Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/michaelengland/deckwright/narrativenpx skills add michaelengland/deckwright --skill narrativegit clone --depth 1 https://github.com/michaelengland/deckwrightWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00057 | $0.01582 |
| Opus 5 | $0.00028 | $0.00791 |
| Sonnet 5 | $0.00011 | $0.00316 |
| Haiku 4.5 | $0.00006 | $0.00158 |
Grade A, and why
narrative scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narrative
Develop the story and message before thinking about slides. This skill converts rough presentation ideas into validated narrative documents through collaborative dialogue.
Prerequisites
- User has a presentation idea, topic, or goal, OR
- A PptxGenJS generation script exists from a previous import or creation (edit mode)
Process
Edit Mode Check
Before starting, check: does a deck folder in decks/ contain a PptxGenJS generation script (a .js file containing require("pptxgenjs"))?
- If no: This is a new presentation. Follow the standard process below.
- If yes: This is an edit. Read the generation script to understand the current slides, then:
- Summarize the narrative you see in the deck — audience, purpose, key message, and story arc as you interpret them from the slide content and speaker notes
- Present this to the user as your interpretation:
"Based on the current deck, here's the narrative I see:
- Audience: [inferred]
- Key message: [inferred]
- Arc: [slide-by-slide summary of the story flow]
What would you like to change about the story?"
- Focus questioning only on what the user wants to change — skip settled topics
- Produce a narrative document as usual, noting which parts are unchanged vs. reworked
1. Understand the Context
Before asking questions, review any existing context:
- User's initial request and goals
- Any documents, data, or materials they've shared
- Prior conversation context
2. Sequential Questioning
Ask ONE question at a time. Favor multiple-choice when possible.
Core questions to explore (adapt based on context):
- Audience: Who will see this? What do they already know? What do they care about?
- Purpose: What should the audience think, feel, or do after seeing this?
- Key message: If they remember only ONE thing, what should it be?
- Constraints: Time limit? Existing template or brand guidelines?
- Content: What evidence, data, or examples support the message?
- Sources: What source materials, documents, reports, or data back up the claims?
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 166 lines · 57 tokens per session scan A 20a68ca15791
narrative is a skill published in the GitHub repository michaelengland/deckwright (2 stars, last pushed 6mo ago), licensed MIT. It adds 57 tokens to every session and 1,582 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ppt-master
AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable Brand/Style/Layout/Deck workspaces, filling native PPTX templates, and enhancing finished PPTX files. Use when the user asks to create, generate, reconstruct, regenerate, beautify, redesign…
codex-ppt
Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or outlines.
impress-presentations
Use when creating, opening, or editing LibreOffice Impress ODP presentations, or PPTX decks only when PowerPoint compatibility is explicitly required.
deep-ppt
Use when creating or revising research-style PowerPoint decks for lab meetings, journal clubs, defenses, weekly reports, or conferences, especially Chinese or English academic slides that need a resumable agent workflow, the deepPPT blue title system, evidence-led layouts, selective red key findings, package checks…
themed-cn-pptx
Build, modify, and QA-verify Chinese + IP/character-themed + QR-embeddable EDITABLE PPTX decks using PptxGenJS, with SOTA AI image generation via OpenAI GPT Image 2 or Google Nano Banana Pro, locked aesthetic recipes, and a deterministic render-QA gate (CJK overflow, text overlap, editable-text, color contrast).…
imagegen-pptx-pipeline
End-to-end stateful workflow for designing and generating editable PowerPoint decks from briefs, templates, reference decks, brand assets, data, ImageGen comps, or user-supplied slide images. Uses multi-round content/style confirmation, reviewed per-slide comps, mandatory Real-ESRGAN 4K comp/icon upscaling, built-in…