Home / calle-ai / awesome-phone-call-agents · GitHub

call-leading-question-guard SKILL.md skillA

call-leading-question-guard from calle-ai/awesome-phone-call-agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add calle-ai/awesome-phone-call-agents/call-leading-question-guard@git:20261003.e8470b1

Pins git:20261003.e8470b1 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: calle-ai/awesome-phone-call-agents
Path: skills/call-leading-question-guard/SKILL.md
Versions recorded: 1
Latest version: git:20261003.e8470b1, committed Oct 3, 2026
Size: 4,523 bytes
Repository stars: 112
License: MIT

Offline heuristic CALL-E phone call transcript skill that classifies agent questions into leading forms (tag questions, negative interrogatives, presupposition triggers, coercive framing), flags values affirmed under leading forms as tainted elicitation, and emits a neutral-elicitation goal template. It is not proof an answer was coerced, intent detection, or authorization to act automatically.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# call-leading-question-guard

> **A leading question does not ask - it instructs the answer, then
> collects a signature.**

How a question is worded shapes what comes back. "What day works best
for you?" and "You can pick up on Friday, right?" are both questions,
but only one hands the person a decision; the other hands them a form
to sign. On a phone call, where answers are spoken and immediately
acted on, that wording pressure can end up driving bookings and record
updates. This skill grades the agent's interrogation wording, not the
callee's answers.

## When To Use

- after any CALL-E call where the agent elicits decisions (dates,
  times, amounts, plan choices) from the person
- when a recorded value was affirmed immediately after an agent
  question and you want to know how the question was framed
- before placing calls, to craft a neutral-elicitation goal that opens
  open-form and confirms in bounded closed form
- as a review aid alongside sibling conduct skills on the same
  transcript

## When Not To Use

- on the callee's questions - only agent turns are scanned
- to prove coercion; a flagged form is not proof the answer was
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add calle-ai/awesome-phone-call-agents/call-leading-question-guard@sha256:b7a2d98215ac4459

The line at the top of this page pins the label git:20261003.e8470b1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_u5kyjmuekpcz5c3a.svg)](https://markdownregistry.com/a/art_u5kyjmuekpcz5c3a)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 3, 2026.

version	committed	commit	size	audit
git:20261003.e8470b1 latest	2026-10-03	e8470b1	4,523 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (4523 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

calle-ai/awesome-phone-call-agents · 112 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_u5kyjmuekpcz5c3a
GET https://markdownregistry.com/api/v1/resolve?ref=calle-ai/awesome-phone-call-agents/call-leading-question-guard
GET https://markdownregistry.com/api/v1/blob/b7a2d98215ac4459a25d5794cc8a31542043294994bc341d6514131fd212ec78

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.