Script Compliance Auditor
SkillAI & modelsChecks AI phone call scripts against legal rules, flagging missing disclosures and banned pressure tactics.
Use Script Compliance Auditor in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Script Compliance Auditor and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Script Compliance Auditor skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
About this skill
Heuristic legal and regulatory compliance auditor for AI phone call scripts. Scans for required disclosures and prohibited high-pressure tactics.
What this skill tells your AI
The instructions your AI receives, as published by calle-ai/awesome-phone-call-agents in skills/call-script-compliance-auditor/SKILL.md and read by Ahel’s review.
The call-script-compliance-auditor skill is an offline experimental phrase checklist for AI-agent call scripts. Its PASS/WARN/FAIL labels describe heuristic checks only; they neither establish legal compliance nor authorize dialing. A qualified human must review real use.
Supported Jurisdictions
- UK_FCA: Financial Conduct Authority (Consumer Duty rules).
- EU_GDPR: General Data Protection Regulation (Articles 7, 13, 14).
- US_TCPA: Telephone Consumer Protection Act.
- US_HIPAA: Health Insurance Portability and Accountability Act (Privacy Rule).
Research & Regulatory Scope
The jurisdiction names label illustrative rule sets, not complete or current legal coverage. Research and regulatory links are background only; no published benchmark or legal clause-to-rule certification is claimed. See research scope.
How it works
The skill parses the call script (either plain text or a JSON task definition) and runs it through a dictionary of regex-based rules for the chosen jurisdiction.
Each rule is categorized as:
- REQUIRED: The script must contain specific language (e.g. "opt out"). Failure results in
FAIL. - WARN_IF_ABSENT: The script should probably contain this language (e.g. risk warnings), but its absence isn't an automatic failure. Results in
WARN. - PROHIBITED: The script must NOT contain this language (e.g. "this offer expires tonight"). Presence results in
FAIL.
It outputs a structured JSON report with an overall_verdict (PASS, WARN, or FAIL), risk level, and suggested rewrites where implemented. Some failed rules have no rewrite suggestion.
Expected Outcomes & Metrics
These are unvalidated design targets, not measured legal accuracy.
| Metric | Target | Notes |
|---|---|---|
| Regulatory Precision | > 95% | False positives (flagging compliant text) are acceptable; false negatives (missing a violation) are critical failures. |
Limitations & Known Constraints
- Heuristic Limitations: This tool uses regex pattern matching. It does not possess deep semantic understanding. A highly obfuscated script might bypass the checks.
- Not Legal Advice: This is a technical guardrail, not a substitute for qualified legal counsel.
Signals
- GitHub stars
- 104
- Forks
- 528
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
call-script-compliance-auditor- Source
- github.com/calle-ai/awesome-phone-call-agents
github.com/calle-ai/awesome-phone-call-agents
More in AI & models
Skill · anthropics
More in AI & modelstriage
Skill · mattpocock
More in AI & modelswayfinder
Skill · mattpocock
More in AI & modelsalgorithmic-art
Skill · anthropics
More in AI & modelscode-review-and-quality
Skill · addyosmani
More in AI & modelsmarketing-psychology
Skill · coreyhaines31
More in AI & models