skills.rest
gozonerd
gozonerdCOMMUNITY
Explore all skills by this author →
GitHub

Rule-Based Compliance Testing

Tests deliverable outputs against nine accuracy rules and reports pass/fail results in YAML.

Updated Apr 11, 2026
Search Tags:#validation#audit#compliance testing#content verification#pass fail#accuracy rules#yaml report
One-click install
npx skills add https://github.com/gozonerd/shadow-ai-assessment --skill rule-based-compliance-testing-gozonerd
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Rule-Based Compliance Testing
Source: https://github.com/gozonerd/shadow-ai-assessment/tree/main/.claude/skills/dmis/task_type/TT-08_Rule_Based_Compliance_Testing
Command: npx skills add https://github.com/gozonerd/shadow-ai-assessment --skill rule-based-compliance-testing-gozonerd

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) components.

What problem does it solve? Content pipelines produce deliverables that must comply with a fixed set of accuracy rules, and manual checking is inconsistent and error-prone. This Skill deterministically tests outputs against the 9 Critical Accuracy Rules (ACC-001 through ACC-009) and produces an auditable pass/fail compliance report. ## Core Features & Use Cases - Deterministic Rule Testing: Applies all nine accuracy rules (terminology, attribution, thresholds, platform distinctions) to a deliverable and records binary pass/fail results with evidence. - Structured YAML Reporting: Produces a compliance report conforming to the TT-08 output schema, including compliance summary, rule-by-rule results, violation log, and remediation guidance. - Output Validation: Ships a Python script that validates generated reports for correct task type, version, and coverage of all nine rules. - Use Case: Before publishing a digital health framework document, run this Skill to verify that CommCare/Dimagi distinctions, office attributions, and convergence thresholds are stated correctly, and receive a violation log with exact locations to fix. ## Quick Start Test the attached deliverable against all nine accuracy rules and generate a TT-08 compliance report with pass/fail evidence and remediation guidance.

Frequently Asked Questions about Rule-Based Compliance Testing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I test a document against fixed accuracy rules?▼

Provide the deliverable output plus the accuracy rule definitions, and the Skill scans the content, determines which rules apply to each section, and records a binary pass/fail result with quoted evidence for every rule.

What does a rule-based compliance test report contain?▼

The YAML report contains a compliance summary, rule-by-rule test results with evidence, a violation log with exact locations in the deliverable, and remediation guidance. It conforms to the TT-08 output schema referenced in the references directory.

How do I validate a TT-08 compliance report?▼

Run the included validate_output.py script with the report file path. It checks YAML parsing, task_type, version, and confirms all nine accuracy rules ACC-001 through ACC-009 are present in the report.

Can the compliance test skip rules that seem not applicable?▼

No, all nine rules must be tested and reported. When a rule does not apply to the content, the report marks it as passed with an explicit not-applicable explanation rather than omitting it.

What are the limitations of rule-based compliance testing?▼

It only verifies the enumerated accuracy rules and cannot judge general writing quality, factual accuracy outside the rule set, or regulatory requirements. Those concerns require separate verification passes such as source integrity or regulatory checks.

Related Skills

Explore More Legal & Compliance Skills→
EmaRimoldiEmaRimoldi

manuscript-production

Automate manuscript production from blueprint to LaTeX submission package.

Community
Advanced
webrix-aiwebrix-ai
1

expense-management

Categorize business expenses, flag policy violations, and generate reimbursement reports.

Official
Advanced
githubgithub
38.5k

doublecheck

Verifies AI-generated claims through web search and adversarial review with structured reports.

Official
Advanced
mitul-bhatiamitul-bhatia

regex-vs-llm-structured-text

Automates choosing between regex and LLM for parsing structured text.

Community
Intermediate