luabaggluabagg/agent-skills/AGENTS.md

agent-skills

AGENTS.md3 starsChanged 3 months agoMITView on GitHub

This repository is the public source of truth for Luan Baggio's personal agent skills, curated third-party skill list, and related agent tooling references.

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 repository9 other files it gives its agents.
- agentfolio-operatorSkill
- branch-portSkill
- code-commentsSkill
- code-namingSkill
- cognitive-refactorSkill
- memory-palaceSkill
- natural-copy-editingSkill
- testing-business-rulesSkill
- thorough-pr-reviewSkill

The file

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

7 rules. About 1 is common, 1 is distinctive, and 5 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.
5
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific
could be automatic: a setting could enforce it

Very specific:
Use agentfolio-operator to choose Agentfolio profiles.
line 10
Distinctive:
Keep Agentfolio harness-agnostic.
line 11
Very specific:
Do not copy third-party skill folders into skills/ unless you fork the skill.
line 16
Common:
Do not commit tokens, org IDs, internal URLs, API keys, or generated memory.
line 17
Very specific:
Use npx skills / agent-skills list skills to verify skill discovery after changing skills/.
line 21
Very specific:
Keep node_modules/ out of git.
line 23
Very specific:
Treat package-lock.json as the npm dependency lockfile for repo tooling.
line 24

≈ “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

Agent Instructions

This repository is the public source of truth for Luan Baggio's personal agent skills, curated third-party skill list, and related agent tooling references.

Repository Model

This repo is Agentfolio collection #1. collection.yaml declares profiles and ordered harness actions.
scripts/agentfolio-adapter.mjs implements collection actions through the existing agent-skills setup commands.
Personal skills live in skills/<skill-name>/SKILL.md.
Use agentfolio-operator to choose Agentfolio profiles. Do not edit live harness files by hand.
Keep Agentfolio harness-agnostic. Collection-owned adapters and setup scripts live in this repo.
Third-party skills that npx skills can install belong in curated-skills.json sources.
Plugin-style skill references belong in curated-skills.json pluginReferences.
Non-skill tools belong in curated-tools.json.
Harness manifests live under harnesses/; their actions stay collection-owned and profile-selected.
Do not copy third-party skill folders into skills/ unless you fork the skill.
Do not commit tokens, org IDs, internal URLs, API keys, or generated memory.

Repository Editing Rules

Use npx skills / agent-skills list skills to verify skill discovery after changing skills/.
Validate JSON manifests after edits.
Keep node_modules/ out of git.
Treat package-lock.json as the npm dependency lockfile for repo tooling.

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