Run any Skill in Manus with one click

$pwd:

tweet-series-extractor

Name: Tweet Series Extractor
Author: vishalsachdev

// Extract tweet series from X/Twitter profiles with full content, links, and engagement metrics. Use when: (1) User provides a tweet URL and wants similar tweets by the same author, (2) User asks to "extract tweets", "collect tweet series", or "scrape tweets", (3) User wants to analyze a user's recurring tweet format (e.g., daily updates, weekly roundups), (4) User needs tweet content with embedded links preserved for analysis. Requires Chrome browser automation tools (mcp__claude-in-chrome__*).

Run Skill in Manus

$ git log --oneline --stat

stars:4

forks:1

updated:May 2, 2026 at 17:28

SKILL.md

readonly

name

tweet-series-extractor

description

Extract tweet series from X/Twitter profiles with full content, links, and engagement metrics. Use when: (1) User provides a tweet URL and wants similar tweets by the same author, (2) User asks to "extract tweets", "collect tweet series", or "scrape tweets", (3) User wants to analyze a user's recurring tweet format (e.g., daily updates, weekly roundups), (4) User needs tweet content with embedded links preserved for analysis. Requires Chrome browser automation tools (mcp__claude-in-chrome__*).

Tweet Series Extractor

Extract recurring tweet series from X/Twitter with content, links, and engagement metrics.

Prerequisites

Load Chrome tools before use:

ToolSearch: select:mcp__claude-in-chrome__tabs_context_mcp
ToolSearch: select:mcp__claude-in-chrome__navigate
ToolSearch: select:mcp__claude-in-chrome__get_page_text
ToolSearch: select:mcp__claude-in-chrome__read_page
ToolSearch: select:mcp__claude-in-chrome__javascript_tool

Workflow

1. Initialize Browser

mcp__claude-in-chrome__tabs_context_mcp(createIfEmpty: true)

2. Navigate to Seed Tweet

mcp__claude-in-chrome__navigate(url: "https://x.com/username/status/ID", tabId: <id>)

3. Extract Tweet Content

mcp__claude-in-chrome__get_page_text(tabId: <id>)

Returns: Title, URL, full article text, engagement metrics inline.

4. Extract Links from Tweet

// Use javascript_tool with this code:
var links = [];
document.querySelectorAll('article a').forEach(function(a) {
  if (a.href && a.href.length > 10) links.push(a.href);
});
links.slice(4, 50).join(' | ')

slice(4, 50) skips profile/header links
Returns pipe-separated URLs

5. Find Similar Tweets on Profile

Navigate to profile and scroll:

mcp__claude-in-chrome__navigate(url: "https://x.com/username", tabId: <id>)
mcp__claude-in-chrome__javascript_tool(text: "window.scrollBy(0, 2000); 'scrolled'")
mcp__claude-in-chrome__read_page(tabId: <id>, depth: 12)

Look for articles with matching title patterns (e.g., "Welcome to [Date]"). Extract tweet URLs from href="/username/status/ID" links.

6. Collect Each Tweet

For each found tweet URL, repeat steps 2-4.

Parsing Engagement Metrics

Metrics appear in page text after the timestamp:

6:12 AM · Jan 24, 2026·33.7K Views
80 68 594 163

Format: replies reposts likes bookmarks

Also found in group elements:

group "80 replies, 68 reposts, 594 likes, 163 bookmarks, 33738 views"

Output JSON Structure

{
  "author": {
    "name": "Display Name",
    "handle": "@username",
    "profile_url": "https://x.com/username"
  },
  "series": "Pattern description",
  "collected_at": "YYYY-MM-DD",
  "tweets": [
    {
      "date": "Month DD, YYYY",
      "url": "https://x.com/username/status/ID",
      "engagement": {
        "replies": 0,
        "reposts": 0,
        "likes": 0,
        "bookmarks": 0,
        "views": 0
      },
      "content": "Full tweet text...",
      "links": [
        {"text": "anchor text", "url": "https://..."}
      ]
    }
  ]
}

Tips

Scroll profile multiple times to load more tweets
Tweet URLs follow pattern: /username/status/ID
Articles are X's long-form format with embedded links
Use read_page with depth: 12 for full tweet visibility
Parse link text from the generic elements near link refs

related-skills.json

same repository

llm-council.md

from "vishalsachdev/claude-code-skills"

Convene a 3-model council (Claude + GPT via codex CLI + Gemini CLI) on a high-stakes decision. Forces cross-critique between members and surfaces where they actually disagree, breaking Claude's default agreeableness. Use when the user asks to "convene a council", "get a second opinion", "ask GPT and Gemini", "what would other models say", or has an architecture / strategy / hiring / pricing decision where being wrong is expensive. Skip for factual questions, code with one right answer, or anything premortem-shaped (route to premortem skill instead).

2026-05-024

agentic-eval-first-development.md

from "vishalsachdev/claude-code-skills"

Architect, execute, and iterate on AI evaluations using the Data-Task-Score framework. Treats evals as the modern, quantifiable version of a PRD. Use when the user asks to "build an eval," "improve model quality," "test an agent workflow," "quantify product intuition," "move beyond vibe checks," "measure AI output," "score LLM responses," "benchmark a prompt," or "set up evaluation infrastructure." Also triggers on phrases like "how do I know if this is working," "is the model getting better," or "eval-driven development."

