Call Cross Call Consistency Checker

Offline experimental CALL-E helper that compares amounts, dates, and times stated by the agent across two finished calls to the same destination and grades each fact kind CONSISTENT, CONTRADICTED, or ONLY_STATED, plus a consistency-guarded goal template. It is not proof either call lied, a record of truth, or authorization for another call.

116 stars 512 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add CALLE-AI/awesome-phone-call-agents --skill call-cross-call-consistency-checker
Manual install
git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git /tmp/awesome-phone-call-agents
mkdir -p ~/.claude/skills
cp -r /tmp/awesome-phone-call-agents/skills/call-cross-call-consistency-checker ~/.claude/skills/call-cross-call-consistency-checker

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# call-cross-call-consistency-checker

> **Call someone twice and say two different things, and you were never
> really trusted the first time.**

Every other skill in this repository analyzes one call. This one analyzes
the space BETWEEN two calls to the same person: did the organization tell
them the same price, the same date, the same time it told them before?
Contradictions across calls are how campaigns lose people - each new call
quietly rewrites reality, and the person on the line is the only one who
notices.

## When To Use

- when a destination has received two or more calls and any result from
  the latest one will be written somewhere
- before drafting the NEXT call to a person whose earlier call had
  disputed or confusing values
- to generate a consistency-guarded goal for the follow-up plan_call

## When Not To Use

- to decide which call's value is true; the record (or a human with it)
  decides - this skill only routes to verification
- on calls to different destinations; comparing unrelated people's facts
  is meaningless
- as a memory system; it compares two transcripts you hand it, it stores
  nothing
- during a call; strictly post-call analysis plus pre-call goal crafting

## Workflow

### Compare two finished calls

```bash
python3 scripts/cross_call_consistency_checker.py analyze \
  --transcript-a path/to/call-a.json --transcript-b path/to/call-b.json
```

Reads the real `get_call_run` result shape (`{status, result: {transcript}}`)
Read the full skill on GitHub

Details

Skill name
call-cross-call-consistency-checker
Path
skills/call-cross-call-consistency-checker/SKILL.md
License
MIT
Repo updated
14 November 2026

FAQ

What does the Call Cross Call Consistency Checker skill do?

Offline experimental CALL-E helper that compares amounts, dates, and times stated by the agent across two finished calls to the same destination and grades each fact kind CONSISTENT, CONTRADICTED, or ONLY_STATED, plus a consistency-guarded goal template. It is not proof either call lied, a record of truth, or authorization for another call.

How do I install the Call Cross Call Consistency Checker skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add CALLE-AI/awesome-phone-call-agents --skill call-cross-call-consistency-checker. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Call Cross Call Consistency Checker popular?

It lives in CALLE-AI/awesome-phone-call-agents, which has 116 GitHub stars and 512 forks.

Related skills

Accesscall

116

CALLE-AI/awesome-phone-call-agents

Conduct phone-based accessibility intake interviews for users who cannot complete web-based accessibility audit forms (screen reader fatigue, motor impairment, low vision, cognitive load), and produce a structured result mapped to VPAT 2.4 / Section 508 conformance reporting fields.

Frontend & Design512

Accessible Outing Verifier

116

CALLE-AI/awesome-phone-call-agents

Demonstrates advisory accessibility-planning checks with offline fixtures and a proposed bounded CALL-E workflow; use for exploring unknown or qualified venue claims without making calls.

Frontend & Design512

Adherence Memory Callback

116

CALLE-AI/awesome-phone-call-agents

Run a consent-based outbound CALL-E medication-adherence phone check-in that remembers each caller across calls, learns side-effect patterns across many callers behind a corroboration gate, and honors "call me back later" by opening the next call with that context.

Productivity & Notes512

Call Human Escalation Request Auditor

116

CALLE-AI/awesome-phone-call-agents

Offline experimental CALL-E transcript helper that detects callee requests for a human agent (transfer intent plus human role, or bare manager/supervisor demands) and grades the agent response window HONORED, DEFLECTED, IGNORED, or FALSE_HUMAN_CLAIM, plus an escalation-honesty goal template. It is not proof a transfer happened, intent detection, or authorization to act.

AI, LLMs & Agents512

Call AI Disclosure Comprehension Auditor

116

CALLE-AI/awesome-phone-call-agents

Offline experimental CALL-E transcript helper that grades whether the agent disclosed being an AI, whether the disclosure came before business content, whether a comprehension question was asked, and whether an acknowledgment was captured, plus a disclosure-first goal template. It is not legal advice, jurisdiction-specific compliance certification, or proof the person did or did not understand.

AI, LLMs & Agents512

Call Negotiation Coach

116

CALLE-AI/awesome-phone-call-agents

Pre-call strategy engine and post-call debrief for negotiation calls. Implements BATNA/ZOPA/Dual Concern Model + DISC-matched tactics.

AI, LLMs & Agents512

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.