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 skills add pnp/sharepoint-skills --skill narrated-story-animationgit clone --depth 1 https://github.com/pnp/sharepoint-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pnp/sharepoint-skills/narrated-story-animation)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/narrated-story-animation"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/narrated-story-animation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/narrated-story-animation"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/narrated-story-animation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00096 | $0.01136 |
| Opus 5.5 | $0.00038 | $0.00454 |
| Sonnet 5.5 | $0.00019 | $0.00227 |
| Haiku 4.5 | $0.00010 | $0.00114 |
Grade A, and why
narrated-story-animation 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 4d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Narrated Story Animation
When to use
Use for a customer story, campaign, product launch, market-entry journey, case study, learning tutorial, or narrative explainer that should play as a self-contained animated HTML experience. Produce HTML only. Do not create a PowerPoint, narration text file, audio file, or video unless the user explicitly asks for one.
Match the editorial Story Studio experience rather than creating a generic slide-like animation. A finished Story Studio reference and a fictional Routewise sample live in this skill's demo/ folder on GitHub.
Inputs
- Story source: user-provided brief, facts, or a named SharePoint source.
- Optional: story type, audience, language, call to action, brand direction, and destination folder.
- If the user supplies no source, create a clearly fictional sample. Never present fictional names, figures, outcomes, or quotes as real.
Steps
- Gather the story. Read a supplied SharePoint source before writing. Use only source facts or the user's stated details. If no source is supplied, label the completed story as fictional.
- Plan a 6–9 scene arc. Use only story-appropriate scene types from the Story Studio system: title, stats, bars, route, network, timeline, quote, result, and CTA.
- Write narration-ready scene data. Keep each
sayfield to 45 words or fewer, with short clauses and natural pauses. Headlines must be concise and may use only<em>for editorial emphasis. Every visible number must come from the source. Use[placeholder]where a number is needed but not provided. - Build one complete, offline-capable HTML file. Do not use CDNs, external fonts, external images, network calls, or
<script src>. - Reproduce the Story Studio design and UX:
- warm editorial paper palette, serif display typography, mono labels, red accent, fine borders, grain, framed 16:9 stage, masthead, running labels, folio, and scene count;
- scene-picker buttons when more than one story variant is included;
- animated wipe transitions, staggered text reveals, masked headline lines, reduced-motion support, and responsive full-screen stage;
- scene-specific motion: count-up statistics, bar fills, animated route and map pins, partner-network reveal, timeline progression, word-by-word quote reveal, and result confetti burst;
- caption words synchronized to narration progress, scene scrubber/progress indicators, previous, next, restart, captions toggle, narration toggle, voice picker, speed picker, full-screen control, keyboard shortcuts, and status text;
- accessibility labels, visible controls, responsive behavior, and
prefers-reduced-motionhandling.
- Narration is ON by default. On load, set narration to enabled and immediately attempt browser speech synthesis for the first scene. Keep narration enabled across scenes and wait for each scene's speech to end before auto-advancing.
- Include a voice picker. Populate it using
speechSynthesis.getVoices()with the viewer's installed English browser/system voices plus a Default voice option. React tovoiceschangedso late-loading voices appear. Selecting a voice must restart the current scene narration using that voice. Do not invent a shared voice library or claim named voices are available to every viewer. - Handle browser autoplay restrictions honestly. Browsers may block audible speech until the viewer interacts with the page. When blocked, show a prominent in-stage message such as
Narration is ready — select Play to hear it, preserve the enabled narration state, and start speech on the first click, keypress, or touch. Do not claim audio is guaranteed to play automatically. - Do not hand-edit a separate animation engine after generating the complete file. Validate that the result is a complete HTML document with working controls and no external dependencies.
- Save all HTML dashboards and animated HTML stories on this site to the Reports library. Do not upload or publish elsewhere unless the user asks for another destination.
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.
- 4d ago First seen · 51 lines · 96 tokens per session scan A cfa62812c35d
narrated-story-animation is a skill published in the GitHub repository pnp/sharepoint-skills (137 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 1,136 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
frontend-slides
OpenDesign as a worked AI-workflow example: how local agents read your files and design on your desktop — concretely. Built as a decision-grade AI literacy deck for teams new to AI, leadership.
manim-composer
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants to plan a Manim video or animation sequence, (5) User asks to "compose" or "plan" a math/science visualization.…
extract-wisdom
Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to extract wisdom or key insights from a given content source.
deliberate-ai-use
Bevisst KI-bruk i Nav: grønn og rød sone, tre-forsøks-regelen, erfaringsnivå og generer-så-forstå, med forskningen bak. Bruk når utvikleren spør om KI bør gjøre en oppgave, vil lære, eller når en oppgave skal plasseres i grønn eller rød sone.
ml-llm-wiki
Use when answering questions from this machine-learning knowledge base. Triggers: questions about transformers, attention cost and efficiency, and long-context scaling; 'what do we know about attention', 'check the ML wiki'. Read-only querying of compiled knowledge; to add, update, supersede, lint, audit, or critique…
learning-opportunities
Facilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises after architectural work (new files, schema changes, refactors). Use when completing features, making design decisions, or when user asks to understand code better. Triggers on "learning exercise", "help me…