social-media-post
Generate optimized social media posts for Threads, X (Twitter), and LinkedIn. Analyzes platform algorithms, applies best practices, and creates engaging content tailored to each platform. Local skill for Navigator marketing only.
What this skill does
# Social Media Post Generator Skill
Generate platform-optimized social media posts using algorithm insights and best practices.
**Note**: This is a LOCAL skill for Navigator marketing only. NOT included in the plugin distribution.
## When to Invoke
Auto-invoke when user says:
- "Create a Threads post about [topic]"
- "Write a social media post for [announcement]"
- "Generate X post for [feature]"
- "Create LinkedIn announcement for [release]"
- "Write Threads post like option 5"
## What This Does
**Platform-Specific Workflow**:
1. **Analyze Content**: Extract key points, features, value propositions
2. **Apply Platform Rules**: Character limits, formatting, hashtag strategies
3. **Optimize for Algorithm**: Engagement tactics, timing recommendations
4. **Generate Variants**: Multiple options (short, medium, detailed)
5. **Include Metadata**: Character count, hashtag suggestions, posting time
**Platforms Supported**: Threads, X (Twitter), LinkedIn
---
## Platform Specifications
### Threads (Instagram)
**Character Limits**:
- Standard post: 500 characters
- Long-form (with attachment): 10,000 characters
- Display: Shows "Read more" after ~500 chars
**Formatting**:
✅ Bold, italic, underline, strikethrough
✅ Emojis (count toward limit)
✅ Bullet points (using • or -)
✅ Line breaks
❌ No hashtags in Threads (algorithm ignores them)
❌ No clickable links in body (use link preview)
**Media**:
- Images: Up to 10 per post
- Video: Up to 5 minutes
- Link previews: Automatic from URLs
**Algorithm Priorities** (2025):
1. **Engagement** (40%): Likes, comments, shares, reply views
2. **Recency** (30%): Fresh content gets priority
3. **Interest/Relevance** (20%): Based on user's past interactions
4. **Profile Visits** (10%): Likelihood user will click profile
**Best Practices**:
✅ Conversational, authentic tone (not corporate)
✅ Ask open-ended questions
✅ Create discussions, not announcements
✅ Post consistently (1-3x daily)
✅ Use visuals (images/videos boost engagement)
✅ Respond to comments within 1 hour
❌ No direct cross-posts from Instagram/X
❌ Avoid promotional language
❌ No hashtags (they don't work on Threads)
**Optimal Posting Times** (US audience):
- Monday-Friday: 9-11 AM, 1-3 PM, 7-9 PM ET
- Saturday-Sunday: 10 AM-2 PM ET
**Content That Works**:
- Behind-the-scenes insights
- Quick tips and tricks
- Relatable experiences
- Open-ended questions
- Industry discussions
- Memes (if relevant)
---
### X (Twitter)
**Character Limits**:
- Standard tweet: 280 characters
- Premium (Blue): 25,000 characters (displays with "Show more")
**Formatting**:
✅ Emojis
✅ Line breaks (use intentionally)
✅ Mentions (@username)
✅ Hashtags (max 2-3 per tweet)
❌ No rich text formatting
**Media**:
- Images: Up to 4 per tweet
- Video: Up to 2:20 (standard), 10 min (Blue)
- GIFs: 1 per tweet
**Algorithm Priorities** (2025):
1. **Engagement rate** (likes, retweets, replies)
2. **Recency** (fresh tweets prioritized)
3. **Media** (tweets with images/video perform better)
4. **Authenticity** (verified accounts, genuine engagement)
**Best Practices**:
✅ Front-load important info (first 100 chars)
✅ Use line breaks for readability
✅ 1-2 hashtags max (more hurts engagement)
✅ Include visual (image/video)
✅ Tag relevant accounts (when appropriate)
✅ Tweet threads for detailed content
❌ Don't overuse hashtags (looks spammy)
❌ Avoid link-only tweets (add context)
**Optimal Posting Times** (US audience):
- Monday-Friday: 8-10 AM, 12-1 PM, 5-6 PM ET
- Saturday-Sunday: 9 AM-12 PM ET
---
### LinkedIn
**Character Limits**:
- Post: 3,000 characters (shows "see more" after ~140 chars in feed)
- Article: 125,000 characters
**Formatting**:
✅ Emojis (use sparingly)
✅ Bullet points
✅ Line breaks
✅ Bold (using Unicode)
✅ Numbered lists
❌ No official rich text (use workarounds)
**Media**:
- Images: Up to 9 per post
