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 learning-designergit 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/learning-designer)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/learning-designer"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/learning-designer/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/learning-designer"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/learning-designer.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 | $0.00075 | $0.01610 |
| Opus 5.5 | $0.00030 | $0.00644 |
| Sonnet 5.5 | $0.00015 | $0.00322 |
| Haiku 4.5 | $0.00007 | $0.00161 |
Grade A, and why
learning-designer 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 7d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Designer
Turn a filled Learning Request Brief into a single self-contained HTML learning dashboard that matches the established visual system (navy/yellow, CSS-only flip cards, staged path, Why/When/How/Check blocks).
When to use
- User provides or selects a Learning Request Brief
.docxgenerated from the form. - User asks to “build the learning dashboard”, “turn this brief into a learning experience”, or “design the page for this topic”.
When not to use
- Plain article or support page with no stages or interactivity.
- General slide deck without the dashboard request.
- Topics that require more than 3 stages (ask the user to revise the brief before generating).
Image handling
- Look in the same folder as the Learning Request Brief for a file named exactly
learning-visual.png(preferred) orlearning-visual.jpg. - If found, embed it as a base64 data URI inside the HTML so the page remains fully self-contained.
- Place it in the hero grid (right side) or immediately below the hero as the overview visual — the same prominent position used in the Custom Skills in PowerPoint example.
- Add a short caption if the brief supplies one; otherwise use a neutral caption such as “Overview”.
- If the image is missing, omit it cleanly and continue. Never invent an image or use a placeholder that implies content exists.
Flashcards
-
Turn
{FlashcardConcepts}and{KnowledgeChecks}into CSS flip cards using the.flip/.flipInner/.flipFacepattern added to the reference. -
Front = question or concept, back = answer.
-
Cards must flip on hover and on keyboard focus (
:hoverand:focus-within). -
Place the deck in its own section or after the relevant stage. Do not use static button quizzes for these items.
-
Do not add any organisational branding, logos, or text such as company names or site headers that are not present in the reference template.
-
Clone only the structure and content from
references/test-output-custom-skills.html. Do not invent or inject extra header elements. -
If the generated page includes any external branding, remove it before finishing.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 114 lines · 75 tokens per session scan A a271b14252e6
learning-designer is a skill published in the GitHub repository pnp/sharepoint-skills (140 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 1,610 once invoked, about $0.0003 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 2026-10-21.
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.
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…
explain
Explain a concept, system or piece of code as a diagram-first terminal answer, or as an interactive HTML page.
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.