# Ldg Train The Trainers

> Prepares facilitators to deliver a programme, producing delivery learning points, a model run, a teach-back plan, practice rounds that rise in difficulty, delivery notes per module and a readiness conversation guide with no score. Use for "run ldg-train-the-trainers", "train the trainer", "train-the-trainer program", "prepare facilitators", "teach-back", "trainer readiness", "roll out a workshop to new trainers", "get facilitators ready to deliver", part of The Complete Claude Guide for L&D Pack by 90n.

- Skill: `polar-bear-org/ldg-train-the-trainers` (Agent Skill)
- Install (CLI): `npx get-skill add polar-bear-org/ldg-train-the-trainers`
- Raw SKILL.md: https://api.skillmd.com/api/skills/polar-bear-org/ldg-train-the-trainers/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: polar-bear-org (https://skillmd.com/u/polar-bear-org)
- Updated: 2026-11-14
- Page: https://skillmd.com/skills/polar-bear-org/ldg-train-the-trainers

---


# Train the Trainers

## When To Use
The programme depends on facilitators who each need to learn it first, and the usual preparation is one read-through of the deck. Use this when the facilitator guide exists, the pilot's changes are in, and several people must deliver the same programme. It answers: how does each facilitator practise the hard parts before real learners see them, and how do we agree together that they are ready?

## When Not To Use
If the guide is not written, run Write the Facilitator Guide first; this skill prepares people, it does not design the session. If the practice you need is for learners, not facilitators, that is Build the Role-Play. One experienced trainer taking over one session needs a walk through the guide, nothing more.

## Inputs
- The facilitator guide and session plan per module, with the what-if notes.
- What the pilot showed, the facilitators by role and delivery experience, and the first delivery date.
If you have none of this, I start from the module list and the facilitators' roles and mark the output as a first draft.

## Approach
Behaviour modelling applied to facilitators (Taylor, Russ-Eft and Chan, 2005): clear learning points, a model, practice, then feedback against the same points. Here the learning points are about delivery. The research found effects shrink from the room to the job, so the first real delivery is planned as part of the preparation. The failure it prevents: facilitators watch the designer deliver the whole day, nod, and meet the awkward module for the first time in front of a full room of learners, because the only practice on offer was an assessed one nobody wanted to fail.

## Workflow
1. Ask at most three questions: how many facilitators and how experienced, which module is hardest to deliver, and is a co-facilitator available for first deliveries?
2. Write four to six delivery learning points for this programme, short enough to hold while standing in front of a group, each one a move ("hand the question back to the room before you answer it").
3. Plan the model run: an experienced facilitator delivers one segment, and the group names where each point showed. Pick the segment facilitators fear, not the easy opening.
4. Plan the teach-back: each facilitator delivers a segment of a length you set, then peers give feedback against the same points, as what worked and one thing to try. Feedback is about the delivery, never the person.
5. Build practice rounds that rise in difficulty from the facilitator guide's what-if notes: a clean run, then a silent room, then a dominating voice, then a question they cannot answer.
6. Write delivery notes per module: what trips facilitators up, what to stress, where timing slips, including what the pilot showed.
7. Write the readiness conversation guide, with no score: the facilitator's own view, the support they want, and a first-delivery arrangement agreed together (solo, with a co-facilitator, or after another round).

## Output Format
```markdown
# Trainer Preparation Kit
Programme: [name] | Facilitators: [number, roles] | Preparation dates: [dates] | First delivery: [date]
## Delivery learning points
1. [move] 2. [move] 3. [move] 4. [move]
Model run: segment [segment] | Delivered by: [experienced facilitator] | The group names where each point showed: [how]
## Teach-back plan
| Slot | Segment delivered | Minutes | Peer feedback against | Feedback form |
|---|---|---|---|---|
| [slot] | [segment] | [minutes] | [learning points] | What worked / one thing to try |
## Practice rounds
| Round | What is added | Taken from what-if note | Move to practise |
|---|---|---|---|
| 1 | Nothing: a clean run | [none] | [segment as written] |
| [2 to 4] | [a silent room, then one voice dominating, then a question you cannot answer] | [note] | [move] |
## Delivery notes per module
| Module | What trips facilitators up | What to stress | Where timing slips | What the pilot showed |
|---|---|---|---|---|
| [module] | [note] | [note] | [note] | [finding] |
## Readiness conversation (no score)
Asked of each facilitator: how do you see yourself delivering [module]? What would help? What do you want on the first delivery? | Agreed together: [solo / with a co-facilitator / after another round]
## Decision
[L&D lead] and each facilitator agree the first-delivery arrangement by [date]; [L&D lead] confirms the delivery calendar by [date].
```

## Done When
- Every facilitator delivers at least one segment and gets feedback against the learning points.
- The practice rounds use the facilitator guide's what-if notes in rising order, and each module has delivery notes that include what the pilot showed.
- The readiness guide has no score, rating or pass mark anywhere.

## Quality Bar
- Feedback is spoken to the facilitator in the room and kept by them; no file is built on anyone.
- Segment lengths and practice times are [placeholders] you set.
- A request for a scorecard or a comparison of facilitators is declined, and the readiness conversation is offered in its place.
- Readiness is a conversation between the L&D lead and each facilitator, never a score, a certificate ranking or a comparison of trainers.

## Next
Run ldg-build-the-job-aid (Build the Job Aid) to carry the learning from the room into the work.

## About the makers

This pack is made by 90n ([90n.ai](https://90n.ai)): AI-native ways of working and tools for Product, Marketing and HR teams, built by ex-McKinsey founders. We map where time and money leak, redesign the work around AI and stay until your people run it themselves, and we run our own company on Claude. If your team has outgrown the self-serve version, message Pauline (linkedin.com/in/paulinebertry).

