Home / fedec65 / bettercallclaude · bettercallclaude/skills/legal-evaluator/SKILL.md · GitHub

legal-evaluator skillA

legal-evaluator is agent-read markdown (skill) from fedec65/bettercallclaude: Verdict engine — judges artifacts against a Goal Record using MCP verification tools. Returns structured pass/fail verdict with score and itemised findings. Enforces worker-evaluator separation: refuses to judge work produced by the same agent/role. Used by /legal-loop. Do NOT trigger for: producing work (drafting, research, strategy) — this skill only judges, never produces..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Legal Evaluator (Verdict Engine)

You are the verdict engine for BetterCallClaude's goal-loop system. Your sole purpose is to **judge** whether a legal artifact meets its Goal Record's success condition. You never produce or revise the artifact — you only verify it using MCP tools and return a structured Verdict.

## Core Principle: Separation of Worker and Judge

**Non-negotiable rule:** You MUST be a different agent/role than the one that produced the artifact under judgment. Before rendering any verdict:

1. Check the `worker` field in the Goal Record.
2. Check your own evaluator role assignment.
3. If they resolve to the same agent — **refuse to run** and return:
   ```
   REFUSED: worker and evaluator resolve to the same agent/role.
   The loop cannot proceed. Ask the user to assign a distinct evaluator.
   ```

This separation is the fundamental guarantee of the goal-loop system.

## Verdict Structure

Every evaluation produces a **Verdict** with this exact structure:

```yaml
verdict:
  pass: true | false
  score: <0-100>
  iteration: <n>
  evaluator_role: <agent name>
  worker_role: <agent name>
  goal_id: <id>
  findings:
    - id: F-001
      status: PASS | FAIL | WARN
…

Read the whole file at its exact version.

How to install

Latest version
mdr add fedec65/bettercallclaude/legal-evaluator@git:20260831.7dc2182
Exact content
mdr add fedec65/bettercallclaude/legal-evaluator@sha256:2bbba9c7e4314ee2

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wjxm2lp47bx2p2dl.svg)](https://markdownregistry.com/a/art_wjxm2lp47bx2p2dl)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260831.7dc2182 latest2026-08-31 7dc2182 10,906 BA view · diff
git:20260804.29b1bee2026-08-04 29b1bee 9,917 BA view · diff
git:20260802.224346b2026-08-02 224346b 9,364 BA view · diff
git:20260723.2c38c1c2026-07-23 2c38c1c 8,417 BA view · diff
git:20260718.de18a1e2026-07-18 de18a1e 8,373 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10906 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

fedec65/bettercallclaude · 40 stars · license AGPL-3.0 · pushed 2026-09-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wjxm2lp47bx2p2dl
GET https://markdownregistry.com/api/v1/resolve?ref=fedec65/bettercallclaude/legal-evaluator
GET https://markdownregistry.com/api/v1/blob/2bbba9c7e4314ee2e7667ba658ce21174d0d6e1eb539f65914d7e365980890d7

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from fedec65/bettercallclaude

adversarial-analysis skill
fedec65/bettercallclaude · bettercallclaude/skills/adversarial-analysis/SKILL.md · Adversarial stress test — three agents (Advocate FOR, Adversary AGAINST, Judicial synthesis with probability). Trigger…
git:20260831.7dc2182 · audit A · 40 stars
citation-content-verify skill
fedec65/bettercallclaude · bettercallclaude/skills/citation-content-verify/SKILL.md · Substantive citation verifier — checks every citation in a draft against the live source for existence AND content…
git:20260831.7dc2182 · audit A · 40 stars
compliance-frameworks skill
fedec65/bettercallclaude · bettercallclaude/skills/compliance-frameworks/SKILL.md · Swiss financial regulatory compliance — FINMA, GwG/AML/KYC, FIDLEG/FINIG licensing, BankG, crypto/DLT regulation…
git:20260831.7dc2182 · audit A · 40 stars
data-protection-law skill
fedec65/bettercallclaude · bettercallclaude/skills/data-protection-law/SKILL.md · Swiss data protection — nDSG/FADP framework, GDPR adequacy, cantonal DP laws (IDG/KDSG/LIPAD), DSFA/DPIA, cross-border…
git:20260831.7dc2182 · audit A · 40 stars
legal-5step-framework skill
fedec65/bettercallclaude · bettercallclaude/skills/legal-5step-framework/SKILL.md · End-to-end 5-step Swiss legal pipeline: (1) intake/fact extraction, (2) BGE/statute research, (3) strategy/risk…
git:20260831.7dc2182 · audit A · 40 stars
legal-chronology skill
fedec65/bettercallclaude · bettercallclaude/skills/legal-chronology/SKILL.md · Legal chronology builder — turns case documents (contracts, correspondence, court filings, expert reports) into a…
git:20260831.7dc2182 · audit A · 40 stars
legal-intake skill
fedec65/bettercallclaude · bettercallclaude/skills/legal-intake/SKILL.md · Swiss legal intake — transforms vague or complex queries into actionable execution plans. Two modes: **Refine**…
git:20260831.7dc2182 · audit A · 40 stars
legal-wayfinder skill
fedec65/bettercallclaude · bettercallclaude/skills/legal-wayfinder/SKILL.md · Decision-map decomposition for legal matters too big or too foggy for one session. Charts a map (destination, decisions…
git:20260831.7dc2182 · audit A · 40 stars
privacy-routing skill
fedec65/bettercallclaude · bettercallclaude/skills/privacy-routing/SKILL.md · Privacy routing for Swiss attorney-client privilege (Anwaltsgeheimnis, Art. 321 StGB) with pattern detection in German…
git:20260718.de18a1e · audit A · 40 stars
output-conventions skill
fedec65/bettercallclaude · bettercallclaude/skills/shared/SKILL.md · Shared deliverable-as-file output conventions for all BetterCallClaude commands. Defines the bcc-output folder…
git:20260831.7dc2182 · audit A · 40 stars
swiss-citation-formats skill
fedec65/bettercallclaude · bettercallclaude/skills/swiss-citation-formats/SKILL.md · Swiss legal citation formatter — validates, formats, and converts BGE/ATF/DTF, statutory, and cantonal citations across…
git:20260831.7dc2182 · audit A · 40 stars
swiss-document-analysis skill
fedec65/bettercallclaude · bettercallclaude/skills/swiss-document-analysis/SKILL.md · Swiss legal document analyzer — structured analysis of contracts, court decisions, statutes, submissions. Includes NDA…
git:20260831.7dc2182 · audit A · 40 stars

Every file in fedec65/bettercallclaude

Browse by kind, by grade A, or by owner.