcast-script-generator
starsforks
How to install read-podcast-script-generator?
spacezephyr/read-buddy/read-podcast-script-generator
$npx -y skills add SpaceZephyr/read-buddy --skill read-podcast-script-generatorTransform structured podcast notes into engaging video scripts with a conversational, first-person broadcasting style. Use when user asks to "generate podcast script", "convert to broadcast style", "make video script", "rewrite for video", "口播脚本", "改成口播", or wants to turn podcast
SKILL.md
| 1 | # Podcast Script Generator |
| 2 | |
| 3 | Transform structured podcast notes into engaging, presenter-style video scripts. |
| 4 | |
| 5 | ## When to Use |
| 6 | |
| 7 | Use this skill when the user wants to: |
| 8 | - Convert structured notes into presenter-style video scripts |
| 9 | - Rewrite podcast summaries for short video content |
| 10 | - Create conversational broadcast content from formal notes |
| 11 | - Generate scripts with strong personal voice and recommendations |
| 12 | |
| 13 | ## Workflow |
| 14 | |
| 15 | ### Step 1: Get Source Material |
| 16 | |
| 17 | Ask the user for the content source: |
| 18 | |
| 19 | 1. **Direct paste**: User pastes text directly |
| 20 | 2. **Daily podcast file**: File from `/Users/ugreen/Documents/obsidian/每日播客/` |
| 21 | 3. **Other file path**: Any other markdown file |
| 22 | |
| 23 | If user provides a file path, read it with Read tool. |
| 24 | |
| 25 | ### Step 2: Analyze Content Structure |
| 26 | |
| 27 | Identify: |
| 28 | - **Title & Guest**: Podcast name and main speaker |
| 29 | - **Core Theme**: Main topic discussed |
| 30 | - **Key Points**: Numbered list of insights (usually 3-12 points) |
| 31 | - **Highlights**: Dialogue excerpts or quotes |
| 32 | - **Data/Examples**: Statistics, case studies, comparisons |
| 33 | |
| 34 | ### Step 3: Apply Broadcasting Style |
| 35 | |
| 36 | Read `references/style-reference.md` and `references/example-conversions.md` to internalize the target style. |
| 37 | |
| 38 | #### Opening (Varied, Natural) |
| 39 | |
| 40 | **Avoid the fixed template.** Instead, choose from these natural openings based on content: |
| 41 | |
| 42 | - "今天要给你推荐一期播客..." |
| 43 | - "最近听到一期特别有意思的节目..." |
| 44 | - "这期是我最近听到的对[领域]非共识观点最多的一期..." |
| 45 | - "这个月听到的最有收获的一期播客..." |
| 46 | - "如果你关注[话题]，这期播客你一定要听..." |
| 47 | |
| 48 | Then introduce the guest naturally: |
| 49 | - "嘉宾是[名字]，[一句话身份]..." |
| 50 | - "介绍一下[名字]，[成就/背景]..." |
| 51 | |
| 52 | Add a hook specific to the content: |
| 53 | - "她几个月前演讲说'不要相信设计流程'，3个月后自己就觉得过时了..." |
| 54 | - "他可能是华尔街唯一一个既能看懂财务报表，又能看懂火箭发动机的人..." |
| 55 | |
| 56 | #### Content Transformation Rules |
| 57 | |
| 58 | **Rule 1: No "发言人" markers** |
| 59 | |
| 60 | - Direct output without speaker labels |
| 61 | - Use paragraph breaks to indicate natural pauses |
| 62 | |
| 63 | **Rule 2: Banned sentence patterns** |
| 64 | |
| 65 | DO NOT use these rigid contrasting patterns: |
| 66 | - ❌ "不是...而是..." |
| 67 | - ❌ "是...不是..." |
| 68 | - ❌ "被...倒逼着..." |
| 69 | - ❌ "从...变成...，从...变成..." (overly structured parallel) |
| 70 | |
| 71 | Instead, express contrast naturally: |
| 72 | - ✅ "设计不是主动想变，是工程端的变化逼着你必须变" |
| 73 | - ✅ "以前大家把这套流程当真理，但现在基本已经死了" |
| 74 | - ✅ "工程师已经转向命令行和agent模式，而设计师开始用IDE了" |
| 75 | |
| 76 | **Rule 3: Use conversational connectors SPARINGLY** |
| 77 | |
| 78 | Limit these phrases (max 1-2 per section): |
| 79 | - "说白了" → use "意思是" or just omit |
