agentleFS
frankxaifrankxai/creator-skills/AGENTS.md

creator-skills

AGENTS.md6 starsChanged 47 days agoMITView on GitHub

Public skills catalog. Everything here ships to strangers' machines via npx skills add frankxai/creator-skills.

The file

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

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

  • ≈1

    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. Common:

    No secrets, no user paths, no client or employer specifics.

    line 26
  2. Distinctive:

    No emoji in skill bodies or the README.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.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
AGENTS.md

creator-skills — repo conventions

Public skills catalog. Everything here ships to strangers' machines via npx skills add frankxai/creator-skills.

Layout

  • skills/<category>/<name>/SKILL.md — one skill per folder. Categories: video, music, images, brand, reviews, growth.
  • Growth skills plan and stage only: they never post, send, schedule, spend or set prices, and they tell the agent to fetch platform facts from official pages with a read date instead of hard-coding them. Each ships evals/evals.json.
  • Supporting files live beside the SKILL.md (references/, *.json). No nested skill directories.

Skill rules

  • Frontmatter keys: name (kebab-case, must equal the folder name), description (the trigger surface, max 1024 chars), optional version, argument-hint, allowed-tools. Nothing else.
  • The description says WHEN to fire, not what the file contains.
  • Bodies are portable: no personal paths, no machine-specific setup, no references to private repos or internal systems.
  • Engines are referenced, never vendored: skills shipped by vendors (Higgsfield CLI skills, HyperFrames skills) are prerequisites the router dispatches to — do not copy third-party SKILL.md files into this repo.
  • Paid services are named in the skill's first section; env-var patterns only, never literal credentials. Affiliate relationships are disclosed where relevant.

Gates — run before any commit

  • node scripts/validate-skills.mjs must pass (frontmatter schema + banned-pattern scan).
  • New skill → add its Catalog row in README.md.

Never

  • No secrets, no user paths, no client or employer specifics.
  • No emoji in skill bodies or the README.
  • This repo is the source of truth; local runtimes consume it via scripts/sync-to-local.ps1, never the reverse.

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.