Content Recycler logo

Content Recycler

Organization
Amazon-Quick
content-recycler

Repurposes a single piece of long-form content (blog post, whitepaper, talk transcript) into multiple platform-specific formats in one pass: LinkedIn posts, X/Twitter threads, newsletter blurbs, email summaries, slide talking points, and short-form video scripts. Adapts tone, length, and structure per platform. Use when asked to 'repurpose this content', 'turn this blog into social posts', 'create a content package', 'adapt this for LinkedIn', 'multi-platform from this article', or 'content atomization'.

Overview

PublisherAmazon-Quick
RepositoryAmazon-Quick-official-catalog
Skill namecontent-recycler
Stars
50
Forks
4
Bundled files
1
LicenseMIT-0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Amazon-Quick on GitHub. Read the source before you install it.

Installation

Install the Content Recycler AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/marketing/content-recycler
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Amazon-Quick/Amazon-Quick-official-catalog.git /tmp/Amazon-Quick-official-catalog
mkdir -p .claude/skills
cp -r /tmp/Amazon-Quick-official-catalog/skills/marketing/content-recycler .claude/skills/content-recycler
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Content Recycler in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Content Recycler on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Content Recycler is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Overview

Takes a single long-form source and produces ready-to-publish variants for each selected platform. Each variant respects character limits, structural conventions, and audience expectations of its target platform. The skill preserves the core message and claims of the original without introducing new information.

Workflow

<Definition - Platform Constraints> Hard limits and structural expectations per platform:

  • LinkedIn: 3,000 character max per post. Hook line in first sentence. Line breaks for readability. No external links in body (algorithm penalty). CTA or question at the end.
  • X/Twitter: 280 characters per tweet. Threads numbered (1/N). First tweet must stand alone as a hook. Final tweet includes a summary or CTA.
  • Newsletter: 150-300 words. Subject line under 60 characters. One key takeaway per blurb. Scannable with bold or bullet formatting.
  • Email summary: 100-200 words. Plain language. Action-oriented subject line. One clear ask or next step.
  • Slides (talking points): 5-8 bullet points per slide concept. One idea per bullet. No full sentences longer than 15 words.
  • Video script: 60-90 seconds of spoken word (approx. 150-225 words). Conversational register. Opens with a hook question or bold statement. Closes with a single CTA. </Definition - Platform Constraints>

<Definition - Core Message Extraction> The process of identifying the 2-4 central claims or insights from the source material. These become the anchors that every variant must include or reference. Supporting details, examples, and anecdotes are secondary and may be trimmed or swapped depending on format length. </Definition - Core Message Extraction>

<Definition - Content Package> The complete set of platform variants produced from a single source, delivered as a structured document with clear section headers per platform. Saved as a Markdown file and opened in the session tab for review. </Definition - Content Package>

<Workflow - Content Recycling description="End-to-end content repurposing from source to platform-ready variants." tools=[file_read, file_write, run_python, open_in_session_tab] triggers=["repurpose this content", "turn this blog into social posts", "create a content package", "adapt this for LinkedIn", "multi-platform from this article", "content atomization"]

  1. [Agent] Read the source content. If a file path is provided, use file_read (or the appropriate document reader for PDF/DOCX). If the content is pasted inline, capture it directly. Confirm the source length and type. If fails: if the file cannot be read or the pasted text is empty, report the specific error and ask the user to provide the source content again.

  2. [Think] Extract core messages from the source. Identify the 2-4 central claims or insights. Note any direct quotes, statistics, or named examples that should be preserved. Flag any potentially outdated information per Rule 10.

  3. [Ask user] Present the extracted core messages as a numbered list. Confirm these are the right angles to amplify. If the source covers multiple unrelated themes, ask the user to select focus areas. Confirm the target platforms, tone, and any brand voice notes. If fails: if the user does not confirm or the source spans too many themes, ask them to pick the focus themes and target platforms before drafting.

  4. [Think] For each selected platform, draft a variant that meets Platform Constraints. Apply the chosen tone. Incorporate brand voice notes if provided. Verify character/word counts against limits. Ensure each variant satisfies Rules 1-4.