| 80 | - "这什么意思呢" → use "为什么？" or just explain directly |
| 81 | - "所以你看" → use "结果就是" or just show the result |
| 82 | |
| 83 | **Rule 4: Natural transitions** |
| 84 | |
| 85 | Instead of rigid structure markers, use: |
| 86 | - "第一个让我意外的点是..." |
| 87 | - "还有一个特别反直觉的发现..." |
| 88 | - "这里有个特别有意思的地方..." |
| 89 | - "更夸张的是..." |
| 90 | - "说到这个，就不得不提..." |
| 91 | |
| 92 | **Rule 5: Personal commentary** |
| 93 | |
| 94 | Insert reactions naturally: |
| 95 | - "我觉得这个点特别值得思考" |
| 96 | - "特别反直觉" |
| 97 | - "特别有意思" |
| 98 | - "让我特别意外" |
| 99 | |
| 100 | **Rule 6: Explain concepts conversationally** |
| 101 | |
| 102 | When explaining complex ideas: |
| 103 | - Start with the problem or context |
| 104 | - Walk through the logic step by step |
| 105 | - Use "打个比方" for analogies when needed |
| 106 | - End with "就是说" or just the conclusion |
| 107 | |
| 108 | #### Closing |
| 109 | |
| 110 | End naturally: |
| 111 | - "好了，今天就聊到这..." |
| 112 | - "今天就分享到这里..." |
| 113 | - "今天就聊到这，如果你也[相关话题]，强烈建议去听听完整播客..." |
| 114 | - "我是[昵称]，下次见" |
| 115 | |
| 116 | ### Step 4: Output Format |
| 117 | |
| 118 | Produce: |
| 119 | |
| 120 | 1. **Full script** without speaker markers, with natural paragraph breaks |
| 121 | 2. **Estimated duration** (250 words ≈ 1 minute) |
| 122 | 3. **3-5 suggested titles** for the video |
| 123 | 4. **Recommended hashtags/topics** |
| 124 | |
| 125 | ## Style Guidelines |
| 126 | |
| 127 | ### Paragraph Structure |
| 128 | - Each paragraph: 2-4 short sentences |
| 129 | - Use empty lines between paragraphs for pacing |
| 130 | - One idea per paragraph |
| 131 | - Key data/quotes can stand alone |
| 132 | |
| 133 | ### Tone |
| 134 | - Conversational, like talking to a friend |
| 135 | - First person "我" perspective |
| 136 | - Natural enthusiasm without exaggeration |
| 137 | - Occasional rhetorical questions |
| 138 | |
| 139 | ### Language |
| 140 | - Avoid written-style transitions |
| 141 | - Prefer short sentences |
| 142 | - Use spoken Chinese patterns |
| 143 | - Keep technical terms but explain them naturally |
| 144 | |
| 145 | ## Reference Materials |
| 146 | |
| 147 | - `references/style-reference.md` - Full example of target style |
| 148 | - `references/example-conversions.md` - Before/after conversion examples with techniques |
| 149 | |
| 150 | ## Constraints |
| 151 | |
| 152 | 1. Preserve all factual information - change style, not substance |
| 153 | 2. Maintain accuracy of data, quotes, and attributions |
| 154 | 3. Target length: 750-1500 words (3-6 minutes of video) |
| 155 | 4. If source is too long, ask user which points to prioritize |
| 156 | 5. NO "发言人" markers |
| 157 | 6. NO rigid "不是...而是" patterns |
| 158 | 7. Use "说白了" max 1-2 times in entire script |
People who liked this also viewed
6 picksType
- ai-video-generationinference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agentsSkillsJul 2026
- imagegen-frontend-webElite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing pageSkillsJul 2026
- hyperframes-mediaWrite HTML. Render video. Built for agents.SkillsJul 2026
- media-useAgent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + leSkillsJul 2026
- general-videoAuthor or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, staticSkillsJul 2026
- product-launch-videoTurn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos, app and company launches. Use when the user wants to market,SkillsJul 2026
