leamsigc/shortsgenerator/twitter-research-report

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.

Report state — generates the final HTML report (REPORT.html) from raw-posts.json, audience-scores.json, content-drafts.json, and engagement-responses.json. Includes audience scoring matrix, top post analysis, content drafts, and pre-defined engagement responses for every topic post. In Video Ideas Mode it also renders the top-10 videos by views (with outlines) and the 5 video ideas with 3 scripts each (viral/storytelling/inspiration) plus YouTube metadata (title, description, tags, keywords) vi…

Install

npx vskill@latest install leamsigc/shortsgenerator/twitter-research-report

SKILL.md

Twitter/X Research — Report State (v4)

Generates the final HTML report with audience scoring, post links, and engagement responses.

Video Ideas Mode report

When the session contains video-ideas.json (from the analyze state / the video-idea-research playbook), render the dedicated ideas report:

bash
node "$CLAUDE_SKILL_ROOT/scripts/build-ideas-report.js" <path-to-video-ideas.json>
# fallback: node ./skills/video-idea-research/scripts/build-ideas-report.js <path>

Writes ideas-report.md + REPORT.html next to the input with the two mandatory sections: 1) the top 10 videos (rank, title, views, window, velocity, link, outline) and 2) the 5 video ideas (titles, viral + storytelling + inspiration scripts, audiences, view estimate, media links, YouTube metadata). If the main REPORT.html also exists, append a link to it so both are reachable from one index.

Preconditions

  • Config exists: .twitter-research/<timestamp>/config.json
  • Raw posts exist: .twitter-research/<timestamp>/raw-posts.json (10+ topic posts)
  • Analysis exists: .twitter-research/<timestamp>/audience-scores.json
  • Content drafts exist: .twitter-research/<timestamp>/content-drafts.json

Steps

1. Generate engagement responses (per topic post)

For EVERY post in raw-posts.json posts[], craft 3 response types the user can post as replies to build presence on the topic:

TypeStrategyLimitTone
Value addBuild on the tweet's point with an expert insight1-3 sentencesHelpful, authoritative
Discussion starterAsk a thoughtful question that sparks replies1-2 sentencesCurious
Agree + amplifyAgree strongly and add a personal take1-2 sentencesEnthusiastic

Rules: never pitch the product, stay on-topic, reference specifics, end with a hook, keep it short.

Save to .twitter-research/<timestamp>/engagement-responses.json (schema: responses[] with targetPostUrl, targetHandle, postPreview, targetSegment, responses[{type, text, whyThisWorks}], tracking).

2. Generate REPORT.html
bash
node "$CLAUDE_SKILL_ROOT/scripts/report-html.js" <timestamp>
# fallback: node ./skills/twitter-research/scripts/report-html.js <timestamp>

The script renders a self-contained dark-themed report from all JSON files:

  • Audience scoring matrix
  • Top posts with direct X links + engagement stats
  • Content drafts (social posts + video scripts)
  • Engagement responses (copyable, with Reply-on-X links)

Report Completion

✅ Twitter/X Research Report Complete!
Session: .twitter-research/<timestamp>/
📊 REPORT.html — open in browser
📁 audience-scores.json · content-drafts.json · engagement-responses.json

Security

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

Quality evaluation

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

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/twitter-research-report/badge)](https://verified-skill.com/skills/leamsigc/shortsgenerator/twitter-research-report)

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