Files
last30days-skill/README.md
T
Matt Van Horn 169720c607 Add dog-as-human example images to README
Shows the viral trend result:
- Original golden retriever with harness and pink tag
- ChatGPT transformation: same hair color, tongue out, harness, tag

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 17:37:35 -08:00

170 lines
6.0 KiB
Markdown

# /last30days
A Claude Code skill that researches any topic across Reddit and X from the last 30 days, synthesizes the insights, and writes copy-paste-ready prompts for your target tool.
## Installation
```bash
# Clone the repo
git clone https://github.com/mvanhorn/last30days-skill.git ~/.claude/skills/last30days
# Add your API keys
mkdir -p ~/.config/last30days
cat > ~/.config/last30days/.env << 'EOF'
OPENAI_API_KEY=sk-...
XAI_API_KEY=xai-...
EOF
chmod 600 ~/.config/last30days/.env
```
## Usage
```
/last30days [topic] for [tool]
```
Examples:
- `/last30days iOS app mockups for Nano Banana Pro`
- `/last30days remotion animations for Claude Code`
- `/last30days landing page design for Figma`
## What It Does
1. **Researches** - Scans Reddit and X for discussions from the last 30 days
2. **Synthesizes** - Identifies patterns, best practices, and what actually works
3. **Prompts** - Writes copy-paste-ready prompts in the format the research recommends
---
## Example: Remotion Launch Video
**Query:** `/last30days research best practices for beautiful remotion animation videos in claude code`
**Research Output:**
> The Remotion + Claude Code combination has emerged as a powerful workflow. Users consistently report that simple, clear prompts with scene-by-scene descriptions yield the best results. Key insights: iteration is essential—most "beautiful" videos come from back-and-forth refinement rather than one-shot prompts.
**Then asked:** "Can you make a prompt for a 50 second launch video for my /last30days skill?"
**Generated Prompt:**
```
Create a 50-second launch video for "/last30days" - a Claude Code skill that
researches any topic across Reddit and X from the last 30 days, then writes
copy-paste-ready prompts.
SCENE 1 (0-8s): The Problem
Dark background. Text fades in: "You want to create something great."
Beat. Then: "But the internet is overwhelming."
Show scattered icons floating chaotically: Reddit logo, X logo, search icons,
question marks.
Slight camera shake to convey chaos.
SCENE 2 (8-16s): The Solution Reveal
Clean wipe transition. Calm, modern gradient background (deep purple to blue).
"/last30days" types in with a terminal cursor, monospace font.
Subtitle fades in below: "Instant expertise. Real prompts."
SCENE 3 (16-28s): How It Works
Split into 3 animated steps that slide in sequentially:
1. [Reddit + X icons merge] "Scans Reddit & X from the last 30 days"
2. [Brain/lightbulb icon] "Synthesizes what actually works"
3. [Document with sparkle] "Writes prompts you can copy-paste"
Each step has a subtle bounce animation on entry.
SCENE 4 (28-40s): Live Demo Feel
Simulate a terminal. Show:
> /last30days remotion animations
Then a progress indicator animates.
Results appear: "Analyzed 28 sources..."
Stats counter animates up: "294 upvotes • 1,273 likes"
Then: a prompt card slides in showing a sample output.
SCENE 5 (40-50s): Call to Action
Zoom out slightly. Everything fades except the logo.
Text animates in: "Research any topic. Get prompts that work."
GitHub icon + "github.com/mvanhorn/last30days-skill"
Tagline: "A Claude Code Skill"
STYLE NOTES:
- Color palette: Deep purple (#1a1a2e), electric blue (#4361ee), white text
- Typography: Inter or SF Mono for code, clean sans-serif for headlines
- Transitions: Smooth eases, nothing jarring
- Music sync points: Scene transitions should land on beats
```
This prompt was generated based on research from 10 Reddit threads (294 upvotes) and 18 X posts (1,273 likes) about Remotion animation best practices.
---
## Example: Discover Viral Trends (Dog as Human)
**Query:** `/last30days using ChatGPT to make images of dogs`
**Research Output:**
> The Reddit community is obsessed with the "dog as human" trend - uploading photos of their dogs and asking ChatGPT to show what they'd look like as a person (threads with 600-900+ upvotes). Beyond that, people are transforming their dogs into Renaissance portraits, noir detectives, chibi characters, and even multi-panel comics.
**Key patterns discovered:**
1. Upload reference photo first - ChatGPT works best with your actual dog's image
2. "As a human" transformation - The viral trend
3. Style/era transformations - Renaissance, noir, chibi, cartoon
4. Scene placement - French bistro, prison yard, detective office
5. Specific visual details - Lighting, background, expression, accessories
**Then asked:** "what would my dog look like as a human prompt"
**Generated Prompt:**
```
Look at this photo of my dog. Create an image showing what they would look like
as a human person. Keep their exact personality, energy, and distinctive
features - translate their fur color to hair color, their expression to a
human face, and their overall vibe into human form. Make it a realistic
portrait photo, not a cartoon.
```
*How to use: Upload your dog's photo first, then paste this prompt.*
**The Result:**
<p align="center">
<img src="assets/dog-original.jpeg" width="300" alt="Original dog photo"/>
&nbsp;&nbsp;→&nbsp;&nbsp;
<img src="assets/dog-as-human.png" width="300" alt="Dog as human"/>
</p>
Same golden fur → red hair. Same tongue out. Same harness. Same pink tag. ChatGPT nailed it.
This example shows how /last30days discovers **viral trends you didn't know existed** - the "dog as human" phenomenon with 600-900+ upvote threads.
---
## Options
| Flag | Description |
|------|-------------|
| `--quick` | Faster research, fewer sources (8-12 each) |
| `--deep` | Comprehensive research (50-70 Reddit, 40-60 X) |
| `--debug` | Verbose logging for troubleshooting |
| `--sources=reddit` | Reddit only |
| `--sources=x` | X only |
## Requirements
- **OpenAI API key** - For Reddit research (uses web search)
- **xAI API key** - For X research (optional but recommended)
At least one key is required.
## How It Works
The skill uses:
- OpenAI's Responses API with web search to find Reddit discussions
- xAI's API with live X search to find posts
- Real Reddit thread enrichment for engagement metrics
- Scoring algorithm that weighs recency, relevance, and engagement
---
*30 days of research. 30 seconds of work.*