2026-05-024

codebase-singularity.md

from "vishalsachdev/claude-code-skills"

Apply the codebase singularity approach: reliable codebase understanding and change with a repeatable workflow, guardrails, and verification gates. Use for repo work (feature, bugfix, refactor, migration) when you need high trust, minimal diffs, and explicit validation and exit criteria.

2026-05-024

start-session.md

from "vishalsachdev/claude-code-skills"

Use when user says "let's get started", "where are we", or at beginning of a session. Reads project context from CLAUDE.md, checks git status and recent commits, and provides orientation for the session. Works across all repo types (code, research, mixed).

2026-05-024

wrap-up-session.md

from "vishalsachdev/claude-code-skills"

Use when user says "let's wrap up", "close shop", "done for today", or wants to end a session. Handles session wrap-up including git operations, documentation updates, roadmap updates, and preparing for next session. Works across all repo types.

2026-05-024

premortem.md

from "vishalsachdev/claude-code-skills"

Run a premortem on a plan, launch, product, hire, strategy, or decision — assumes it failed 6 months from now and works backward to find every reason why, then produces a revised plan. Use when the user has a concrete plan or commitment with high cost-of-being-wrong and asks to "premortem", "stress test", "find blind spots", "poke holes", "what could kill this", or "what am I missing". Skip for vague ideas without a plan, simple feedback requests, factual questions, or already-irreversible decisions.

2026-05-024

package.json

"author": "vishalsachdev"

"repository": "vishalsachdev/claude-code-skills"

View GitHub Repository View Creator Repositories

$ install --global

$ download --local

Run Skill in Manus

$ useful --forSOC

Software DevelopersComputer and Mathematical Occupations15-1252L4

name

tweet-series-extractor

description

Tweet Series Extractor

Extract recurring tweet series from X/Twitter with content, links, and engagement metrics.

Prerequisites

Load Chrome tools before use:

ToolSearch: select:mcp__claude-in-chrome__tabs_context_mcp
ToolSearch: select:mcp__claude-in-chrome__navigate
ToolSearch: select:mcp__claude-in-chrome__get_page_text
ToolSearch: select:mcp__claude-in-chrome__read_page
ToolSearch: select:mcp__claude-in-chrome__javascript_tool

Workflow

1. Initialize Browser

mcp__claude-in-chrome__tabs_context_mcp(createIfEmpty: true)

2. Navigate to Seed Tweet

mcp__claude-in-chrome__navigate(url: "https://x.com/username/status/ID", tabId: <id>)

3. Extract Tweet Content

mcp__claude-in-chrome__get_page_text(tabId: <id>)

Returns: Title, URL, full article text, engagement metrics inline.

4. Extract Links from Tweet

// Use javascript_tool with this code:
var links = [];
document.querySelectorAll('article a').forEach(function(a) {
  if (a.href && a.href.length > 10) links.push(a.href);
});
links.slice(4, 50).join(' | ')

slice(4, 50) skips profile/header links
Returns pipe-separated URLs

5. Find Similar Tweets on Profile

Navigate to profile and scroll:

mcp__claude-in-chrome__navigate(url: "https://x.com/username", tabId: <id>)
mcp__claude-in-chrome__javascript_tool(text: "window.scrollBy(0, 2000); 'scrolled'")
mcp__claude-in-chrome__read_page(tabId: <id>, depth: 12)

Look for articles with matching title patterns (e.g., "Welcome to [Date]"). Extract tweet URLs from href="/username/status/ID" links.

6. Collect Each Tweet

For each found tweet URL, repeat steps 2-4.

Parsing Engagement Metrics

Metrics appear in page text after the timestamp:

6:12 AM · Jan 24, 2026·33.7K Views
80 68 594 163

Format: replies reposts likes bookmarks

Also found in group elements:

group "80 replies, 68 reposts, 594 likes, 163 bookmarks, 33738 views"

Output JSON Structure

{
  "author": {
    "name": "Display Name",
    "handle": "@username",
    "profile_url": "https://x.com/username"
  },
  "series": "Pattern description",
  "collected_at": "YYYY-MM-DD",
  "tweets": [
    {
      "date": "Month DD, YYYY",
      "url": "https://x.com/username/status/ID",
      "engagement": {
        "replies": 0,
        "reposts": 0,
        "likes": 0,
        "bookmarks": 0,
        "views": 0
      },
      "content": "Full tweet text...",
      "links": [
        {"text": "anchor text", "url": "https://..."}
      ]
    }
  ]
}

Tips

Scroll profile multiple times to load more tweets
Tweet URLs follow pattern: /username/status/ID
Articles are X's long-form format with embedded links
Use read_page with depth: 12 for full tweet visibility
Parse link text from the generic elements near link refs

tweet-series-extractor

Tweet Series Extractor

Prerequisites

Workflow

1. Initialize Browser

2. Navigate to Seed Tweet

3. Extract Tweet Content

4. Extract Links from Tweet

5. Find Similar Tweets on Profile

6. Collect Each Tweet

Parsing Engagement Metrics

Output JSON Structure

Tips

More from this repository

Tweet Series Extractor

Prerequisites

Workflow

1. Initialize Browser

2. Navigate to Seed Tweet

3. Extract Tweet Content

4. Extract Links from Tweet

5. Find Similar Tweets on Profile

6. Collect Each Tweet

Parsing Engagement Metrics

Output JSON Structure

Tips

More from this repository