ktg-plugin-marketplace/plugins/linkedin-thought-leadership/references/url-processing-templates.md

URL Processing Templates

Templates and examples for converting external URLs into LinkedIn content. Use alongside the URL-to-Content Workflow in the main skill.

Template by URL Type

News Article Template

Input: News article URL Output: Commentary post (800-1,400 characters)

HOOK (110-140 chars):
[Attention-grabbing statement about what the news really means]

CONTEXT (100-150 chars):
[Brief summary of what happened - 1-2 sentences max]

ANALYSIS (400-700 chars):
[Your expert perspective]
- What this actually means
- What most coverage misses
- Why your audience should care
- Connection to your expertise

IMPLICATIONS (150-250 chars):
[What happens next / what to do]
- Prediction or recommendation
- Practical next step

CTA (50-100 chars):
[Question inviting perspective]

---
Comment #1: [Link to original article]

Example transformation:

Source: "Microsoft announces new Copilot pricing tiers"

The new Copilot pricing isn't about the money. It's about strategy.

Microsoft just restructured their Copilot licensing. Most headlines focus on the $30/user price point.

Here's what they're missing:

The real story is differentiation. By splitting Copilot into tiers, Microsoft is:

1. Creating an upgrade path (land and expand)
2. Protecting high-margin enterprise deals
3. Addressing the "too expensive for testing" problem

For organizations evaluating Copilot, this changes the conversation from "can we afford it?" to "which tier makes sense?"

My prediction: Expect competitors to follow with similar tiered models within 6 months.

What's your read on this move?

Research Paper/Report Template

Input: Research/report URL Output: Data translation post (1,200-1,800 characters)

HOOK (110-140 chars):
[The most surprising or counterintuitive finding]

SOURCE ATTRIBUTION (50-100 chars):
[Brief, credible source mention]

KEY FINDINGS (400-600 chars):
[3-5 bullet points, simplified]
- Finding 1 (with number if available)
- Finding 2
- Finding 3
- Finding 4 (optional)
- Finding 5 (optional)

YOUR INTERPRETATION (300-500 chars):
[What this means based on your experience]
- Pattern you've observed
- Why this matters
- What it confirms/challenges

PRACTICAL APPLICATION (200-300 chars):
[What to do with this knowledge]
- Action item 1
- Action item 2

CTA (50-100 chars):
[Question about their experience]

---
Comment #1: Full report here: [Link]

Example transformation:

Source: McKinsey report on AI implementation success rates

67% of AI projects fail to meet expectations.

But here's the finding that should worry AI leaders more:

McKinsey's latest analysis of 1,000+ AI implementations reveals:

- 67% fail to achieve expected ROI
- 53% of failures happen in the first 6 months
- Top predictor of success isn't technology - it's organizational readiness
- Companies with dedicated AI change management see 2.3x success rates
- Most failures could have been predicted at project kickoff

After leading 50+ AI projects, this matches what I've seen:

The projects that fail rarely fail for technical reasons. They fail because:
- Expectations weren't calibrated
- Change management was afterthought
- Success metrics were never defined
- Leadership engagement dropped after kickoff

What this means for your next AI project:

1. Invest 20% of budget in change management
2. Define success metrics BEFORE procurement
3. Keep executive sponsor actively engaged

What's been your experience with AI project success rates?

Blog Post/Article Template

Input: Blog post or external article Output: Extension or reframe post (1,000-1,600 characters)

HOOK (110-140 chars):
[Your angle on the topic - agree, disagree, or extend]

REFERENCE (100-150 chars):
[Brief mention of source and their take]

YOUR PERSPECTIVE (500-800 chars):
[Where you agree, disagree, or add]
- Point of agreement/disagreement
- Your experience that supports this
- The nuance that's missing
- The additional consideration

SYNTHESIS (200-300 chars):
[Bringing it together]
- The balanced view
- What you'd add to their argument

CTA (50-100 chars):
[Invite discussion]

---
Comment #1: Original post by [Author]: [Link]

Example transformation:

Source: Blog post arguing "AI will replace most knowledge workers"

"AI will replace knowledge workers" gets the timeline wrong.

Just read [Author]'s piece arguing for mass displacement. The logic is sound, but the conclusion misses something important.

Where I agree:
AI CAN do many knowledge work tasks. Often better than humans. The capability is real.

Where I disagree:
Capability isn't adoption. Between "AI can do this" and "AI does this at scale" sits:
- Regulatory compliance
- Organizational change capacity
- Integration complexity
- Trust and verification needs
- Edge case handling

After implementing AI across 15 organizations, here's what I've seen:

AI augments far more than it replaces. The jobs that disappear are replaced by new jobs managing, training, and overseeing AI.

The better question isn't "what will AI replace?"

It's "what will human-AI collaboration look like?"

Where do you see the balance falling?

