agentleFS
nthnclrknthnclrk/enablement-skills/skills/one-pager-and-slide-outline/SKILL.md

one-pager-and-slide-outline

Skill14 starsChanged 8 months agoMITView on GitHub

Package a defined or approved narrative into a concise one-pager, an assertion-led slide outline, or both from supplied source material. Use for leave-behinds, briefing notes, internal memos, and stakeholder updates when the underlying strategy already exists. Route launch readiness or training design to product-launch-enablement, raw release translation to release-notes-to-seller-updates, message strategy to value-prop-and-positioning, and finished visual production to the user's presentation workflow.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use slide headlines to carry the argument where the evidence supports a claim.

    line 10
  2. Very specific:

    If the user needs positioning first, use value-prop-and-positioning.

    line 16
  3. Distinctive:

    Ask only for what changes the artifact:

    line 22
  4. Distinctive:

    Do not invent evidence or approved claims.

    line 30
  5. Distinctive:

    Read references/narrative-outline-template.md for the one-pager flow and slide-headline rules.

    line 34
  6. Distinctive:

    Write one thesis and one ask.

    line 40
  7. Distinctive:

    If both are requested, reuse the same evidence spine.

    line 44
  8. Distinctive:

    Keep source and approval notes separate from the reader-facing copy.

    line 52
  9. Distinctive:

    No visual design, no slide production

    line 56
  10. Distinctive:

    Every major claim has a source or an explicit gap.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

One-pager and slide outline

Turn supplied messaging into a one-pager or slide outline that helps its audience understand the evidence and take the intended action.

Use slide headlines to carry the argument where the evidence supports a claim. Navigation, instructions, and genuine questions may use other heading forms.

Assertion. "Missed handoffs are now a Friday-ship risk, not an ops nuisance."

Topic. "Overview." "Our solution." "Next steps."

If the user needs positioning first, use value-prop-and-positioning. If they need a launch plan, use product-launch-enablement. This skill does not produce finished slides.

Inputs

Reuse supplied context first. If a missing company fact would change the result, check the relevant sections of .enablement/context.md when available. Preserve source dates and approval limits.

Ask only for what changes the artifact:

  1. Audience, channel, and whether it is internal, customer-facing, or partner-facing
  2. The single objective and the ask
  3. Source material and which claims are approved for that audience
  4. Output branch: one-pager, slide outline, or both
  5. Length or slide-count limit

Do not invent evidence or approved claims.

Supporting material

Read references/narrative-outline-template.md for the one-pager flow and slide-headline rules. Skip it if the user already specified a house format.

Procedure

  1. Pick the branch before drafting. Do not produce both unless asked.
  2. Build a claim register: fact, interpretation, assumption, source, approval.
  3. Write one thesis and one ask. Everything else supports those two sentences.
  4. Change the information hierarchy for the job: executive decision, seller action, partner execution, or internal alignment. Do not only change tone.
  5. One-pager: lead with the point the reader needs, then include the context, proof, and action necessary to support it. Fit the requested page limit; preserve a supplied structure when it works.
  6. Slides: one assertion, one evidence cue, one speaker intent per slide.
  7. If both are requested, reuse the same evidence spine.
  8. Appendix only when it protects the core from clutter.
  9. Final pass: claims, audience safety, length, next action.

Sending or publishing the material requires explicit approval of the audience and final copy.

What to return

Keep source and approval notes separate from the reader-facing copy. For a light edit, preserve accurate content and the author's voice; report only material evidence or approval gaps.

  • One-pager only, slide outline only, or both, matching the request
  • Audience variants only when asked or when the audience actually changes the argument
  • No visual design, no slide production

Quality bar

  • One dominant argument.
  • Slide headlines can be read as claims.
  • Every major claim has a source or an explicit gap.
  • The next action has an owner.
  • Internal-only proof never appears on a customer or partner artifact.
  • A reader can use it without reconstructing the source pile.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.