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

otherend-task-test SKILL.md skillA

otherend-task-test 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/otherend-task-test@git:20260911.75f87c6

Pins git:20260911.75f87c6 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/otherend-task-test/SKILL.md
Versions recorded: 1
Latest version: git:20260911.75f87c6, committed Sep 11, 2026
Size: 8,946 bytes
Repository stars: 112
License: MIT

Rehearse a CALL-E phone-call task against a programmable line the operator owns, answering as a receptionist with a planted adversity or as a scripted person for tasks that call people, before the task reaches real people. Plan without dialing, replay graded fixtures with no keys, place at most N live calls, then turn the grade into task-text edits.

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

# otherend task test

You cannot program the agent CALL-E sends on a call. You can program the person it calls.

This skill rehearses a CALL-E `task` and `result_schema` against a line the operator owns. The line
answers either as a receptionist with a chosen adversity profile (a false Saturday offer, a
stonewall, a demand for a member ID, a scripted hold, an "are you an AI?" question) or, when the
task calls a person rather than a business, as a scripted callee persona (a customer who confirms,
one who reschedules, one who will not decide). CALL-E dials it. Afterwards a deterministic grader
compares what CALL-E *reported* (`task_completed`, `structured_result`, `completion_confidence`,
the caller's disclosure turn) with what the line *actually said*.

The thing under test is the task text and the schema. The output is a list of edits to them.

The runnable app is `apps/python/otherend/` in this repository, a thin CLI over the `voxprobe`
package on PyPI (`voxprobe[calle]`, 0.2.2 or newer). The nine bundled fixture rows are SYNTHETIC:
voxprobe's in-process text simulation produced them, with one open model playing the caller and
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add calle-ai/awesome-phone-call-agents/otherend-task-test@sha256:327988cc4fadb601

The line at the top of this page pins the label git:20260911.75f87c6, 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_ggixte5xtcvdh32e.svg)](https://markdownregistry.com/a/art_ggixte5xtcvdh32e)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 11, 2026.

version	committed	commit	size	audit
git:20260911.75f87c6 latest	2026-09-11	75f87c6	8,946 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 (8946 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_ggixte5xtcvdh32e
GET https://markdownregistry.com/api/v1/resolve?ref=calle-ai/awesome-phone-call-agents/otherend-task-test
GET https://markdownregistry.com/api/v1/blob/327988cc4fadb60120bd9efa3a8e047b13c095938fc92ae9178fba64ca4d073e

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.