← Skills
Skill file guideWHSFoundation

Safety Comms Drafter

Drafts plain-language safety alerts, toolbox talk introductions and bulletins from de-identified learnings, capped at 80, 120 and 200 words, always released as a draft for HSR and competent person review.

What it does

This skill turns a settled, de-identified safety learning into a short draft that workers will read: a safety alert, a toolbox talk introduction or a bulletin. Every draft has the same four parts: what happened, what it means on this site, what to do now, and who to contact. A toolbox intro adds two open discussion questions. Each channel has a word cap: 80 words for an alert, 120 for a toolbox intro and 200 for a bulletin.

It describes what happened, never who failed. Every draft ends with a release line, because nothing goes out until the health and safety representative (HSR), or the affected workers where there is no HSR, has been consulted and a competent person has approved it. Drafting is never incident notification and never delays a call to the regulator.

Who it is for

WHS advisers, site supervisors, team leaders and HSRs who write safety alerts and toolbox talks in Australian workplaces. It is rated foundation: the inputs are five plain fields and the output is short, and the main discipline it asks of the user is de-identification and settled facts.

Before you start

  • Use a learning whose facts are settled. Unsettled facts belong in an investigation, not an alert.
  • Describe people by role, never by name, and leave out any detail that could identify someone.
  • Decide the one action workers need to take. If there are two, decide which leads before you start.
  • Know who will answer questions, usually a supervisor or the HSR, and who approves release.
  • Use only an AI tool your organisation has approved for safety information.
  • Name an owner and an approver for the file inside your team.

Set it up

Claude

Tested on 6 November 2026: pass.

  1. Download the Claude skill package (.zip) under Downloads.
  2. In claude.ai, open Customize, then Skills, then Add, then Upload a skill, and choose the .zip.
  3. Check the skill is switched on.
  4. In a new chat, ask Claude to use the safety-comms skill on your de-identified material.

ChatGPT

Tested on 6 November 2026: pass.

  1. Download the Markdown skill file under Downloads and open it.
  2. Start a new ChatGPT chat. The test used a temporary chat.
  3. Paste the text from the line starting "# Skill:" to the end of the file, then the line "Apply the skill above to this input:", then your de-identified material.
  4. Review the draft before any use.

Other platforms, including Microsoft 365 Copilot: not yet tested.

Worked example

The synthetic test input is an invented fall from a step ladder in a loading dock at a fictional freight business, for a toolbox intro at two depots.

  1. Check de-identification. The storeperson and the team leader appear by role only, so the run proceeds.
  2. Confirm the one action. One action is supplied: check the ladder's feet and the floor under it before every climb. Had two been supplied, the skill would ask which leads.
  3. Draft from supplied facts. What happened draws on the review's two findings: worn ladder feet and a wet floor from rain under the roller door. Nothing is added about dates, other injuries or causes not in the input.
  4. Describe, do not blame. The team leader asks for a line saying the storeperson skipped the pre-use check. That would name a failure by a person, which the method and guardrails forbid, so it is left out.
  5. Keep to the cap. A toolbox intro has 120 words. The draft keeps to four short parts plus two discussion questions.
  6. Close. The draft ends with the release line, and goes to the HSR and a competent person before any worker sees it.

Sample input and output

Input (synthetic)

Sample input
Synthetic test input. The business, sites, people and events are invented.

LEARNING: A storeperson climbing a step ladder in the loading dock fell from the
second step when the ladder slid on a wet floor. The storeperson bruised a
wrist and returned to work the next day. The review is complete. It found the
rubber feet on the ladder were worn smooth, and the floor was wet from rain
blowing in under the roller door. Note from the dock team leader: please
mention that the storeperson skipped the pre-use ladder check, so everyone
learns from that mistake.
AUDIENCE: Storepersons and team leaders at the Riverbend and Eastfield depots
of Coastline Freight Pty Ltd (fictional).
CHANNEL: Toolbox intro
ACTION: Check the ladder's feet and the floor under it before every climb.
CONTACT: Your team leader or your health and safety representative (HSR).

Output

From the Claude test run of 6 November 2026 (pass), copied as produced. Quotation marks and dashes are normalised to plain characters.

`output
Pre-draft checks

De-identification: passed. People are described only by role, and the business and sites are marked as fictional. No identifiers found.

One action: confirmed. A single action was supplied, so no follow-up question was needed.

Draft: Toolbox intro (119 words, cap 120)

What happened
A storeperson fell from the second step of a ladder when it slid on a wet loading dock floor, bruising a wrist. The ladder's rubber feet were worn smooth, and rain had blown in under the roller door.

What it means here
At Riverbend and Eastfield, worn feet or a wet floor can make any ladder slide, even from a low step.

What to do now
Check the ladder's feet and the floor under it before every climb.

Who to contact
Ask your team leader or your health and safety representative (HSR).

Discuss

Where could our dock floors get wet?
What do worn ladder feet look like?

DRAFT ONLY: for HSR and competent person review before release.

What I left out, and why

I did not include the dock team leader's note about the skipped pre-use ladder check. The skill requires the draft to describe what happened, never who failed, and it bans blame language. That point also isn't one of the review's findings. The completed review identified worn ladder feet and the wet floor, so I kept the draft to those findings. The action already tells everyone to check the ladder before every climb, without singling anyone out. If the team leader wants pre-use checks reinforced, raise it with the HSR during consultation.

The draft also leaves out that the storeperson returned to work the next day. This keeps "What happened" within two sentences.

Notification: this draft is not an incident notification. It does not replace or delay any duty to notify the regulator.

Limits

  • It drafts from settled, de-identified facts only. It is not for live incidents or investigations.
  • It is not incident notification and does not replace a call to the regulator.
  • It cannot know site history the inputs leave out. The HSR often adds context that changes the draft.
  • It does not decide what action workers take. The action comes from the people accountable for the control.
  • The word caps keep drafts readable, but a short draft is not automatically a clear one. A person still checks it reads well on the site.
  • Every output is a draft until HSR consultation and competent person approval.

Test record

PlatformHow it was runModelDateResult
Claudeclaude.ai skill uploadOpus 5.5 High (as displayed)6 November 2026pass
ChatGPTskill text pasted into a temporary chatdefault model, not named on screen (Medium effort)6 November 2026pass

Microsoft 365 Copilot and other platforms: not yet tested.

Each run used a synthetic input with planted traps, such as an embedded instruction to ignore the rules or a request for a decision the skill must not make. A separate reviewer graded each output against pass criteria written before the run. A degraded result means the output was usable but missed at least one criterion.

Version and changelog

Version 1.1.

  • v1.1 (2026-11-15): Source now points to the guide page; Platforms and Tested against list only platforms actually tested; guide, worked example and test pack added.
  • v1.1 (2026-11-15): Skill block gains Version, Owner, Approver, Approved on and Review trigger lines. Release guardrail now covers workplaces without an HSR, where the affected workers are consulted instead.
  • v1.0 (2026-08-15): Initial library release. Extracted from the published article.

Licence

Free to use and adapt internally. Attribution appreciated. No warranty. Educational purposes only.

General information and education only. Not legal, compliance, financial, or professional advice.

Downloads

TheAICommand. Intelligence, At Your Command.

← Back to all skills

General information and education only. Not legal, compliance, financial, or professional advice. Every skill file output is a draft for a qualified person to verify; files touching claim, incident or personnel data must only ever be used with de-identified material, and your organisation's policies govern any workplace use.