agentleFS
williamhorschak-devwilliamhorschak-dev/wisconsin-legal-ai-skills/AGENTS.md

wisconsin-legal-ai-skills

AGENTS.md3 starsChanged 6 days agoMITView on GitHub

Canonical skills live in skills/. Keep each skill independently usable with its references, scripts, license, and optional host metadata. Provider adapters must not duplicate or weaken substantive legal guidance. The maintainer is a nonlawyer publishing tools only. Follow LEGAL_NOTICE.md and CONTRIBUTING.md: public support is technical collaboration, not individual legal advice or confidential intake. Do not imply that the maintainer represents users, reviews their matters, or approves generated legal conclusions. Keep the standalone skill notices identical to the root notice and…

  • 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 33,315 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 repository3 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. Distinctive:

    Verify material legal corrections against current primary sources and record the retrieval date and affected scope in the assessment/source …

    line 13
  2. Very specific:

    Keep Git authorship with the human contributors.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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

Maintaining this repository

Canonical skills live in skills/. Keep each skill independently usable with its references, scripts, license, and optional host metadata. Provider adapters must not duplicate or weaken substantive legal guidance.

The maintainer is a nonlawyer publishing tools only. Follow LEGAL_NOTICE.md and CONTRIBUTING.md: public support is technical collaboration, not individual legal advice or confidential intake. Do not imply that the maintainer represents users, reviews their matters, or approves generated legal conclusions. Keep the standalone skill notices identical to the root notice and include them in prompt exports.

Verify material legal corrections against current primary sources and record the retrieval date and affected scope in the assessment/source notes. Preserve the author's style as a preference, not a mandatory statewide rule. Use synthetic facts in tests and templates; do not add private matter records, credentials, source archives, or paid content to this public repository.

Run python -m unittest discover -s tests -v and python scripts/skill_tools.py validate after consequential changes. Rebuild affected JSON-backed templates into a scratch directory and inspect the rendered pages before replacing the bundled DOCX assets. Update manifests only after reviewing changes.

Structural validation, script tests, source checks, and visual checks answer different questions. Report their limits. Do not describe a generated document as filing-ready solely because a script or linter passed.

Keep Git authorship with the human contributors. Do not add AI-provider co-author trailers or generated-by signatures to commits or pull requests. The shared .claude/settings.json disables Claude Code's automatic attribution; see the attribution setting.

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.