agentleFS
Sign inStart free
haoyuqihaoyuqi/engineering-agent-skills/AGENTS.md

engineering-agent-skills

AGENTS.md0 starsChanged 23 days agoApache-2.0View on GitHub

This repository contains independently installable Agent Skills. Preserve that independence: a Skill may declare an external dependency, but it must not silently depend on another Skill in this repository. Before editing, read docs/skill-quality-standard.md. Keep the main SKILL.md focused on the path every run needs; move branch-specific reference material and long output templates into one-level-deep references/ or assets/ files with an explicit condition for loading them. Every change must preserve the default read-only boundary. A state-changing operation must show its exact…

  • 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 31,700 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

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Before editing, read docs/skill-quality-standard.md.

    line 5
  2. Distinctive:

    Every change must preserve the default read-only boundary.

    line 7
  3. Distinctive:

    Run these checks before claiming completion:

    line 9
  4. Very specific:

    When npm access is available, also run python3 tests/test_installer_compatibility.py and npx --yes skills@1.5.20 add .

    line 30
  5. Distinctive:

    Do not stage, commit, push, publish, or open a PR/MR unless the user explicitly requests that separate delivery action.

    line 32

≈ “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

Repository guidance for coding agents

This repository contains independently installable Agent Skills. Preserve that independence: a Skill may declare an external dependency, but it must not silently depend on another Skill in this repository.

Before editing, read docs/skill-quality-standard.md. Keep the main SKILL.md focused on the path every run needs; move branch-specific reference material and long output templates into one-level-deep references/ or assets/ files with an explicit condition for loading them.

Every change must preserve the default read-only boundary. A state-changing operation must show its exact target and effect, receive user confirmation, and be verified afterward. Never add real organization names, private endpoints, employee or customer data, production logs, credentials, or workstation paths.

Run these checks before claiming completion:

python3 tests/test_repository_structure.py
python3 tests/test_workflow_supply_chain.py
python3 tests/test_compatibility_contract.py
python3 tests/test_configuration_contract.py
python3 tests/test_public_content.py
python3 tests/test_public_content_coverage.py
python3 tests/test_public_content.py --history
python3 tests/test_repository_vulnerability_discovery.py
python3 tests/test_repository_vulnerability_normalization.py
python3 tests/test_repository_vulnerability_audit_runner.py
python3 tests/test_core_eval_fixtures.py
python3 tests/test_evaluation_contract.py
python3 tests/test_evaluation_result_validator.py
python3 tests/test_external_dependency_contract.py
python3 tests/test_template_quality.py
git diff --check

When npm access is available, also run python3 tests/test_installer_compatibility.py and npx --yes skills@1.5.20 add . --list.

Do not stage, commit, push, publish, or open a PR/MR unless the user explicitly requests that separate delivery action.

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