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

call-semantic-barge-in-analyzer SKILL.md skillA

call-semantic-barge-in-analyzer 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-semantic-barge-in-analyzer@git:20260920.54a80de

Pins git:20260920.54a80de 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-semantic-barge-in-analyzer/SKILL.md
Versions recorded: 1
Latest version: git:20260920.54a80de, committed Sep 20, 2026
Size: 4,389 bytes
Repository stars: 112
License: MIT

Post-call cooperation skill. Classifies callee turns in a CALL-E transcript as backchannels ("mm-hmm", "right, okay"), frustration barge-ins ("wait", "hold on", "slow down"), or substantive answers - disambiguating answers from backchannels via the preceding agent question - and computes pacing metrics including backchannel density and whether the agent shortened its turns after the first interruption. Returns a cooperation profile (ENGAGED_COOPERATIVE / NEUTRAL / FRUSTRATED_INTERRUPTING /…

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-semantic-barge-in-analyzer

> **Was the person on the other end with you, against you, or barely there?**

`call-review` audits call compliance, including ignored stop requests.
This skill answers a different question: how cooperative was the callee,
and how should the NEXT call be paced? A callee who answers "Mm-hmm."
while you explain is with you; a callee who says "Wait, slow down." three
times is telling you your pacing failed - and the fix is a shorter-turn
script, not more repetition.

## When To Use

- after any CALL-E call where the agent delivered multi-part information,
  to check whether the callee could keep up
- to decide whether the next call should use a pacing goal (short turns,
  explicit confirmation points)
- to generate that pacing goal for `plan_call` directly

## When Not To Use

- to audit compliance or ignored stop requests; use `call-review`
- to detect fraud; use `call-fraud-shield`
- during a call; CALL-E exposes transcripts, not live audio, so
  interruptions are read post-hoc from turn text, not from overlapping
  speech timing
- as a judgment about the person; profiles are pacing advice only and the
  card says so

## Workflow
…

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-semantic-barge-in-analyzer@sha256:ce60bf1e067f2ee6

The line at the top of this page pins the label git:20260920.54a80de, 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_up7xi6op7sqjhnus.svg)](https://markdownregistry.com/a/art_up7xi6op7sqjhnus)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 20, 2026.

version	committed	commit	size	audit
git:20260920.54a80de latest	2026-09-20	54a80de	4,389 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 (4389 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_up7xi6op7sqjhnus
GET https://markdownregistry.com/api/v1/resolve?ref=calle-ai/awesome-phone-call-agents/call-semantic-barge-in-analyzer
GET https://markdownregistry.com/api/v1/blob/ce60bf1e067f2ee66c8da3ce0ace42165a460716299eb7e2bdbf4aa314bddc75

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.