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

homeworkhawk-graded-worksheet-callback SKILL.md skillA

homeworkhawk-graded-worksheet-callback 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/homeworkhawk-graded-worksheet-callback@git:20260915.2c8e1a2

Pins git:20260915.2c8e1a2 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/homeworkhawk-graded-worksheet-callback/SKILL.md
Versions recorded: 1
Latest version: git:20260915.2c8e1a2, committed Sep 15, 2026
Size: 6,129 bytes
Repository stars: 112
License: MIT

After an automated grading pipeline (HomeworkHawk, OpenCV 5) grades a finished worksheet photo, optionally places ONE outbound CALL-E call to a verified parent/guardian delivering advisory results (score, which questions to review, which ones the system could not read confidently). Default mode is a no-call preview that returns the exact script and result schema; a real call requires explicit operator approval, an authorized guardian destination, and an unambiguous grading result. Returns a…

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

# HomeworkHawk — Graded Worksheet Callback

## Why this exists

Automated homework grading is only useful if the results reach the
parent. A grading result that lives in a dashboard nobody opens at work
is a dead end. This skill closes the loop: when a grading pipeline
finishes a worksheet, it hands the structured result to CALL-E, which
phones the parent, delivers the summary in a warm and non-judgmental
tone, names the questions worth reviewing, flags the ones the system
itself escalated as unreadable, and offers a review session for
tomorrow evening. The call returns a schema-validated result the
grading app can act on.

It is a **workflow skill** on top of CALL-E's one-off
`calls.createAndWait` SDK call — no new backend, no scheduler state.

**The grading result is advisory.** It tells a parent what to look at
together with their child; it is never an official grade, a judgment of
the child, or a placement decision.

## Default: preview, no call

Running the skill **without `--approve-call` places no call**. Preview
mode prints (and returns as JSON):

- the exact script the agent would read, with the student name and any
  escalated questions included,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add calle-ai/awesome-phone-call-agents/homeworkhawk-graded-worksheet-callback@sha256:1735c3d81c092023

The line at the top of this page pins the label git:20260915.2c8e1a2, 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_u2eqtv2okyr74cmq.svg)](https://markdownregistry.com/a/art_u2eqtv2okyr74cmq)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 15, 2026.

version	committed	commit	size	audit
git:20260915.2c8e1a2 latest	2026-09-15	2c8e1a2	6,129 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 (6129 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_u2eqtv2okyr74cmq
GET https://markdownregistry.com/api/v1/resolve?ref=calle-ai/awesome-phone-call-agents/homeworkhawk-graded-worksheet-callback
GET https://markdownregistry.com/api/v1/blob/1735c3d81c092023622d322739091a5508543b6100b09a3d5206fac4c25fb868

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.