agentsclimarketplace

Law checker

Skill ellmos-ai/skills/skills/utilities/law-checker

Portable SKILL.md library for Claude Code, Codex-compatible agents, BACH, and local-first LLM workflows

Install
npx -y skills add ellmos-ai/skills --skill law-checker

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Points to the standalone module law-checker ("Legal Department"): source-grounded AI first-look legal assessments for German law with a statute registry and a statute-embodiment agent. Use this skill when a situation, contract, official notice, or legal question under German law should be checked with exact citations (article/section, paragraph, sentence) -- with a clear boundary: AI-assisted first orientation, not a substitute for a lawyer.

SKILL.md

3.9 KB, 715 tokens by cl100k_base, as published. Nobody here has run it

<img src="banner.png" width="100%" alt="law-checker banner">

Deutsch — Offizielle Deutsch-Version / Documento Oficial en Deutsch.

law-checker (Legal Department) -- Pointer Skill (Deutsch)

This skill is a thin pointer (wrapper) to the standalone, public module repository ellmos-ai/law-checker (MIT license, public). The actual skill lives there -- this repository only links to it and documents installation, so the module is discoverable through the central skill catalog.

What the module does

law-checker produces source-grounded AI first-look legal assessments for German law:

  • Statute registry (config.json): togglable statutes; every statute claim must be backed by locally fetched official law texts (article or section, paragraph, sentence where needed, short quote, source, retrieval date).
  • Statute-embodiment agent (agents/gesetzbuch.md): a generic agent that answers "from inside the statute" for any registered law -- scales to arbitrary statutes added to the registry.
  • Separate case-law layer: court decisions are cited only after web verification (court, date, docket number, ECLI where available).
  • Risk and escalation workflow: report format with a risk-level scale, deadline discipline, and a lawyer-specialty routing matrix.

Boundaries (important)

  • AI-assisted first orientation only, not a substitute for individual legal advice, and not performed by a licensed lawyer.
  • Not a law firm, not a hosted legal service, not a deadline calendar.
  • If real legal mail is involved (warning letter, official notice, lawsuit, deadline): secure the original document, note the deadline, and consult a qualified lawyer -- do not automate the matter.

Installation (generic, no local paths)

  1. Clone the module: 
    git clone https://github.com/ellmos-ai/law-checker.git <clone-path>
  2. Adopt <clone-path>/SKILL.md into your own skill environment (e.g. ~/.claude/skills/law-checker/ or the equivalent for your agent runtime).
  3. Set the module path in the adopted SKILL.md and its references to <clone-path> -- do NOT commit real local paths or hostnames into a versioned skill environment.
  4. Load the statute registry: python <clone-path>/_tools/gesetze_fetch.py (fetches the configured official statute texts; the texts themselves are deliberately not in the repo, to avoid redistributing stale portal snapshots).
  5. For structure, license, and liability details, see the module repo's README.

Origin of this pointer skill

This wrapper was added on 2026-07-23 as a showcase entry for the ellmos-ai/skills repository. There is no code duplication -- maintenance and versioning stay solely in the ellmos-ai/law-checker module repo.

Änderungsprotokoll

0.1.0 (2026-07-23)

  • Initial pointer skill for ellmos-ai/law-checker.

Gives 0 of the 12 instructions most quality gates skills give in 715 tokens

Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-06

  • read the output and check the exit codein 55 of 1195, across 14 files
  • verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
  • identify the verification command proving the claimin 53 of 1195, across 12 files
  • run the full verification commandin 51 of 1195, across 11 files
  • verify output confirms the claimin 49 of 1195, across 10 files
  • check version control diff after agent delegationin 45 of 1195, across 5 files
  • state claim with evidencein 43 of 1195, across 3 files
  • run the test suitein 32 of 1195, across 24 files
  • keep state in memory by defaultin 27 of 1195, across 6 files
  • make prototype runnable with one commandin 26 of 1195, across 5 files
  • detect the package manager from lockfilesin 24 of 1195, across 5 files
  • produce a verification reportin 23 of 1195, across 12 files

Said here and by no other author read

  • back statute claims with locally fetched official texts
  • cite court decisions only after web verification
  • include deadline discipline in the risk report
  • secure original documents involving real legal mail
  • consult a qualified lawyer for real legal mail
  • clone the module repository to a local path

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.