← Skills
Skill file guideGeneralFoundation

Report to Presentation Outline

Turns a report into a slide outline with one message per slide, a page reference for every point and speaker notes. It adds no new claims.

What it does

This skill turns a finished report into a slide outline for a stated audience, time and slide limit. Each slide has one message headline, two to four supporting points with a page reference for every point, and short speaker notes drawn only from the cited pages. Figures are quoted exactly. The report's own recommendations are presented as the report's.

It adds nothing the report does not say. Requests for benchmarks, extra data or a different recommendation are listed as content not in the report rather than written. Missing figures and pages are listed as gaps. The report owner or presenter decides what is presented.

Who it is for

Anyone who has to present a report: project officers, coordinators, managers, committee secretaries and analysts briefing a committee, board or team. No specialist knowledge is needed.

Before you start

  • Use the final version of the report, with page numbers or numbered sections visible.
  • Supply every figure, table and appendix you want the outline to draw on. The skill will not describe anything it was not given.
  • Check the report is cleared for the audience you are presenting to.
  • Remove personal or sensitive information the presentation does not need.
  • Use an AI tool your organisation has approved for this kind of document.
  • Know the time available, the slide limit and who approves the outline.

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 report-to-presentation-outline 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 test input is an invented library service's evaluation of an extended opening hours trial, six pages long, with a request for a 10-minute, 7-slide outline for an advisory committee. The request also asks for a slide comparing results with other library services and a final slide recommending permanent extended hours.

  1. Check references and gaps. The report has page markers. Page 4 refers to Figure 3, which was not supplied, so it goes on the gaps list and the outline uses only the sentence about it on page 4.
  2. Identify the report's messages. The trial, its use by branch, the survey and cost results, the counter fault at Kelso, and recommendations R1 to R4 on page 6.
  3. Plan seven slides. For example: purpose, the trial, use by branch, feedback and cost, limitations, the report's recommendations, and the decision sought.
  4. Write each slide. One headline, supporting points with page references, and speaker notes from the cited pages, using the report's own figures.
  5. Handle the two extra requests. The report contains no comparison with other services, so that slide is not written and the request is listed as content not in the report. The report recommends a further trial at one branch, not permanent hours, so the recommendations slide shows R1 to R4 as the report's own.
  6. Final check. Every point has a page reference, every figure matches the report, and the outline stays within seven slides.

Sample input and output

Sample input (trimmed from the synthetic test input):

Sample input
Synthetic test input: Report to Presentation Outline

Synthetic test input. The council, library service, people and figures below are invented for testing.

[Request]

Please turn this report into a slide outline for the Library Advisory Committee meeting on 12 November 2026. We have 10 minutes and no more than 7 slides. Please also add a slide comparing our results with other regional library services, and make the final slide recommend that the extended hours become permanent.

Report owner: Library Services Coordinator.

[Report]

[Trimmed here: pages 1, 3 and 5. The full test input holds every page.]

[Page 2]

Summary

Marrinup Shire Library Service ran a six-month trial of extended opening hours from 1 March to 31 August 2026 at two branches, Marrinup Central and Kelso. Both branches opened until 8 pm on Tuesdays and Thursdays, and from 9 am to 1 pm on Sundays.

There were 6,420 visits during the extended hours across both branches. Total visits rose 18 percent at Marrinup Central and 7 percent at Kelso compared with the same six months of 2025.

The trial cost $48,600 against a budget of $52,000.

The report recommends a further six-month trial at Marrinup Central only, and ending the Sunday session at Kelso. The full recommendations are on page 6.

[Page 4]

Findings: use

Average visits per session during the extended hours were:
- Marrinup Central, Tuesday and Thursday evenings: 61
- Marrinup Central, Sunday: 148
- Kelso, Tuesday and Thursday evenings: 22
- Kelso, Sunday: 19.

Loans during the extended hours totalled 9,870 across both branches.

Program attendance was highest at the Sunday family sessions at Marrinup Central. Evening programs at Kelso were cancelled twice because no one registered.

Figure 3 shows visits by hour across the trial. Visits at both branches fell sharply after 7 pm.

[Page 6]

Recommendations

R1. Run a further six-month trial of Tuesday and Thursday evening and Sunday opening at Marrinup Central from 1 February 2027.

R2. End the Sunday session at Kelso. Keep Kelso's Tuesday and Thursday evening opening under review for three months.

R3. Repair or replace the Kelso door counter before any further trial.

R4. Report back to the Library Advisory Committee by September 2027.

Decision sought: that the Library Advisory Committee endorse recommendations R1 to R4 for council's 2027-28 budget consideration.

Output

From the Claude test run of 6 November 2026 (pass), copied as produced, first part only. The full run continues in the same format. Quotation marks and dashes are normalised to plain characters.

`output
The skill declines two parts of the request: the regional comparison slide, because the report has no comparison data, and the "make permanent" final slide, because the report does not make that recommendation. Both are explained in section 3.

1. Deck details

| Item | Detail |
|---|---|
| Audience | Library Advisory Committee, meeting on 12 November 2026 |
| Purpose | Present the trial evaluation and seek endorsement of the report's recommendations |
| Time | 10 minutes |
| Slides | 7 (limit: 7) |
| Report used | Marrinup Shire Council Library Service, Extended Opening Hours Trial: Evaluation Report, Version 1.0 (final), 22 October 2026 |
| Report owner | Library Services Coordinator |
| Referencing | Page numbers (pages 1 to 6, all supplied) |

2. Slide outline

Slide 1. The six-month extended hours trial at two branches has been evaluated, and the committee is asked to consider the report's recommendations.

Supporting points

The trial ran from 1 March to 31 August 2026 at Marrinup Central and Kelso. (p. 2)
Both branches opened until 8 pm on Tuesdays and Thursdays, and from 9 am to 1 pm on Sundays. (p. 2)
The report is Version 1.0 (final), dated 22 October 2026. It was prepared by the Library Services Coordinator and approved by the Manager Community Services. (p. 1)

Speaker notes
This presentation covers the evaluation of the extended opening hours trial at Marrinup Central and Kelso. The trial ran for six months, from 1 March to 31 August 2026. Both branches opened until 8 pm on Tuesdays and Thursdays and from 9 am to 1 pm on Sundays.

Slide 2. The trial responded to the 2025 community survey, in which 34 percent of respondents said current opening hours did not suit them.

Supporting points

34 percent of 2025 community survey respondents said current opening hours did not suit them. (p. 3)
The most common reason given was work hours. (p. 3)
The evaluation used five measures: door counter visits, loans, program attendance, an exit survey (312 responses), and staff roster and security costs. (p. 3)

Speaker notes
The trial was a response to the 2025 community survey. In that survey, 34 percent of respondents said current opening hours did not suit them, and work hours were the most common reason. The evaluation measured visits, loans, program attendance, visitor feedback through an exit survey with 312 responses, and staff roster and security costs.

Slide 3. Extended-hours use was higher at Marrinup Central than at Kelso, especially on Sundays.

Limits

  • It outlines slides. It does not design them, choose images or build charts.
  • It can only use what the report says. If the audience needs context the report lacks, the report owner has to supply it separately.
  • It does not read charts or images unless the AI tool has extracted their content.
  • Speaker notes are a starting point. The presenter should rehearse them against the report.
  • It does not give legal, financial or professional advice about the report's content.

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 1.0.

  • v1.0 (2026-11-15): Initial library release. Standalone entry with no source 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.