name: twitter-research-report version: 4.0.0 description: | 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) via the shared video-idea-research report script.

allowed-tools:

• Bash
• Read
• Write
• ChromeDevTools

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:

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:

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

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