菜单
Transform long-form content into multiple short-form pieces. Use when: converting podcast to social posts; extracting Twitter threads from blog posts; pulling quotes from transcripts; creating content variants from single source
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | content-repurposer |
| description | Transform long-form content into multiple short-form pieces. Use when: converting podcast to social posts; extracting Twitter threads from blog posts; pulling quotes from transcripts; creating content variants from single source |
| license | MIT |
| metadata | {"author":"ClawFu","version":"1.0.0","mcp-server":"@clawfu/mcp-skills"} |
Turn one piece of content into 10+ pieces using AI-powered extraction and reformatting - the "create once, publish everywhere" workflow.
| Claude Does | You Decide |
|---|---|
| Structures production workflow | Final creative direction |
| Suggests technical approaches | Equipment and tool choices |
| Creates templates and checklists | Quality standards |
| Identifies best practices | Brand/voice decisions |
| Generates script outlines | Final script approval |
pip install anthropic jinja2 click pyyaml
# Requires ANTHROPIC_API_KEY environment variable
python scripts/main.py repurpose transcript.txt --formats "twitter,linkedin,instagram"
python scripts/main.py repurpose blog-post.md --formats all
python scripts/main.py thread article.md --max-tweets 10
python scripts/main.py thread transcript.txt --style educational
python scripts/main.py quotes podcast-transcript.txt --count 5
python scripts/main.py quotes interview.txt --style inspirational
python scripts/main.py hooks content.txt --count 10
python scripts/main.py hooks product-page.txt --style curiosity
# Input: 45-minute podcast transcript
python scripts/main.py repurpose episode-42-transcript.txt --formats all
# Output directory: episode-42-transcript_repurposed/
# ├── twitter_thread.md (10-tweet thread)
# ├── linkedin_post.md (long-form post)
# ├── instagram_carousel.md (10 slides)
# ├── quotes.md (5 quotable moments)
# └── hooks.md (5 attention grabbers)
# Convert 2000-word article to thread
python scripts/main.py thread positioning-strategy.md --max-tweets 12 --style educational
# Output: positioning-strategy_thread.md
# 1/ Here's how the best B2B companies position themselves (thread)
# 2/ First, they identify their competitive alternatives...
# ...
# 12/ TL;DR: Position for differentiation, not features. Link in bio.
# Pull shareable quotes from interview
python scripts/main.py quotes founder-interview.txt --count 10 --style inspirational
# Output: founder-interview_quotes.md
# 1. "We didn't build a product, we built a belief system."
# 2. "Your first 100 customers should feel like co-founders."
# ...
| Format | Best For | Typical Length |
|---|---|---|
twitter | Thread with numbered tweets | 8-15 tweets |
linkedin | Long-form professional post | 1,200-1,500 chars |
instagram | Carousel slide content | 10 slides |
quotes | Shareable quote graphics | 5-10 quotes |
hooks | Opening lines for posts | 10 hooks |
summary | Executive summary | 200-300 words |
newsletter | Email-friendly summary | 500-800 words |
| Style | Tone | Use Case |
|---|---|---|
educational | Teaching, explaining | Tutorials, how-tos |
inspirational | Motivating, uplifting | Founder stories |
provocative | Challenging assumptions | Thought leadership |
conversational | Casual, relatable | Personal brand |
professional | Formal, authoritative | B2B, enterprise |
category: automation
subcategory: content-automation
dependencies: [anthropic, jinja2]
difficulty: beginner
time_saved: 8+ hours/week
api_cost: ~$0.02-0.10 per repurpose
Run a structured 5-pass finishing audit on any website before launch — scoring visual polish, technical foundation, UX completeness, content quality, and cross-device readiness on 100 points. Use when: **Pre-launch** - Final validation before going live; **Post-redesign** - Verify nothing broke during the overhaul; **Client handoff** - Structured proof that the site is ready; **Quarterly review** - Catch accumulated debt; **Single-pass focus** - Run just Pass 2 after a perf sprint
Use when rewriting AI-generated text to match a specific person's or brand's authentic voice. Use when AI output sounds generic, corporate, or detectable. Unlike generic "humanizers," this skill requires voice analysis input and produces voice-consistent output, not fake imperfections.
Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map-reduce across files without context rot. Use when: analyzing large repositories; auditing security or auth across many files; finding patterns across 50+ files; processing large log files or data dumps
Model best-case, worst-case, and likely revenue scenarios with sensitivity analysis for strategic planning. Use when: building financial forecasts; presenting board scenarios; planning headcount around revenue uncertainty; modeling pricing changes impact; preparing investor updates with upside/downside ranges
Use when analyzing server logs to understand how AI crawlers (GPTBot, ClaudeBot, PerplexityBot) interact with your site. Use when optimizing content placement for LLM retrieval, diagnosing why AI search isn't citing your content, or auditing crawl patterns to find optimization gaps.
Use when optimizing for AI search visibility where individual experts and entities outperform generic brand pages. Use when building cross-platform authority for people, organizations, or products that AI models should recognize and cite.