teach-back SKILL.md skillA

teach-back from atman-33/workhub is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add atman-33/workhub/teach-back@git:20261001.f514851

Pins git:20261001.f514851 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
atman-33/workhub
Path
plugins/thinking/skills/teach-back/SKILL.md
Versions recorded
2
Latest version
git:20261001.f514851, committed Oct 1, 2026
First version recorded
Sep 19, 2026
Size
7,894 bytes
Repository stars
3
License
MIT

Quiz the user on a document, one question at a time, until they can explain it to someone else — definitions, numbers, evidence, background, scope — and log the document's own gaps separately. For material that makes causal claims or rests on hypotheses (incident reports, post-mortems, proposals), also runs armor mode: sorts fact from hypothesis, checks the cause-and-effect chain, cross-examines it, and hands over what to assert, hedge and leave out. Use when the user wants to understand…

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

# teach-back

The user leaves able to explain the material in their own words. You get them
there by asking, never by summarising: every answer on the record is theirs.

The measure is a **teach-back** — the user explaining the material back, as if
to the person they will face. Your questions are the rehearsal for that person.

## Armor mode

Material that makes causal claims or rests on hypotheses needs more than
understanding: the user must be able to defend each claim. Armor mode adds
steps 3, 7 and 8 below. It applies when the material asserts that A caused B,
states a hypothesis, or is a report the user will stand behind. Plain
reference material runs without it.

Armor means each claim is asserted at the strength its evidence supports. You
cannot verify outside facts; the user's labels and their stated checks are the
evidence. Say "I have not verified this" for whatever you could not check.

## Steps

1. **Read the material.** Files, folders, URLs, images and pasted text. Read
   pdf / pptx / xlsx / docx through their skills when installed; view images
   with Read. Done when you can point to where each claim in it lives.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add atman-33/workhub/teach-back@sha256:fc59b58d49a40150

The line at the top of this page pins the label git:20261001.f514851, 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 badge

[![mdr](https://markdownregistry.com/badge/art_3hnzd2jmpygb7xjo.svg)](https://markdownregistry.com/a/art_3hnzd2jmpygb7xjo)

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

Versions

The registry has recorded 2 versions of this file, between Sep 19, 2026 and Oct 1, 2026, about one every 12 days.

versioncommittedcommitsizeaudit
git:20261001.f514851 latest2026-10-01 f514851 7,894 BA view · diff
git:20260919.0f2819d2026-09-19 0f2819d 4,614 BA 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 (7894 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

atman-33/workhub · 3 stars · license MIT · pushed 2026-10-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3hnzd2jmpygb7xjo
GET https://markdownregistry.com/api/v1/resolve?ref=atman-33/workhub/teach-back
GET https://markdownregistry.com/api/v1/blob/fc59b58d49a401501b1ca6d651e34bd205fb1d916f5fc973161dccea8a45ea58

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.

More from atman-33/workhub

CLAUDE.md CLAUDE.md file
atman-33/workhub · CLAUDE.md
git:20260929.5a11e52 · audit A · 3 stars
AGENTS.md@demo-vault AGENTS.md file
atman-33/workhub · demo-vault/AGENTS.md
git:20260830.27fbb5d · audit A · 3 stars
CLAUDE.md@demo-vault CLAUDE.md file
atman-33/workhub · demo-vault/CLAUDE.md
git:20260930.4c9347d · audit A · 3 stars
handoff-go SKILL.md skill
atman-33/workhub · plugins/agent-ops/skills/handoff-go/SKILL.md · Write a handoff document and launch the next agent in a split multiplexer pane (herdr or zellij), with new-window and…
git:20260901.114c610 · audit A · 3 stars
handoff SKILL.md skill
atman-33/workhub · plugins/agent-ops/skills/handoff/SKILL.md · Compact the current conversation into a handoff document for another agent to pick up.
git:20260901.114c610 · audit A · 3 stars
herdr SKILL.md skill
atman-33/workhub · plugins/agent-ops/skills/herdr/SKILL.md · Control herdr from inside it. Manage workspaces and tabs, split panes, spawn agents, read output, and wait for state…
git:20260901.114c610 · audit A · 3 stars
launch-team SKILL.md skill
atman-33/workhub · plugins/agent-ops/skills/launch-team/SKILL.md · Launch a role-based team of Claude Code agents in separate multiplexer panes that coordinate on one task by messaging…
git:20260901.114c610 · audit A · 3 stars
setup-herdr SKILL.md skill
atman-33/workhub · plugins/agent-ops/skills/setup-herdr/SKILL.md · Install herdr (terminal-native agent multiplexer), set up its Claude Code and OpenCode integrations, and configure…
git:20260901.114c610 · audit B · 3 stars
setup-zellij SKILL.md skill
atman-33/workhub · plugins/agent-ops/skills/setup-zellij/SKILL.md · Install Zellij and configure shell profiles to auto-launch Zellij on startup (replacing any existing herdr autostart…
git:20260901.114c610 · audit A · 3 stars
sidekick-go SKILL.md skill
atman-33/workhub · plugins/agent-ops/skills/sidekick-go/SKILL.md · Use when the user explicitly asks to delegate work to a persistent sidekick/helper agent in its own pane that you can…
git:20260901.114c610 · audit A · 3 stars
wsl-vscode-doctor SKILL.md skill
atman-33/workhub · plugins/agent-ops/skills/wsl-vscode-doctor/SKILL.md · Diagnose and fix `code .` failing to launch, or opening a disconnected Windows-side VS Code instead of a WSL-connected…
git:20260901.114c610 · audit A · 3 stars
create-claude-md SKILL.md skill
atman-33/workhub · plugins/authoring/skills/create-claude-md/SKILL.md · Generate or refine a concise, effective CLAUDE.md for the current project following official best-practice guidelines…
git:20260901.114c610 · audit A · 3 stars

Every file in atman-33/workhub

Other files named teach-back

teach-back SKILL.md skill
tmusser/ai-engineering-skills · skills/teach-back/SKILL.md · Transfer ownership of a verified implementation by testing and repairing the human's understanding of its behavior…
git:20260729.b84f061 · audit A · 6 stars

Browse by kind, by grade A, or by owner.