Interview Outline
Generate podcast interview outlines for 破壁圆桌 from guest information and web research. Produces a guest profile, themed interview questions, and opening script — all in a casual, specific, human voice. Use when the user wants to prepare an interview, 采访大纲, 采访提纲, 播客准备, or 嘉宾调研.
Install
npx skills add fanyu-meng/podcast-content-studio --skill interview-outlinegit clone --depth 1 https://github.com/fanyu-meng/podcast-content-studio.git /tmp/podcast-content-studio
mkdir -p ~/.claude/skills
cp -r /tmp/podcast-content-studio/.agents/skills/interview-outline ~/.claude/skills/interview-outlinePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Podcast Interview Outline Generator
## Input
Guest information provided by the user: name, role, links, and a rough interview direction.
## Workflow
### Step 1: Collect guest information — Round 1
Ask the user the following 4 questions using AskQuestion (or conversationally). Present them together in one round.
**Q1: Guest name**
> "嘉宾的名字是什么?(中英文都写上,如果有的话)"
Free text input.
**Q2: Current identity**
> "用一句话描述嘉宾现在在做什么?"
Free text input.
**Q3: How you met**
> "你们是怎么认识/找到这个嘉宾的?"
Options:
- 嘉宾主动找上门的
- 朋友/听众推荐的
- 我们自己找到并邀请的
- 社交媒体上认识的
- 其他(自定义输入)
**Q4: Rough direction**
> "这次采访你最想聊的方向是什么?(可以很模糊,比如'聊聊她的创业经历')"
Free text input.
### Step 2: Collect guest information — Round 2
Ask the user for reference materials. All fields are optional but encourage filling in as many as possible:
> "请提供嘉宾的相关链接和资料,越多越好——我会用这些来做调研,写出更有针对性的问题。没有的就跳过。"
- 个人网站 URL
- LinkedIn URL
- 社交媒体账号(小红书/Twitter/微博/Instagram 等)
- 过往采访/播客/YouTube 链接(可多个)
- 其他补充信息(如嘉宾发来的自我介绍、简历、作品集等)
If the user has files (PDF, text, etc.) with guest information, read them.
### Step 3: Web research
Conduct automated research using WebSearch and WebFetch.
#### 3a: Search queries
Run at least 3 searches, adapting keywords to the guest's field:
1. `"{guest_name_cn}" 采访 OR 播客 OR interview OR 对话`
2. `"{guest_name_en}" podcast OR interview OR keynote OR talk`
3. `"{guest_name}" {industry_keyword} {role_keyword}`
If initial results are thin, try additional queries:
- `"{guest_name}" site:linkedin.com`Details
- Skill name
interview-outline- Repository
- fanyu-meng/podcast-content-studio
- Path
.agents/skills/interview-outline/SKILL.md- Repo updated
- 17 October 2026
FAQ
What does the Interview Outline skill do?
Generate podcast interview outlines for 破壁圆桌 from guest information and web research. Produces a guest profile, themed interview questions, and opening script — all in a casual, specific, human voice. Use when the user wants to prepare an interview, 采访大纲, 采访提纲, 播客准备, or 嘉宾调研.
How do I install the Interview Outline skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add fanyu-meng/podcast-content-studio --skill interview-outline. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Interview Outline popular?
It lives in fanyu-meng/podcast-content-studio, which has 9 GitHub stars and 2 forks.
Related skills
Podcast Shownotes
9fanyu-meng/podcast-content-studio
Generate clear, natural podcast show notes from a transcript PDF, with restrained titles, fluent Chinese, guest introductions, episode summaries, and accurate timestamps. Use when the user asks for show notes, a podcast summary, or timestamps.
Xiaohongshu Copywriting
9fanyu-meng/podcast-content-studio
Generate Xiaohongshu (小红书) promotional posts from a podcast transcript PDF or existing show notes. Supports three output types — text post, multi-angle posts, and carousel slide copy. Written in a natural human voice optimized for social media engagement. Use when the user wants 小红书文案, 小红书推广, 播客宣传, or 社交媒体文案.
Video Vision
9Moh4696/claude-video-vision
Watch and understand local video files. Extracts sampled frames with ffmpeg and generates a timestamped transcript with local Whisper, then answers the user's question grounded in both visual and audio evidence. Use this skill whenever the user references a video file (.mp4, .mov, .mkv, .webm, .avi, .m4v) and wants it watched, summarized, analyzed, described, searched, captioned, transcribed, clipped, or asks questions like "what happens in this video", "what is said at 1:30", "find the part where X", "summarize this recording / lecture / meeting / clip", even if they don't explicitly say "wat
Empathy Reviewer
10gener8v/gener8v.claude-skills.rfp-response
Reviews each drafted section for tone, voice, and client-centricity. Flags where the proposal sounds like it was written for a generic client rather than this specific one. This is a relationship pass, not a grammar pass. Trigger when the user says "review for tone," "empathy pass," "check the voice," "does this sound right," or after the section drafter has produced sections/*.md files.
Alterlab Vcd Photo Editor
21AlterLab-IEU/AlterLab-FC-Skills
This skill should be used when the user asks about "photo editing", "image editing", "retouching", "photo retouching", "photo essay", "photo curation", "AI photo editing", "color grading photography", "Lightroom", "Photoshop", "image compositing", "photo narrative", "editorial photography", "act as a photo editor", "photo editor mode", "image correction", "exposure adjustment", "white balance", "skin retouching", "photo story", "picture editing", "batch editing photos", "RAW processing", "photo selection", "editing ethics", "portrait retouching", "product photography editing", or needs experti
Working with Provenance
9konflux-ci/agent-plugins
Use when tracing Konflux builds from image references, finding build logs from artifacts, or verifying source commits for container images - extracts provenance attestations to navigate from images back to builds and source code
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.