Stats
Actions
Tags
From gtm-skills
Scores X/Twitter posts for viral potential using a 19-element heuristic system based on X's published recommendation architecture. Rewrites drafts to improve algorithmic reach and debugs underperforming tweets.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gtm-skills:x-impact-checkerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read bootstrap context before asking questions: `strategy/brand.md` for brand, audience, offer, channels, tools, constraints, and metrics; `about/me.md` for personal voice; `content/ideas.md` and `content/calendar.md` for content planning. Use legacy product-marketing context files only as fallback. Save generated drafts to `content/<platform>/drafts/YYYY-MM-DD_short-topic-slug.md`, and route d...
Read bootstrap context before asking questions: strategy/brand.md for brand, audience, offer, channels, tools, constraints, and metrics; about/me.md for personal voice; content/ideas.md and content/calendar.md for content planning. Use legacy product-marketing context files only as fallback. Save generated drafts to content/<platform>/drafts/YYYY-MM-DD_short-topic-slug.md, and route durable learnings back to strategy/brand.md, about/me.md, or content/ideas.md.
This skill is self-contained for its frontmatter scope: use its local instructions, references, scripts, and assets as the playbook; ask only for missing task-specific inputs; hand off to adjacent skills instead of expanding scope; and return an actionable artifact, decision, plan, draft, or diagnostic.
Analyze X posts for viral potential using a 19-element scoring system and heuristics inspired by X's published recommendation architecture.
| Factor | Max | Scoring Guide |
|---|---|---|
| Reply Potential | 22 | 22: Direct question/debatable claim, 12: Invites response, 4: Statement only |
| Retweet Potential | 16 | 16: Actionable insight/surprising fact, 8: Interesting but niche, 0: No share value |
| Favorite Potential | 12 | 12: Emotionally resonant/personal story, 6: Useful reference, 0: Low appeal |
| Quote Potential | 10 | 10: Strong opinion inviting commentary, 5: Thought-provoking, 0: No quote value |
| Factor | Max | Scoring Guide |
|---|---|---|
| Dwell Time | 6 | 6: Long-form/detailed content, 3: Medium depth, 0: Skimmable |
| Continuous Dwell Time | 4 | 4: Thread/story arc requiring sustained attention, 2: Medium complexity, 0: Quick read |
| Click Potential | 5 | 5: Compelling link with clear CTA, 3: Link with context, 1: Bare URL, 0: No link |
| Photo Expand Potential | 4 | 4: Multiple images/visual storytelling, 2: Single image reference, 0: No visual content |
| Video View Potential | 3 | 3: Long-form video with hook (>5s), 2: Short clip, 0: No video |
| Quoted Click Potential | 3 | 3: Bold claim inviting verification, 2: Interesting claim, 0: Self-contained |
| Factor | Max | Scoring Guide |
|---|---|---|
| Profile Click | 5 | 5: Creates author curiosity, 3: Shows expertise, 0: Generic voice |
| Follow Potential | 4 | 4: Demonstrates ongoing value, 2: Shows potential, 0: One-off content |
| Share Potential | 2 | 2: General sharing value, 1: Limited appeal, 0: No value |
| Share via DM | 2 | 2: Personal/relatable "send to friend" content, 1: Somewhat relatable, 0: Generic |
| Share via Copy Link | 2 | 2: Reference/bookmark worthy, 1: Useful but not evergreen, 0: Ephemeral |
| Risk | Range | Trigger |
|---|---|---|
| Not Interested | -5 to -15 | Clickbait, irrelevant content |
| Mute Risk | -5 to -15 | Repetitive, annoying patterns |
| Block Risk | -10 to -25 | Offensive, aggressive tone |
| Report Risk | -15 to -30 | Policy violations, spam signals |
| Score | Grade |
|---|---|
| 90-100 | S (Exceptional) |
| 75-89 | A (Strong) |
| 60-74 | B (Good) |
