agentleFS
samulee003samulee003/agentic-ppt-skills/skills/presentation-story-architecture/SKILL.md

presentation-story-architecture

Skill0 starsChanged 24 days agoMITView on GitHub

Turns an approved brief and supported claims into a thesis, audience journey, chapter roles, transitions, and slide-by-slide jobs for the main talk and backup. Use when the story-architecture gate is current for a presentation project or when a router asks for the story and storyboard.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use when story-architecture is the current gate.

    line 8
  2. Very specific:

    Read repo instructions, PRESENTATION-BRIEF.md, EVIDENCE-LEDGER.md, and the cited source files before structuring the talk.

    line 10
  3. Very specific:

    Write STORY.md from templates/STORY.md.

    line 13
  4. Distinctive:

    If a chapter needs unsupported evidence, return the work to evidence instead of letting the chapter enter the story.

    line 16
  5. Distinctive:

    Write spoken transitions that explain why the next chapter or slide must exist.

    line 18
  6. Very specific:

    Run node .agents/skills/make-presentation/scripts/unslop-check.mjs <work-root>/STORYBOARD.md and fix findings using …

    line 21
  7. Distinctive:

    Language Separation Contract: Ensure all storyboard on-screen draft copy is standard Traditional Written Chinese (繁體書面語).

    line 27
  8. Distinctive:

    Keep chapter order tied to the promised audience outcome, not to the order sources were found.

    line 39
  9. Distinctive:

    Use another structure when it better fits the product, audience, and evidence.

    line 41
  10. Distinctive:

    Stop once the thesis, audience journey, chapter roles, transitions, main/backup boundaries, and slide jobs are coherent enough for story …

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Build the story architecture

Use when story-architecture is the current gate.

  • Read repo instructions, PRESENTATION-BRIEF.md, EVIDENCE-LEDGER.md, and the cited source files before structuring the talk.
  • Require one memorable thesis.
  • Require an explicit audience change from where the talk starts to where it should end.
  • Write STORY.md from templates/STORY.md.
  • Write STORYBOARD.md from templates/STORYBOARD.md.
  • Build the story from the approved brief and supported evidence claims only.
  • If a chapter needs unsupported evidence, return the work to evidence instead of letting the chapter enter the story.
  • Assign each chapter a role such as context, tension, proof, decision, action, or closing commitment.
  • Write spoken transitions that explain why the next chapter or slide must exist.
  • Separate the main-talk range from backup or Q&A material.
  • Confirm one necessary job and one dominant message per slide.
  • Run node .agents/skills/make-presentation/scripts/unslop-check.mjs <work-root>/STORYBOARD.md and fix findings using ../make-presentation/references/unslop-copy.md before finishing.
  • Mandatory Page Archetype Assignment: In STORYBOARD.md, assign each slide explicitly to one of the 4 visual archetypes to guarantee visual dynamic rhythm and prevent repetitive box layouts:
    1. [大字流]: Hero thesis, golden rules, safeguard statements (e.g. 100px+ punchline cards).
    2. [半圖半文]: Split editorial grid 1.1:0.9 (visual vignette on one side, structured action steps on the other).
    3. [大圖流]: Full-canvas vector diagram (70%+ canvas occupied by 3px ink stroke SVG system model).
    4. [物理卡片流]: 2~3 multi-card grid with micro-rotations and <Steps> progressive reveal.
  • Language Separation Contract: Ensure all storyboard on-screen draft copy is standard Traditional Written Chinese (繁體書面語); keep spoken colloquialisms exclusively for spoken transitions and speaker notes.
  • Split the slide rather than shrink text or pack distinct messages onto one page. Remove ornamental, duplicate, or “nice to have” pages.
  • Meaningful Brevity (Anti-Over-Pruning): Text pruning must eliminate fluff and secondary clutter while preserving clear, grammatically sound, and intellectually substantive core takeaways. Do not reduce statements to cryptic 2-word fragments.

Instructional design & 4MAT learning cycle

Incorporate adult learning dynamics (ATD / 4MAT / Kirkpatrick Level 2 & 3 behavior transfer):

  1. Why (Relevance & Emotional Safety): Open with visceral pain points and validation to establish psychological safety before introducing solutions.
  2. How / Logic (Underlying Cognitive Insight): Deconstruct the psychological and systemic mechanisms (e.g. dignity defense, family subsystems) so the audience understands the why behind behaviors.
  3. What (Actionable Tool Chunking): Deliver chunked, memorable tools, role definitions, and boundary frameworks with high memory stickiness.
  4. Action / What If (Behavioral Rehearsal & Transfer): Provide concrete dialogue templates, case vignettes, and takeaway scaffolding so learning converts into immediate real-world practice.
  • Keep chapter order tied to the promised audience outcome, not to the order sources were found.
  • Allow SCQA but never force it.
  • Use another structure when it better fits the product, audience, and evidence.
  • Stop once the thesis, audience journey, chapter roles, transitions, main/backup boundaries, and slide jobs are coherent enough for story grilling or prototyping.

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.