kenashekenashe/x-article-toolkit/llms.txt

x-article-toolkit

llms.txt2 starsChanged 42 days agoMITView on GitHub

Model-neutral methodology for X Article headlines, hooks and covers, ported from research-based skills by @fuckgrowth (Sep 2026). Plain Markdown that any AI agent can follow; scripts and the dataset are optional. Start with AGENTS.md. Version 1.0.0. Repository: https://github.com/kenashe/x-article-toolkit. All links below are raw files on the main branch. Headline candidates for an X Article draft, scored against seven measured moves and four failure marks (levels L0 to L4). Two-line openings (the ~130 visible characters on the card) for a locked…

In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- cover-writerSkill
- headline-writerSkill
- hook-writerSkill

The file

Create a free account to mount

Files

llms.txt

# x-article-toolkit

> Model-neutral methodology for X Article headlines, hooks and covers, ported from research-based skills by @fuckgrowth (Sep 2026). Plain Markdown that any AI agent can follow; scripts and the dataset are optional. Start with AGENTS.md.

Version 1.0.0. Repository: https://github.com/kenashe/x-article-toolkit. All links below are raw files on the `main` branch.

## Start here

- [AGENTS.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/AGENTS.md): Instructions for any AI agent: load order, capabilities, hard rules.
- [workflows/x-article-publishing.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/workflows/x-article-publishing.md): The full pipeline with locks and the X ARTICLE PACKAGE output format.

## headline-writer

Headline candidates for an X Article draft, scored against seven measured moves and four failure marks (levels L0 to L4).

- [skills/headline-writer/SKILL.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/headline-writer/SKILL.md): read in this order (~1945 tokens)
- [skills/headline-writer/rules.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/headline-writer/rules.md): read in this order (~2794 tokens)
- [skills/headline-writer/templates.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/headline-writer/templates.md): read in this order (~927 tokens)
- [skills/headline-writer/scripts/headline_check.py](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/headline-writer/scripts/headline_check.py): optional scoring script, Python 3 standard library

## hook-writer

Two-line openings (the ~130 visible characters on the card) for a locked headline. Requires: locked headline.

- [skills/hook-writer/SKILL.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/hook-writer/SKILL.md): read in this order (~1723 tokens)
- [skills/hook-writer/rules.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/hook-writer/rules.md): read in this order (~1050 tokens)
- [skills/hook-writer/templates.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/hook-writer/templates.md): read in this order (~1184 tokens)
- [skills/hook-writer/scripts/hook_check.py](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/hook-writer/scripts/hook_check.py): optional scoring script, Python 3 standard library

## cover-writer

Cover or no-cover decision; if cover, brief (A to J), cover text, image prompt and 1200 x 480 specs. Requires: locked headline and locked hook.

- [skills/cover-writer/SKILL.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/cover-writer/SKILL.md): read in this order (~2336 tokens)
- [skills/cover-writer/rules.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/cover-writer/rules.md): read in this order (~1300 tokens)
- [skills/cover-writer/briefs.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/cover-writer/briefs.md): read in this order (~1427 tokens)
- [skills/cover-writer/scripts/cover_check.py](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/skills/cover-writer/scripts/cover_check.py): optional scoring script, Python 3 standard library

## Context

- [SOURCES.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/SOURCES.md): Original article, research, dataset and skills by @fuckgrowth; reuse terms.
- [shared/research/README.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/shared/research/README.md): What the research establishes and what it does not.
- [shared/data/README.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/shared/data/README.md): The external dataset: editions, columns, how to fetch it.
- [state/README.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/state/README.md): Optional personalization and performance-tracking interface.
- [PROVENANCE.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/PROVENANCE.md): Which files are original, ported or added.

## Optional

- [toolkit.json](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/toolkit.json): this index, machine-readable
- [adapters/generic/README.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/adapters/generic/README.md): copy-paste instructions for any agent runtime
- [optional/x-articles-finder/README.md](https://raw.githubusercontent.com/kenashe/x-article-toolkit/main/optional/x-articles-finder/README.md): the paid data collector, evaluated separately, not a dependency

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.

Check your setup, free