agentleFS
bradautomatesbradautomates/content-ideas/CLAUDE.md

content-ideas

CLAUDE.md109 starsChanged 6 months agoMITView on GitHub

A cross-host skill that turns competitor activity into a daily "For You" feed of content ideas. Runs the same on Claude Code and Codex (and any host that reads AGENTS.md). Dependency-free Python (stdlib only) plus a single self-contained HTML renderer. The skill resolves its own directory from the Codex cache, the Claude plugin cache, or a repo checkout — see the resolution block at the top of SKILL.md. Keep that block in sync if directory names change.

  • Reads credentials
  • Installs packages
  • In this repositoryOne other file it gives its agents.

The file

We split this CLAUDE.md into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Keep that block in sync if directory names change.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

content-ideas plugin

A cross-host skill that turns competitor activity into a daily "For You" feed of content ideas. Runs the same on Claude Code and Codex (and any host that reads AGENTS.md). Dependency-free Python (stdlib only) plus a single self-contained HTML renderer.

Structure

  • skills/content-ideas/SKILL.md — canonical skill definition (the entry point)
  • skills/content-ideas/scripts/scrape.py — competitor/own-channel scraper
  • skills/content-ideas/scripts/generate_feed.py — builds the For You HTML feed
  • skills/content-ideas/scripts/lib/ — platform fetchers, scoring, relevance, rendering
  • skills/content-ideas/assets/for-you-template.html — renderer template
  • skills/content-ideas/references/content-strategy.md — idea-generation guidance

Cross-host packaging

  • .claude-plugin/plugin.json + marketplace.json — Claude Code install
  • .codex-plugin/plugin.json ("skills": "./skills/") — Codex install
  • AGENTS.md → @CLAUDE.md — Codex / generic-agent entry point
  • commands/content-ideas.md — Claude Code slash command
  • hooks/hooks.json — SessionStart setup preflight (one-line hint, silent when ready)

The skill resolves its own directory from the Codex cache, the Claude plugin cache, or a repo checkout — see the resolution block at the top of SKILL.md. Keep that block in sync if directory names change.

Commands

# run the test suite (stdlib + pytest, no network)
python3 -m pytest -q

# exercise the scraper / feed generator directly against a checkout
python3 skills/content-ideas/scripts/scrape.py --help
python3 skills/content-ideas/scripts/generate_feed.py --help

Rules

  • Runtime stays dependency-free: stdlib only (urllib, json, ...). No pip installs at runtime.
  • skills/content-ideas/scripts/lib/__init__.py is a bare package marker — no eager imports.
  • Persistent state lives under $CONTENT_HOME (default ~/Documents/Content), never the cwd.
  • Credentials live in ~/.config/content/.env (SCRAPECREATORS_API_KEY, SETUP_COMPLETE).
  • Version is tracked in pyproject.toml, .claude-plugin/plugin.json, .claude-plugin/marketplace.json, .codex-plugin/plugin.json, and the version: field of SKILL.md — keep them identical. tests/test_plugin_contract.py enforces this.

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.