  5. [Agent] Assemble the full content package as a Markdown document. Structure with H2 headers per platform. Include character/word counts next to each variant. Add a "Suggested first comment" line for LinkedIn if links are relevant. Add thread numbering validation for X/Twitter. If fails: if any variant exceeds its platform limit, tighten that variant and re-measure before assembling the package.

  6. [Ask user] Present the content package for review. Highlight any variants where constraints forced simplification of the source message. Ask if any variants need a different angle, tighter editing, or tone adjustment. If fails: if the requested changes are unclear, ask which specific variants and what angle before revising.

  7. [Agent] Apply any requested revisions. Re-verify character/word counts after edits. Confirm all variants still satisfy the rules. If fails: if a revised variant breaks a rule or limit, revert to the prior compliant version and flag the conflict to the user.

  8. [Agent] Save the final content package to the workspace and open it in the session tab. Provide a brief summary: number of variants produced, platforms covered, and any flags (outdated info, simplification notes, link placement reminders). If fails: report the specific save or open error and present the content package inline instead.

</Workflow - Content Recycling>

<Template - LinkedIn Post>

markdown
{{hook_line}}

{{body_paragraph_1}}

{{body_paragraph_2}}

{{cta_or_question}}

---
Suggested first comment: {{link_or_additional_context}}

Character count: {{count}}/3000

</Template - LinkedIn Post>

<Template - X/Twitter Thread>

markdown
Tweet 1 (1/{{N}}):
{{standalone_hook}} ({{count}}/280)

Tweet 2 (2/{{N}}):
{{supporting_point_1}} ({{count}}/280)

Tweet 3 (3/{{N}}):
{{supporting_point_2}} ({{count}}/280)

Tweet {{N}} ({{N}}/{{N}}):
{{summary_or_cta}} ({{count}}/280)

</Template - X/Twitter Thread>

<Template - Newsletter Blurb>

markdown
Subject line: {{subject_line}} ({{count}}/60 chars)

{{hook_sentence}}

{{key_takeaway}}

{{supporting_detail_or_example}}

{{closing_line_with_link_or_cta}}

Word count: {{count}}/300

</Template - Newsletter Blurb>

<Template - Email Summary>

markdown
Subject: {{action_oriented_subject}}

{{opening_context_sentence}}

{{core_message_summary}}

{{clear_next_step_or_ask}}

Word count: {{count}}/200

</Template - Email Summary>

<Template - Slide Talking Points>

markdown
Slide concept: {{slide_title}}

- {{point_1}}
- {{point_2}}
- {{point_3}}
- {{point_4}}
- {{point_5}}

(5-8 points per slide concept, one idea per bullet, under 15 words each)

</Template - Slide Talking Points>

<Template - Video Script (60-90s)>

markdown
[HOOK - first 5 seconds]
{{bold_opening_question_or_statement}}

[BODY - 45-70 seconds]
{{main_point_1}}

{{main_point_2}}

{{supporting_example}}

[CTA - final 10 seconds]
{{single_clear_cta}}

Word count: {{count}}/225 (target: 150-225 words for 60-90 seconds)

</Template - Video Script (60-90s)>

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Content Recycler AI skill do?

Repurposes a single piece of long-form content (blog post, whitepaper, talk transcript) into multiple platform-specific formats in one pass: LinkedIn posts, X/Twitter threads, newsletter blurbs, email summaries, slide talking points, and short-form video scripts. Adapts tone, length, and structure per platform. Use when asked to 'repurpose this content', 'turn this blog into social posts', 'create a content package', 'adapt this for LinkedIn', 'multi-platform from this article', or 'content atomization'.

Why use Content Recycler on TypingMind?

Because you install it once and use it with any model. Content Recycler is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Content Recycler in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/marketing/content-recycler. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Content Recycler?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Content Recycler?

As many as you like. As long as a model supports skills, you can use Content Recycler with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Content Recycler AI skill free?

Yes. It is published on GitHub by Amazon-Quick under the MIT-0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