YouTube Video/Talk Template

Input: YouTube video or conference talk URL Output: Key takeaways post (1,000-1,400 characters)

HOOK (110-140 chars):
[The insight that stopped you - the "aha" moment]

CONTEXT (100-150 chars):
[Where you encountered this, brief credibility of source]

KEY TAKEAWAYS (400-600 chars):
[3-5 lessons, your interpretation]
1. Takeaway 1 (with your lens)
2. Takeaway 2
3. Takeaway 3
4. Takeaway 4 (optional)
5. Takeaway 5 (optional)

APPLICATION (200-300 chars):
[How you'll apply or already have]
- Specific action you're taking
- How it changes your approach

CTA (50-100 chars):
[Ask if others have watched/learned from this]

---
Comment #1: Full talk here: [Link]

Example transformation:

Source: Conference keynote on AI governance

"The biggest AI risk isn't bias or hallucinations. It's organizational amnesia."

Just watched [Speaker]'s keynote at [Conference]. This line stopped me cold.

Key insights that will change how I approach AI governance:

1. We're building AI systems on institutional knowledge that's not documented. When key people leave, the AI keeps running but nobody knows why it makes decisions.

2. Audit trails aren't enough. We need "decision archaeology" - understanding the full context of how AI systems were designed.

3. Governance isn't a checkpoint, it's continuous. The AI that passed review 6 months ago may be operating in a completely different context today.

4. The governance question isn't "is this AI safe?" It's "can we explain and defend this AI's decisions in 3 years?"

I'm immediately adding "documentation decay" as a risk category in our AI governance framework.

Has anyone else encountered this organizational amnesia problem?

Company Announcement Template

Input: Company press release or announcement Output: Strategic analysis post (1,000-1,600 characters)

HOOK (110-140 chars):
[What the announcement really signals - beyond the PR]

WHAT HAPPENED (100-150 chars):
[Brief factual summary]

ANALYSIS (500-800 chars):
[Your strategic read]
- What this means for the company
- What this means for the industry
- What's NOT in the announcement
- Who benefits/loses

IMPLICATIONS FOR YOUR AUDIENCE (200-300 chars):
[What your followers should do with this]
- If you're a customer...
- If you're a competitor...
- If you're evaluating...

CTA (50-100 chars):
[Question about their read]

---
Comment #1: [Link to announcement]

Attribution Language Examples

Direct Quotes

As [Author] writes in [Publication]: "[exact quote]"

In [Author]'s words: "[exact quote]"

"[Quote]" - [Author], [Publication]

Paraphrasing

Research from [Source] shows that...

According to [Publication]'s analysis...

[Author] argues that... (my interpretation: ...)

Building on [Author]'s work at [Organization]...

General Reference

A recent study found...

New research suggests...

Industry data indicates...

Credit and Extension

[Author] nailed the diagnosis. Let me add to the prescription...

Inspired by [Author]'s post on [topic]. Here's my experience...

Great thread from [Author] on [topic]. Adding my perspective...

Transformation Examples by Domain

AI/Technology Source

Original headline: "OpenAI releases new reasoning model"

Weak transformation: "OpenAI's new model is amazing! The future of AI is here."

Strong transformation: "OpenAI's new reasoning model changes one thing for enterprise AI. Here's what it is and why it matters for your roadmap..."

Business/Strategy Source

Original headline: "Companies cutting AI budgets despite hype"

Weak transformation: "AI budgets being cut! Is the hype over?"

Strong transformation: "AI budgets are shrinking. As someone who helps organizations plan AI investments, here's what's actually happening (and it's not what headlines suggest)..."

Research/Academic Source

Original headline: "Study finds AI increases productivity 40%"

Weak transformation: "New study shows AI boosts productivity by 40%! Adopt AI now!"

Strong transformation: "The new 40% AI productivity study is both right and misleading. After implementing AI for 50+ teams, here's the nuance the headlines miss..."

Quality Checklist for URL Transformations

Before publishing URL-based content:

Attribution

• Source clearly credited
• Link in comment, not post body
• Author tagged if on LinkedIn
• Quote marks for direct quotes

Value Addition

• At least 30% original content
• My perspective clearly stated
• Connected to my expertise
• Actionable for my audience

Accuracy

• Facts double-checked
• Numbers verified
• Context preserved
• No misrepresentation

Format

• Appropriate length for content type
• Strong hook in first 140 chars
• Proper formatting (paragraphs, bullets)
• Clear CTA

Common Mistakes to Avoid

Mistake	Why It's Bad	Fix
Just summarizing	No unique value	Add perspective
Copying structure	Looks like plagiarism	Restructure for LinkedIn
Burying the source	Appears deceptive	Credit early
Over-quoting	Looks lazy	Paraphrase more
Link in post body	Reach penalty	Move to comment
Missing CTA	Lower engagement	Add discussion question
Wrong angle	Doesn't fit expertise	Choose relevant angle
Too timely	Loses relevance fast	Add evergreen insight