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/pnp/sharepoint-skills/topic-explainernpx skills add pnp/sharepoint-skills --skill topic-explainergit 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/topic-explainer)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/topic-explainer"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/topic-explainer.svg" alt="Measured on agentmods" 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 | $0.00121 | $0.01264 |
| Opus 5 | $0.00060 | $0.00632 |
| Sonnet 5 | $0.00024 | $0.00253 |
| Haiku 4.5 | $0.00012 | $0.00126 |
Grade A, and why
topic-explainer 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Topic Explainer
When to use
Use this skill whenever the user asks to create an explainer, explainer page, or explainer dashboard for a topic. The output should be a polished, interactive HTML dashboard that explains the topic clearly for a business audience.
Use a clean, professional card-based design as the content model, but adapt the sections to fit the topic and content. Do not force every section into every dashboard.
Inputs
- Required: the topic to explain.
- Optional: target audience, organization/team context, preferred tone, source files/pages, and whether the dashboard should be saved as a SharePoint file or shown inline.
- If the topic needs current, enterprise, or document-specific information, retrieve or summarize the relevant content first. Do not invent source-specific claims.
Steps
- Identify the explainer topic, audience, and main user need from the request.
- Decide which sections fit the topic before building the dashboard. Use the strongest-fit sections only:
- Always consider: hero/header, shortest version, core concept cards, active-detail panel, comparison table, use cases/examples, governance or watch-outs, and source notes.
- Include a decision guide only when the topic asks users to choose between options, make a recommendation, follow a path, or decide “when to use what”.
- Include a Without vs With section only when the topic naturally compares adopting a capability, method, or maturity step. Skip it for side-by-side product comparisons where it feels artificial.
- Include a context overload / complexity explanation only when reusable instructions, knowledge context, complexity, or prompt burden is central to the topic.
- Include implementation, rollout, adoption, governance, or operating model sections only when relevant.
- If a section is skipped, rebalance the layout. Do not leave an empty adjacent panel. Expand the neighboring section to full width, replace the skipped section with a better-fit section, or use a single-column layout for that row.
- Build the dashboard content around the selected sections. Common section options:
- Hero/header with a short title, subtitle, and “shortest version”.
- 3–5 core concept cards for the most important ideas in the topic.
- Active concept detail panel containing: what it is, analogy, when to use it, example prompts/scenarios, and watch-outs.
- Decision guide with practical questions and recommendations, when relevant.
- Clear comparison table across the core concepts, platforms, methods, or options.
- “Without vs with” section, only when it creates real explanatory value.
- Topic-specific section such as channel selection, operating principles, adoption playbook, risks, anti-patterns, stakeholder map, maturity model, or examples.
- Searchable use cases and examples by team, role, or scenario.
- Governance notes, risks, or implementation considerations.
- