call-emotional-contagion-monitor skillA
call-emotional-contagion-monitor is agent-read markdown (skill) from calle-ai/awesome-phone-call-agents: Offline experimental keyword-based transcript review with suggested de-escalation prompts, without altering live calls or guaranteeing behavior..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Emotional Contagion Monitor
This skill checks supplied post-call transcripts using a small lexicon and suggests prompt changes for human review. It does not apply those changes, measure internal emotions, or guarantee de-escalation.
## Research Scope
Related literature is background inspiration, not validation of the prototype or its thresholds. See [research scope](references/research-papers.md). The scores are keyword heuristics, not calibrated measures of professionalism.
## Background
Current generation LLMs have an inherent "alignment bias" where they tend to mirror the style and sentiment of the user. In a customer service or crisis setting, if a human yells or uses abusive language, an unmonitored AI might begin mirroring that aggression, becoming inappropriately terse, or inappropriately defensive ("I am not to blame, you need to calm down"). This skill catches those instances.
## How It Works
1. The system scans each turn in the transcript.
2. When the `callee` speaks, it calculates a Negative Arousal score (0.0 to 1.0).
3. When the `agent` speaks, it calculates a Negative Valence score and derives the agent's Professionalism (1.0 - Negative Valence).
…Read the whole file at its exact version.
How to install
mdr add calle-ai/awesome-phone-call-agents/call-emotional-contagion-monitor@v1.0.0mdr add calle-ai/awesome-phone-call-agents/call-emotional-contagion-monitor@sha256:26167e1e3c98fe2fPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_uc5xaovn6qva3i4j)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3104 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
calle-ai/awesome-phone-call-agents · 103 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uc5xaovn6qva3i4j GET https://markdownregistry.com/api/v1/resolve?ref=calle-ai/awesome-phone-call-agents/call-emotional-contagion-monitor GET https://markdownregistry.com/api/v1/blob/26167e1e3c98fe2fef4347180df4e4282a35e2d29225e4c75233788278a4c1c8
Your agent 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.