agentleFS
IgorGanapolskyIgorGanapolsky/ThumbGate/.agents/skills/skool-headless-reader/SKILL.md

skool-headless-reader

Skill29 starsChanged 7 months agoMITView on GitHub

Read, monitor, and analyze Skool communities or posts headlessly for lead discovery, customer pain, acquisition opportunities, or ThumbGate revenue research without blocking the user's browser.

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 8 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use the user's Comet, Chrome, or Computer Use session first.

    line 14
  2. Distinctive:

    Do not post, comment, DM, scrape private data, or take write actions.

    line 15
  3. Very specific:

    Use cookies only through the SKOOL_COOKIE environment variable when a private group requires auth.

    line 16
  4. Very specific:

    Keep outputs focused on revenue: pain, buyer intent, possible ThumbGate angle, and a concrete next action.

    line 17
  5. Distinctive:

    Read a public community:

    line 21
  6. Very specific:

    Use --post-limit to read more posts before returning the top --limit signals.

    line 33
  7. Distinctive:

    Run the local MCP server:

    line 35
  8. Distinctive:

    Read the community overview to identify categories, member count, and visible post volume.

    line 49
  9. Distinctive:

    Look for Claude Code, Codex, Cursor, MCP, n8n, GitHub, Supabase, Vercel, token cost, and broken automation workflows.

    line 51
  10. Very specific:

    Keep outreach non-spam: give useful diagnosis first, then mention ThumbGate only where the reliability problem is direct.

    line 53
  11. Distinctive:

    If a group is not publicly SSR-readable, supply an operator-provided cookie header through the environment without storing it:

    line 57
  12. Distinctive:

    Never save that cookie in repo files, memories, PR text, logs, or test fixtures.

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skool Headless Reader

Overview

Use this skill when a task asks to inspect Skool communities, find revenue opportunities in Skool, summarize Skool posts, or mine AI automation communities for ThumbGate acquisition signals. It uses direct HTTP reads and the local MCP connector instead of the user's logged-in browser, so the user can keep working.

Operating Rules

  • Do not use the user's Comet, Chrome, or Computer Use session first. Start with the headless reader.
  • Do not post, comment, DM, scrape private data, or take write actions. Draft replies or outreach only unless the user explicitly authorizes posting.
  • Use cookies only through the SKOOL_COOKIE environment variable when a private group requires auth. Never print, commit, or persist cookies.
  • Keep outputs focused on revenue: pain, buyer intent, possible ThumbGate angle, and a concrete next action.

Quick Start

Read a public community:

node scripts/skool-reader.js --community ai-automation-society --limit 10 --format json

Rank ThumbGate revenue signals:

node scripts/skool-reader.js --url https://www.skool.com/ai-automation-society --category "Support Needed" --signals --format markdown

Use --post-limit to read more posts before returning the top --limit signals.

Run the local MCP server:

node adapters/skool/server-stdio.js

Useful MCP tools:

  • skool_read_community: return normalized categories, posts, and engagement.
  • skool_revenue_signals: rank posts for ThumbGate acquisition opportunities.
  • skool_post_detail: read a single Skool post URL.

Revenue Workflow

  1. Read the community overview to identify categories, member count, and visible post volume.
  2. Prioritize Support Needed, Hire Me / Looking For Hire, Wins, and high-comment posts.
  3. Look for Claude Code, Codex, Cursor, MCP, n8n, GitHub, Supabase, Vercel, token cost, and broken automation workflows.
  4. Produce a lead list with post URL, pain, ThumbGate angle, and draft reply.
  5. Keep outreach non-spam: give useful diagnosis first, then mention ThumbGate only where the reliability problem is direct.

Private Groups

If a group is not publicly SSR-readable, supply an operator-provided cookie header through the environment without storing it:

SKOOL_COOKIE='skool_session=...' node scripts/skool-reader.js --community private-community --signals

Never save that cookie in repo files, memories, PR text, logs, or test fixtures.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.