call-disfluency-stress-profiler skillA
call-disfluency-stress-profiler is agent-read markdown (skill) from calle-ai/awesome-phone-call-agents: Offline heuristic CALL-E transcript skill that measures filled-pause, self-repair, repetition, and hesitation-opener rates per speaker side to detect callee stress and agent knowledge-gap hesitancy, then emits a reassurance-paced follow-up call goal. It is not a clinical stress assessment, a proof of speaker intent, or authorization to act automatically..
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
# call-disfluency-stress-profiler > **Repeated pauses and repairs can be useful prompts for human review, > but do not establish a speaker's emotional state or knowledge.** Spoken conversation carries signals that plain transcripts still preserve: disfluency. When a callee is stressed, confused, or overwhelmed, their filled-pause rate (`uh`, `um`, `er`) and self-repair frequency (`I mean`, `actually`, word repetitions) spike measurably above baseline. When an agent encounters questions outside its prepared knowledge, the same markers appear in its turns. This skill reads the finished `get_call_run` transcript, computes per-side disfluency rates, and flags `CALLEE_STRESSED` or `AGENT_HESITANT` when rates cross illustrative, unvalidated demo thresholds. It then offers a reassurance-paced follow-up call goal or a script-review recommendation. ## When To Use - after any CALL-E call where the contact seemed distressed or uncertain - as part of a QA pipeline to detect agent knowledge gaps at scale - in healthcare, collections, or support workflows where caller distress carries legal or ethical weight - to identify topics that consistently cause agent hesitancy (→ update scripts) …
Read the whole file at its exact version.
How to install
mdr add calle-ai/awesome-phone-call-agents/call-disfluency-stress-profiler@git:20260924.afe6d97mdr add calle-ai/awesome-phone-call-agents/call-disfluency-stress-profiler@sha256:4f607887756c1286Pin 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_dvnu53uiiez7pdii)
0 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 (5759 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_dvnu53uiiez7pdii GET https://markdownregistry.com/api/v1/resolve?ref=calle-ai/awesome-phone-call-agents/call-disfluency-stress-profiler GET https://markdownregistry.com/api/v1/blob/4f607887756c1286defcba40346c97f4ff33dc017edeecb4b7dd0b0ef1c08abd
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.