leamsigc/shortsgenerator/ig-research

Claude Code and agent skill by leamsigc/shortsgenerator

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Social media content research tool — scrape, transcribe, analyze top-performing content across platforms (Instagram, Facebook, LinkedIn, X, YouTube). Main orchestrator skill. Delegates to state sub-skills for each phase. Also runs the shared video-ideas pipeline (video-idea-research subskill): research the topic on the platform for the reels/videos with the most views in a window (week/month/year) → extract outlines → 5 video ideas × 3 scripts (viral / storytelling / inspiration) + YouTube metadata (title, description, tags, keywords) → REPORT.html with the top 10 videos and the 5 scripted ideas.

Install

npx vskill@latest install leamsigc/shortsgenerator/ig-research

SKILL.md

Social Research Tool — Main Skill

Full workflow: Setup → Scrape → Transcribe → Report → Analyze → Video Ideas

Video Ideas Mode

Given a topic (e.g. "futbol mexicano"), research the platform's top reels by views in a window and build video ideas from them:

/ig-research ideas:<topic> [platform:instagram|facebook|linkedin|x|youtube] [window:week|month|year] [limit:10] [ideas:5] [lang:es]

Full protocol: skill video-idea-research. Instagram specifics:

StepHow (Instagram)
Collect candidateshashtag pages (/explore/tags/<hashtag>/), reels tab, competitor accounts
Windownewest-first browse + post date on each reel page
Viewsreel page play count when visible; else likes + saves × est. (record the proxy used)
Outlinecaption = hook; Whisper transcript via scripts/transcribe.sh for beats/CTA
Mediareel URLs from the scrape feed the final video (short-generator)
Outputvideo-ideas.json → node "$CLAUDE_SKILL_ROOT/scripts/build-ideas-report.js" <path> (script ships with the video-idea-research skill; fallback: node ./skills/video-idea-research/scripts/build-ideas-report.js <path>)

Architecture

skills/ig-research/            # Skill (bundled, global-installable via ~/.claude/skills/)
├── SKILL.md
└── scripts/                   # Bundled — no external .ig-research/scripts needed
    ├── package.json
    ├── scrape.js
    ├── transcribe.sh
    └── report-html.js
 
.ig-research/                  # Tool data directory (project root, auto-resolved)
└── projects/<name>/
    ├── config.json            # Global per-project config
    ├── latest.json            # -> <YYYY-MM-DD_HHMMSS>
    └── <YYYY-MM-DD_HHMMSS>/   # One folder per run (dated)
        ├── raw-posts.json
        ├── transcripts/
        ├── hook-screenshots/
        └── report.html

Platform Extensibility

Each platform has its own scraper. The config schema includes a platform field:

PlatformScraper locationConfig platform
Instagramscripts/scrape.js (default)instagram
Facebookplatforms/facebook/scrape.jsfacebook
LinkedInplatforms/linkedin/scrape.jslinkedin
Xplatforms/x/scrape.jsx
YouTubeplatforms/youtube/scrape.jsyoutube

To add a new platform: create a scraper script in skills/ig-research/platforms/<name>/scrape.js (or external platforms/<name>/scrape.js with --data-root) that outputs raw-posts.json with the same schema (posts array with postId, type, likes, caption, author, platform, hasScreenshots, hasAudio). The transcribe and report steps work with any platform's output.

Workflow

Load the full workflow with: skill ig-research

Each state can be run independently with: skill ig-research-<state>

bash
# Run full pipeline for a project
skill ig-research-setup     # Step 1: Setup (prerequisites + config)
skill ig-research-scrape    # Step 2: Scrape Instagram
skill ig-research-transcribe # Step 3: Transcribe audio
skill ig-research-report    # Step 4: Generate HTML report
skill ig-research-analyze   # Step 5: Content psychology analysis + video ideas

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
348
Repository forks
75
7-day trend score
29

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/leamsigc/shortsgenerator/ig-research/badge)](https://verified-skill.com/skills/leamsigc/shortsgenerator/ig-research)

Something wrong with this skill or its page? Tell us.