call-semantic-barge-in-analyzer skillA
call-semantic-barge-in-analyzer is agent-read markdown (skill) from calle-ai/awesome-phone-call-agents: 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 / DISEN.
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-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
mdr add calle-ai/awesome-phone-call-agents/call-semantic-barge-in-analyzer@git:20260920.54a80demdr add calle-ai/awesome-phone-call-agents/call-semantic-barge-in-analyzer@sha256:ce60bf1e067f2ee6Pin 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_up7xi6op7sqjhnus)
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 (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
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_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 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.