| 45-59 | C (Average) |
| 30-44 | D (Below average) |
| 0-29 | F (Low potential) |
Show analysis progress when the host environment supports task tracking:
Score: 🎯 XX/100 (Grade: X)
Breakdown Table:
| Category | Factor | Score | Max | Assessment |
|----------|--------|-------|-----|------------|
| **💬 Core Engagement** | | | 60 | |
| | 💭 Reply Potential | X/22 | 22 | [reason] |
| | 🔄 Retweet Potential | X/16 | 16 | [reason] |
| | ❤️ Favorite Potential | X/12 | 12 | [reason] |
| | 💬 Quote Potential | X/10 | 10 | [reason] |
| **⏱️ Extended Engagement** | | | 25 | |
| | 👀 Dwell Time | X/6 | 6 | [reason] |
| | ⏳ Continuous Dwell Time | X/4 | 4 | [reason] |
| | 🔗 Click Potential | X/5 | 5 | [reason] |
| | 🖼️ Photo Expand | X/4 | 4 | [reason] |
| | 🎥 Video View | X/3 | 3 | [reason] |
| | 🔍 Quoted Click | X/3 | 3 | [reason] |
| **🤝 Relationship Building** | | | 15 | |
| | 👤 Profile Click | X/5 | 5 | [reason] |
| | ➕ Follow Potential | X/4 | 4 | [reason] |
| | 📤 Share Potential | X/2 | 2 | [reason] |
| | 💌 Share via DM | X/2 | 2 | [reason] |
| | 📋 Share via Link | X/2 | 2 | [reason] |
| **⚠️ Negative Signals** | | | | |
| | 😐 Not Interested Risk | -X | 0 to -15 | [reason] |
| | 🔇 Mute Risk | -X | 0 to -15 | [reason] |
| | 🚫 Block Risk | -X | 0 to -25 | [reason] |
| | 🚨 Report Risk | -X | 0 to -30 | [reason] |
| **🏆 TOTAL** | | **XX/100** | | **Grade: X** |
📈 Top 5 Priority Improvements: Specific, actionable suggestions across different categories
✨ Optimized Version: Rewritten post with improvements applied (in original language)
Understanding the underlying models helps explain why the scoring works.
Real-graph — Predicts interaction likelihood between users
SimClusters — Community detection with sparse embeddings
TwHIN — Knowledge graph embeddings mapping users and content topics
Tweepcred — User reputation/authority scoring
Explicit (high weight): Likes, replies, retweets, quote tweets
Implicit (also weighted): Profile visits, link clicks, dwell time, saves/bookmarks
Negative: Block/report (heavily penalized), mute/unfollow, quick scroll-past
| Layer | Strategy |
|---|---|
| Real-graph | Ask questions; create debate; post when followers are active |
| SimClusters | One clear topic; use community language; provide niche value |
| TwHIN | Lead with domain expertise; stay consistent; build topical authority |
| Tweepcred | Reply to quality accounts; avoid engagement bait; engage deeply |
Final Score = Base Score (0-100) + Penalties (-75 to 0)
Normalized Score = max(0, min(100, Final Score))
Penalty capping: total penalties > -20 causes gradual dampening; hard cap at -75.
This skill performs heuristic text-based analysis, not ML prediction. It cannot detect actual media presence, real engagement metrics, author follower count, or network graph relationships. Best used for pre-publishing optimization, not post-hoc analytics.
Detect input language. Respond in same language. Keep optimized version in original language.
When input is in Japanese, display Category and Factor names as: 日本語訳（English Original）
Japanese translations:
See references/algorithm-weights.md for complete weight details from X's open-source algorithm (19-element system).
npx claudepluginhub manojbajaj95/claude-gtm-plugin --plugin gtm-skillsAnalyzes and rewrites tweets using Twitter's algorithm insights (Real-graph, SimClusters, TwHIN) to boost engagement signals like likes, replies, and retweets for maximum reach.
Drafts X (Twitter) tweets and threads in the voice of GTM build-in-public founders, pulling hook patterns from reference accounts and banning LinkedIn/em dashes.
Analyzes Elon Musk's X repost patterns and generates tweets optimized for reposts. Use for viral AI/tech product launches targeting Musk or X reach maximization.