agentleFS
matthewdonsemail-labmatthewdonsemail-lab/log/.claude/skills/log-inbox-rea-looksmaxxing/SKILL.md

log-inbox-rea-looksmaxxing

Skill63 starsChanged 2 days agoMITView on GitHub

/rea-looksmaxxing: moneymaxx like a creator. A log play (docs/useCases/inbox/reaLooksmaxxing.md): Reverse engineer how a creator gets paid, then run the same play on your own accounts. [treg](https://treg.to/?ref=matthewdonse-aebsh) reads the social data (the creator's most viral clips, the clip farms reposting them, views and comments), the formula is decoded from what won, and log posts it through your accounts and funnels everyone who replies or DMs into your offer, every message checked against how you write. Clavicular is the worked example: 40 of his clips pulled, the top one at 8.44M views, a looksmaxxing program as the offer. The video and the page (`log.listeningkit.com/rea-looksmaxxing`) tell the same play.

  • Pipes a download into a shell

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Social data costs money: Search and page reads through treg are free with TinyFish, but platform data (TikTok, Instagram, X posts and …

    line 39
  2. Distinctive:

    The numbers are real, the scores are not: Every view count keeps its source URL.

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

/rea-looksmaxxing: moneymaxx like a creator

This is the log play inbox/reaLooksmaxxing. Before anything else, call the log MCP tool getGuide({ useCase: "inbox/reaLooksmaxxing" }): it returns this page and makes it the session's play, so every log tool's answer says which step you are on and a send with no play loaded is refused (rules 157, 158). Then follow the steps in order.

Draft every message from that person's own thread and matt's real replies (voice with no text, search), never from memory, and never send two that read alike (sameAsSent).

Reverse engineer how a creator gets paid, then run the same play on your own accounts. treg reads the social data (the creator's most viral clips, the clip farms reposting them, views and comments), the formula is decoded from what won, and log posts it through your accounts and funnels everyone who replies or DMs into your offer, every message checked against how you write. Clavicular is the worked example: 40 of his clips pulled, the top one at 8.44M views, a looksmaxxing program as the offer. The video and the page (log.listeningkit.com/rea-looksmaxxing) tell the same play.

How the owner asks for it: "/rea-looksmaxxing how clavicular gets paid", "moneymaxx like <creator>", "how does <creator> get paid"

Run it from a fresh context

Say: "go on docs/useCases/inbox/reaLooksmaxxing.md for <creator> and <offer>". The agent reads this page and treg's web-access skill, loads getGuide({ topic: "xSending" }) before anything on X, and runs the steps. Outside this repo the same play is the rea-looksmaxxing skill: curl -fsSL https://log.listeningkit.com/install.sh | sh -s -- --skills rea-looksmaxxing --skillsOnly installs it with treg's treg and web-access skills beside it (on Windows, set LOG_SKILLS=rea-looksmaxxing and LOG_SKILLS_ONLY=1 before irm https://log.listeningkit.com/install.ps1 | iex), and npx skills add log.listeningkit.com finds it too.

The steps

#StepToolDone when
1Find the creator's clips and the clip farms around them. Search treg's catalog by the job ("tiktok search videos", "tiktok user posts", "instagram user reels", "x user tweets"), never a remembered id. Say the price before the batch and cap it with X-Treg-Route-Max-Costtreg catalog search, catalog get, callevery clip with its account, caption, views, likes, date and URL
2Decode the formula: sort the top clips into formats, count the views per format, and note the hook, the tension and the payoff of the best one in each. Find how the creator sells (a program, a Discord, merch, a link in bio)the agentthe 3 formats with the most views, each with its proof clip, and the funnel
3Check every account the play runs on is signed intwitterSessionCheck, instagramSessionCheck, discordSessionCheckthe platform says loggedIn
4Write the posts in the winning formats, in the owner's voice, never copied. One goes out with twitterPostLive; several through the account's one queue at random timestwitterPost, twitterPostLive, or twitterQueueBuild, twitterQueuePlan, twitterQueueRunLiveX answers sent
5See who replied, liked or followedtwitterNotificationsa list of real people and what they did
6Read each person's whole thread before a word is writtentwitterDms { with }, instagramDms, discordReadwhat they asked and where the talk stands
7Draft the answer in the owner's voice and gate it against the same personvoice { to, with, context }, then voice with textthe gate passes
8Answer them, then point them at the offer once they're keen. The first message is about them, never the pitchtwitterReplyLive, twitterDmLive, instagramSendLive, discordSendLive, or for a DM on the account's own platform messagesSendLive { account, chat, text, approvedBy: "<owner>", confirmLive: true } after its dry run messagesSendthe platform answers sent, and they're in the Discord or on the offer

What to know

  • Social data costs money. Search and page reads through treg are free with TinyFish, but platform data (TikTok, Instagram, X posts and comments) costs cents a call. Say the price first and cap every batch (rule 41).
  • The numbers are real, the scores are not. Every view count keeps its source URL. A format score is the agent's reading of the views, not a fact.
  • Sends follow the account's rules. Reads first, every …Live tool needs confirmLive: true, one session per account, never in quick succession, and a 429 or any refusal stops the run (rules 8, 94, 105).
  • Sell the outcome. Step 7 of the video says to build the offer on people's insecurities and adds "we don't recommend it". The play doesn't either.
  • The video's beats, copy rules and render steps are in the reaLooksmaxxing skill (skills/reaLooksmaxxing/SKILL.md); the play everyone can install is skills/published/reaLooksmaxxing/SKILL.md.

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.