- Video: Up to 10 minutes
- Documents: PDF uploads
**Algorithm Priorities** (2025):
1. **Dwell time** (how long users read your post)
2. **Engagement** (likes, comments, shares)
3. **Relevance** (to user's network and interests)
4. **Personal connections** (1st-degree connections prioritized)
**Best Practices**:
✅ Professional but authentic tone
✅ Hook in first 2 lines (before "see more")
✅ Tell stories, share insights
✅ Use data/statistics
✅ Ask for opinions (engagement)
✅ Tag relevant companies/people
✅ Post 2-5x per week
❌ Avoid overly promotional content
❌ Don't overuse hashtags (3-5 max)
**Optimal Posting Times** (US business hours):
- Tuesday-Thursday: 8-10 AM, 12-1 PM ET
- Avoid: Weekends, late evenings
---
## Workflow Protocol
### Step 1: Content Analysis
**Execute**: `post_analyzer.py`
**Extract**:
- Key announcement/feature
- Value proposition
- Technical details
- Target audience
- Tone (technical, casual, professional)
**Example Input**:
```
Topic: Navigator v3.3.1 with nav-upgrade skill
Key features: One-command updates, automatic configuration
Value: 83% time savings (12 min → 2 min)
Audience: Developers using Claude Code
```
**Output**:
```json
{
"topic": "Navigator v3.3.1 plugin update automation",
"key_points": [
"One-command updates via nav-upgrade skill",
"Automatic version detection from GitHub",
"83% time savings",
"18 total skills"
],
"value_proposition": "Eliminates manual update process",
"call_to_action": "Install or update Navigator",
"tone": "technical-casual"
}
```
---
### Step 2: Platform Optimization
**Execute**: `engagement_optimizer.py --platform threads`
**Apply Platform Rules**:
- Character limit enforcement
- Formatting constraints
- Hashtag strategy
- Media recommendations
- CTA placement
**Optimize for Algorithm**:
- Engagement hooks
- Question placement
- Visual suggestions
- Timing recommendations
---
### Step 3: Generate Post Variants
**Create 3 Variants**:
1. **Short & Punchy** (Option 5 style)
- Under 280 chars (X-compatible)
- Emoji bullets
- Clear value props
- Direct CTA
2. **Medium Detailed**
- 300-500 chars (Threads standard)
- More context
- Multiple CTAs
- Conversation starter
3. **Long-Form** (Threads attachment / LinkedIn)
- 800-1500 chars
- Full story/context
- Multiple sections
- Rich formatting
---
### Step 4: Add Metadata
For each variant, include:
```markdown
**Platform**: Threads
**Character Count**: 287/500
**Estimated Engagement**: High (question + visual + emojis)
**Hashtags**: None (Threads doesn't use hashtags)
**Media Suggestion**: Screenshot of update command
**Best Time to Post**: Tuesday 9-11 AM ET
**Follow-up**: Reply with technical details after 2 hours
```
---
## Templates
### Template: Product Launch (Threads)
```
[Hook Question]
[Product Name] [Version] just landed:
✅ [Feature 1]: [Benefit]
✅ [Feature 2]: [Benefit]
✅ [Feature 3]: [Benefit]
✅ [Key Metric]: [Value proposition]
[CTA 1]:
[Command/Installation]
[CTA 2]:
[Command/Update]
[Link]
[Conversation Hook]
```
**Example**:
```
Teach your Claude Code to design like a Product Designer.
Navigator v3.3.1:
✅ Figma MCP (design extraction)
✅ Storybook automation
✅ Chromatic integration
✅ One-command updates
Install:
/plugin marketplace add alekspetrov/navigator
Update:
"Update Navigator"
https://github.com/alekspetrov/navigator
What's your biggest design handoff pain point?
```
**Character Count**: 289/500
**Engagement Hook**: Opening question + closing question
---
### Template: Feature Announcement (X)
```
[Feature Name] just shipped 🚀
[Key benefit in 1 line]
[Emoji] [Feature detail 1]
[Emoji] [Feature detail 2]
[Emoji] [Feature detail 3]
[CTA with link]
[Optional: Thread continuation →]
```
**Example**:
```
One-command Navigator updates 🚀
No more manual /plugin update, CLAUDE.md editing, or verification.
✅ "Update Navigator"
✅ 2 min vs 12 min manual
✅ 95% success rate
Install: /plugin marketplace add alekspetrov/navigator
https://github.com/alekspetrov/navigator
```
**Character Count**: 241/280
**Thread continuation**: Technical 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.