agentleFS
glitterpixelyglitterpixely/skills/AGENTS.md

skills

AGENTS.md6 starsChanged 7 days agoMITView on GitHub

This repository owns these six skills: h3-prompt-writing, kling-4-prompting, minimax-music-30, seedance-25, suno-song-builder, and threejs-rendering. Preserve their complete reference, script, template, and agent-metadata folders. Do not publish unrelated installed skills or private creative assets. The owner's requested workflow is to update this repository whenever we update these skills locally. A Git-backed installation uses this checkout directly, while separate local skill directories should be kept in sync when updated. A post-commit hook (.git/hooks/post-commit) and ./optimize_skills.sh (also wired to launchd com.glitterpixely.skills-autopush in --changed-only mode)…

  • Commits and pushes
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository6 other files it gives its agents.

The file

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

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read back the remote branch with git ls-remote origin refs/heads/<branch> and compare its SHA with the pushed local commit.

    line 16
  2. Distinctive:

    Run from this repository root:

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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

Working on this skills library

Scope

This repository owns these six skills: h3-prompt-writing, kling-4-prompting, minimax-music-30, seedance-25, suno-song-builder, and threejs-rendering. Preserve their complete reference, script, template, and agent-metadata folders. Do not publish unrelated installed skills or private creative assets.

Local edits and GitHub updates

The owner's requested workflow is to update this repository whenever we update these skills locally. A Git-backed installation uses this checkout directly, while separate local skill directories should be kept in sync when updated.

  1. Confirm the checkout and origin are for glitterpixely/skills. Inspect the current branch, working-tree diff, and staged changes before editing. Read CONTRIBUTING.md.
  2. Fetch origin. If the working tree is clean and the checked-out branch tracks the intended remote branch, use git pull --ff-only. Preserve existing work; never reset, overwrite, auto-stash, or force-push to resolve divergence. If concurrent edits or conflicts make intent unclear, ask the owner.
  3. Edit the relevant skill files in the checkout. If an edit was made in a separate installed copy, compare it with the checkout and transfer only the intended changes; do not blindly mirror the whole skills directory.
  4. Review the diff and run the relevant checks below. Preserve exact provider grammar and source attributions. Never commit credentials, private user materials, generated outputs, or machine-specific backups.
  5. Stage only the reviewed task files, inspect git diff --cached and git diff --cached --check, then create a descriptive commit. The owner has pre-authorized automatic commit and git push origin main after each validated change to the repository skills (h3-prompt-writing, kling-4-prompting, minimax-music-30, seedance-25, suno-song-builder, threejs-rendering) without pausing for confirmation. Do not publish unrelated staged work.
  6. Read back the remote branch with git ls-remote origin refs/heads/<branch> and compare its SHA with the pushed local commit. Only report synchronization after they match. On a push/authentication failure, retain local work and report that GitHub is not yet updated.

A post-commit hook (.git/hooks/post-commit) and ./optimize_skills.sh (also wired to launchd com.glitterpixely.skills-autopush in --changed-only mode) automatically validate, sync installed copies in ~/.gemini/config/skills/, commit, and push after each skill change.

Validation

Run from this repository root:

python3 h3-prompt-writing/scripts/validate_coverage.py
python3 h3-prompt-writing/scripts/lint_h3_prompt.py --self-test
python3 seedance-25/scripts/validate_coverage.py
python3 seedance-25/scripts/prompt_lint.py --self-test
python3 minimax-music-30/scripts/validate_coverage.py
python3 minimax-music-30/scripts/lint_music_prompt.py --self-test
python3 threejs-rendering/scripts/validate_coverage.py
node threejs-rendering/scripts/physical.mjs

For Kling and Suno, check frontmatter and local reference links, and review the changed guidance. For shared documentation, verify links and instructions. Passing these checks is not proof of generated video or music quality.

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.