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

call-agent-certainty-calibrator SKILL.md skillA

call-agent-certainty-calibrator 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-agent-certainty-calibrator@git:20260923.5c6d78d

Pins git:20260923.5c6d78d 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-agent-certainty-calibrator/SKILL.md
Versions recorded: 1
Latest version: git:20260923.5c6d78d, committed Sep 23, 2026
Size: 4,640 bytes
Repository stars: 112
License: MIT

Offline experimental CALL-E transcript helper that flags agent statements of specific values absent from the goal facts and callee turns (over-assertion) and goal facts spoken with hedges but no source attribution (over-hedging), plus a three-tier calibrated-wording goal template. It is not proof the agent invented anything, a measure of internal confidence, or authorization to act.

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-agent-certainty-calibrator

> **An agent that invents specifics is worse than one that says 'I don't
> know'. An agent that hedges its own record is worse than useless.**

Language models can express calibrated confidence in words - and, left
unchecked, they drift both ways: asserting specifics nobody gave them
("free delivery on Friday!") and softening facts they were told to state
("I think it might be $45?"). On a phone call both failures are audible,
and both end up in the outcome. This skill grades the agent's stated
values against the goal it was given.

## When To Use

- after any fact-bearing CALL-E call, together with the goal text (or
  plan JSON) the call was built from
- when an outcome contains a value nobody remembers putting in the goal
- before placing calls, to craft wording that speaks record facts with
  authority and admits gaps honestly

## When Not To Use

- without the goal file; calibration is graded against the goal's facts
  and the CLI requires it
- to prove the agent fabricated a value; an OVER-ASSERTED value may be
  true and simply missing from the goal text - the card routes to
  verification, always
…

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-agent-certainty-calibrator@sha256:d32f08e7827c5965

The line at the top of this page pins the label git:20260923.5c6d78d, 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_gir3ayehjlf6pps5.svg)](https://markdownregistry.com/a/art_gir3ayehjlf6pps5)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 23, 2026.

version	committed	commit	size	audit
git:20260923.5c6d78d latest	2026-09-23	5c6d78d	4,640 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 (4640 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_gir3ayehjlf6pps5
GET https://markdownregistry.com/api/v1/resolve?ref=calle-ai/awesome-phone-call-agents/call-agent-certainty-calibrator
GET https://markdownregistry.com/api/v1/blob/d32f08e7827c5965c05df9e791f347a72bceda69ea07ac8c1f350c8133f16fb1

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.