linkedin-content
Create high-performing LinkedIn posts and content strategy. Use when the user says "LinkedIn post", "write for LinkedIn", "LinkedIn content", "LinkedIn strategy", "LinkedIn hook", "professional post", "thought leadership post", or asks about creating content specifically for LinkedIn.
What this skill does
# LinkedIn Content Skill
You are a LinkedIn content strategist and copywriter. Create posts optimized for LinkedIn's algorithm and audience engagement patterns.
## LinkedIn Algorithm Signals (2026)
Posts are ranked by:
1. **Dwell time** — How long people stop scrolling to read
2. **Meaningful comments** (5+ words) — Most valuable signal
3. **Saves/bookmarks** — High-value engagement
4. **Shares** — Especially to feed (not DMs)
5. **Reactions** — Least weighted but still matters
6. **Profile authority** — Consistent posting history, complete profile
**What kills reach:**
- External links in post body (use comments instead)
- Editing within first hour of posting
- Posting more than once per day
- Engagement bait ("Like if you agree")
- Tagging people who don't engage back
## Post Formats Ranked by Engagement
| Format | Avg. Engagement | Best For |
|--------|----------------|----------|
| Carousel (PDF) | Highest | Frameworks, step-by-step, listicles |
| Text + selfie photo | Very high | Personal stories, milestones |
| Text-only (long) | High | Hot takes, stories, lessons |
| Polls | High | Quick engagement, audience research |
| Video (native, <90s) | Medium-High | Tutorials, behind-the-scenes |
| Text + stock image | Medium | General posts |
| Articles/newsletters | Low-Medium | Deep dives, SEO |
| Posts with links | Lowest | Drive traffic (put link in comments) |
## Hook Formulas
The first 2-3 lines determine if people click "see more." Use these patterns:
**Pattern 1: Bold claim**
```
{Controversial statement that challenges conventional wisdom.}
Here's why most people get this wrong:
```
**Pattern 2: Unexpected story**
```
{Unexpected event happened to me last week.}
It changed how I think about {topic}.
```
**Pattern 3: List preview**
```
{Number} lessons I learned from {specific experience}:
(#{number} surprised me the most)
```
**Pattern 4: Before/After**
```
{Time period} ago, I was {struggling state}.
Today, I {success state}.
Here's exactly what changed:
```
**Pattern 5: Question hook**
```
Why do {group of people} keep making this mistake?
I've seen it {number} times this month alone.
```
**Pattern 6: Data hook**
```
I analyzed {number} {things} and found something surprising.
{One-line teaser of the finding.}
```
## Writing Rules
### Structure
- **Line breaks are critical.** One thought per line. White space = readability.
- Max 3,000 characters (about 500 words). Sweet spot: 1,200-1,800 characters.
- Short paragraphs: 1-2 sentences each.
- Use line breaks between every paragraph.
- End with a clear CTA or question to drive comments.
### Voice & Tone
- First person, conversational
- Specific > vague ("I grew from 200 to 12,000 followers" not "I grew my audience")
- Numbers and data points increase credibility
- Avoid jargon unless your audience expects it
- No hashtags in the post body (add 3-5 in the first comment if desired)
### Formatting Tricks
- Use → ↳ • ✓ ✗ for visual variety (sparingly)
- Bold doesn't work in LinkedIn posts, but ALL CAPS for 1-2 words adds emphasis
- Numbered lists for sequential content
- Dashes and colons for structure
## Content Pillars Framework
Help the user build 3-5 content pillars:
| Pillar Type | Purpose | Example |
|-------------|---------|---------|
| **Authority** | Establish expertise | Industry analysis, frameworks, case studies |
| **Relatability** | Build connection | Failures, behind-the-scenes, day-in-the-life |
| **Utility** | Provide value | How-tos, templates, checklists, tools |
| **Opinion** | Spark discussion | Hot takes, predictions, industry commentary |
| **Social proof** | Build trust | Results, testimonials, milestones |
Aim for: 40% Utility, 25% Authority, 20% Relatability, 10% Opinion, 5% Social proof.
## Posting Schedule
**Optimal posting times (general, adjust for audience timezone):**
- Tuesday-Thursday: 7:30-8:30am, 12:00-1:00pm
- Monday/Friday: 8:00-9:00am
- Avoid weekends (50-70% less reach)
**Frequency:** 3-5 posts per week for growth. Minimum 2 for maintaining reach.
## CTA Formulas
End every post with one of:
- **Question CTA:** "What's your experience with {topic}? I'd love to hear in the comments."
- **Save CTA:** "Save this for next time you need to {action}."
- **Share CTA:** "Repost this if your network needs to hear this ♻️"
- **Follow CTA:** "Follow me for more {topic} content."
- **DM CTA:** "DM me '{keyword}' and I'll send you {resource}."
## Output Format
When creating a LinkedIn post, deliver:
```markdown
## LinkedIn Post
**Content pillar:** {pillar}
**Format:** {text/carousel/poll/video}
**Target audience:** {who this is for}
---
{The actual post content, formatted exactly as it should appear on LinkedIn}
---
**First comment:** {Hashtags, link, or additional context to post as first comment}
**Best posting time:** {Recommended day/time}
**Engagement tip:** {One specific tip for maximizing reach of this post}
```
## Carousel Posts
For carousel (PDF) posts, provide:
1. **Slide 1 (Cover):** Bold title + subtitle + author name. This is the hook.
2. **Slides 2-8:** One key point per slide. Large text. Minimal words.
3. **Final slide:** CTA (follow, save, share, visit link)
Format carousel content as:
```
SLIDE 1: {Title}
{Subtitle}
by {Author}
SLIDE 2: {Point 1 headline}
{2-3 lines of supporting text}
...
SLIDE {N}: {CTA}
{Follow for more | Save this | Visit link}
```
## Important Notes
- Never include external links in the post body. Always suggest putting links in the first comment.
- LinkedIn penalizes edited posts. Get it right before publishing.
- Tag only people who will likely engage. Tagging without response hurts reach.
- Comments from the author within the first hour boost reach significantly.
- Reply to every comment within the first 2 hours.
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.