call-verbal-irony-detector SKILL.md skillA

call-verbal-irony-detector 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-verbal-irony-detector@git:20260920.49cb149

Pins git:20260920.49cb149 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-verbal-irony-detector/SKILL.md
Versions recorded
1
Latest version
git:20260920.49cb149, committed Sep 20, 2026
Size
3,362 bytes
Repository stars
112
License
MIT

Offline experimental CALL-E transcript helper using English irony markers and complaint-context scoring. Returns advisory evidence spans, illustrative confidence buckets or abstention, and suggested de-escalation wording. It does not establish a person's intent, authorize another call or perform consequential actions.

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-verbal-irony-detector

> **What was said is not always what was meant.**

`call-summarizer` reports caller sentiment - what was said. This skill detects
verbal irony - the mismatch between the two - and turns it into the next
call's strategy. A callee who answers "Oh, great. Just perfect." after a
complaint is not happy, and an agent that acts on the literal words will
make it worse.

## When To Use

- after any CALL-E call where the outcome hinges on a positive-sounding
  answer inside a complaint discussion
- to decide whether a follow-up call should use a de-escalation goal
- to generate that de-escalation goal for `plan_call` directly

## When Not To Use

- to detect sentiment in general; use `call-summarizer` for that
- to detect fraud or social engineering; use `call-fraud-shield`
- during a call; this is strictly post-call analysis plus pre-call goal
  crafting, because CALL-E exposes transcripts, not live audio
- as proof of the callee's emotional state; text-only irony cues are
  ambiguous and the card says so

## Workflow

### Analyze a finished call

```bash
python3 scripts/irony_detector.py analyze --transcript path/to/call-result.json
```
…

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-verbal-irony-detector@sha256:65cb9d4773c0406b

The line at the top of this page pins the label git:20260920.49cb149, 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 badge

[![mdr](https://markdownregistry.com/badge/art_dvnhofirzgb2ocyg.svg)](https://markdownregistry.com/a/art_dvnhofirzgb2ocyg)

2 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.

versioncommittedcommitsizeaudit
git:20260920.49cb149 latest2026-09-20 49cb149 3,362 BA 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 (3362 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_dvnhofirzgb2ocyg
GET https://markdownregistry.com/api/v1/resolve?ref=calle-ai/awesome-phone-call-agents/call-verbal-irony-detector
GET https://markdownregistry.com/api/v1/blob/65cb9d4773c0406bae310cf585fdb3599209293f3a14829219253daa1b72b548

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.

More from calle-ai/awesome-phone-call-agents

AGENTS.md AGENTS.md file
calle-ai/awesome-phone-call-agents · AGENTS.md
git:20261027.4a5b3a5 · audit A · 112 stars
AGENTS.md@apps/python/buddye AGENTS.md file
calle-ai/awesome-phone-call-agents · apps/python/buddye/AGENTS.md
git:20260917.2209027 · audit A · 112 stars
DESIGN.md@apps/python/buddye/docs DESIGN.md file
calle-ai/awesome-phone-call-agents · apps/python/buddye/docs/DESIGN.md
git:20260917.2209027 · audit A · 112 stars
AGENTS.md@apps/python/callback-scam-screener AGENTS.md file
calle-ai/awesome-phone-call-agents · apps/python/callback-scam-screener/AGENTS.md
git:20260914.bd607da · audit A · 112 stars
DESIGN.md@apps/python/measureback DESIGN.md file
calle-ai/awesome-phone-call-agents · apps/python/measureback/DESIGN.md · A kitchen instrument for reading recipe measurements and their source words.
git:20260914.3dfc38c · audit A · 112 stars
AGENTS.md@apps/python/quotewake AGENTS.md file
calle-ai/awesome-phone-call-agents · apps/python/quotewake/AGENTS.md
git:20260826.9ce0c85 · audit A · 112 stars
AGENTS.md@apps/typescript/arc-platform AGENTS.md file
calle-ai/awesome-phone-call-agents · apps/typescript/arc-platform/AGENTS.md
git:20260911.edc1937 · audit A · 112 stars
CLAUDE.md@apps/typescript/arc-platform CLAUDE.md file
calle-ai/awesome-phone-call-agents · apps/typescript/arc-platform/CLAUDE.md
git:20260911.edc1937 · audit B · 112 stars
AGENTS.md@apps/typescript/bellwrench AGENTS.md file
calle-ai/awesome-phone-call-agents · apps/typescript/bellwrench/AGENTS.md
git:20261004.2169d84 · audit A · 112 stars
CLAUDE.md@apps/typescript/bellwrench CLAUDE.md file
calle-ai/awesome-phone-call-agents · apps/typescript/bellwrench/CLAUDE.md
git:20261004.2169d84 · audit B · 112 stars
AGENTS.md@apps/typescript/fraud-ops-caller AGENTS.md file
calle-ai/awesome-phone-call-agents · apps/typescript/fraud-ops-caller/AGENTS.md
git:20260911.062b54b · audit A · 112 stars
CLAUDE.md@apps/typescript/fraud-ops-caller CLAUDE.md file
calle-ai/awesome-phone-call-agents · apps/typescript/fraud-ops-caller/CLAUDE.md
git:20260911.062b54b · audit B · 112 stars

Every file in calle-ai/awesome-phone-call-agents

Browse by kind, by grade A, or by owner.