agentleFS
Natan-MohartNatan-Mohart/24-strategy-skills-for-claude/skills/narrative-builder/SKILL.md

narrative-builder

Skill41 starsChanged 3 months agoMITView on GitHub

Structures a strategy or recommendation into the Pyramid Principle (answer-first, MECE-supported) and a Situation-Complication-Resolution arc, so a senior audience gets the conclusion before the reasoning instead of a chronological walk through the analysis. Use whenever the user needs to turn analysis into an executive-ready narrative, deck, or presentation, or has a draft that walks through the work chronologically ("first we looked at X, then we looked at Y") instead of leading with the answer.

The file

Files
SKILL.md

Narrative Builder

When to use

Use whenever analysis needs to become a presentation, memo, or pitch for a senior or executive audience — especially when the current draft is structured chronologically (the order the analysis was actually done) rather than around the answer the audience needs first. A chronological walk-through is how you did the work; it is rarely how an executive wants to receive it.

What it does

Restructures the material using the Pyramid Principle (Barbara Minto): lead with the answer/recommendation, support it with a small number of MECE arguments, each backed by evidence — rather than building up to the conclusion at the end. Wraps that structure in a Situation-Complication-Resolution arc so the narrative has tension and stakes, not just a stacked argument.

Method

  1. Write the governing thought first: the single sentence that is the answer, recommendation, or conclusion — if you can't state it in one sentence before building anything else, the analysis isn't actually finished yet.
  2. Identify the 3-4 supporting arguments that, together, are both necessary and sufficient to justify the governing thought (MECE) — not a longer list of everything that's true and relevant, which dilutes the argument instead of strengthening it.
  3. Under each supporting argument, place only the evidence that directly proves that specific argument — resist the instinct to include every analysis performed; anything that doesn't directly support one of the 3-4 arguments belongs in an appendix, not the main narrative.
  4. Frame the whole narrative with Situation-Complication-Resolution: the situation (shared, uncontested context), the complication (what changed or what's at stake — this is what creates the need for a decision now), the resolution (the governing thought, positioned as the answer to the complication, not just a standalone recommendation).
  5. Order supporting arguments by strength or logical dependency, not by the order the underlying analysis happened to be done — the audience should never have to wait through weaker points to reach the strongest one.
  6. Write section/slide headlines as complete argumentative sentences, not topic labels — "Onboarding friction is costing $2M in preventable churn," not "Onboarding Analysis." A reader skimming only the headlines should be able to follow the entire argument.
  7. Anticipate the single hardest objection and address it explicitly within the narrative (or immediately after the recommendation), rather than leaving it for the Q&A to surface, which reads as unprepared.
  8. Cut anything that doesn't serve the governing thought, no matter how interesting or how much work went into producing it — an executive narrative is curated, not comprehensive.

Inputs

  • The underlying analysis and its actual findings
  • The single decision the narrative needs to drive
  • The audience's likely starting position and their hardest probable objection

Output format

One-sentence governing thought; 3-4 MECE supporting arguments each with its directly-relevant evidence; SCR framing (situation/complication/resolution); complete-sentence headlines throughout; explicit handling of the hardest anticipated objection; appendix for supporting analysis that didn't make the main narrative.

Example

A 40-slide analytical deck walking chronologically through market sizing, competitive analysis, and financial modeling gets restructured: slide 1 states the governing thought ("Enter the mid-market segment via partnership, not direct sales — projected to add $8M in year-2 revenue at half the customer acquisition cost of our current motion"), followed by three argument slides (market timing, unit economics, execution risk) each with only its directly supporting evidence, with the remaining 30 slides of underlying analysis moved to an appendix.

Common pitfalls

  • Building the narrative chronologically (the order the work was done) instead of around the answer the audience actually needs.
  • Including every piece of analysis in the main narrative instead of curating to what directly supports the 3-4 core arguments.
  • Writing topic-label headlines ("Market Analysis") instead of argumentative sentence headlines that carry the point on their own.

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.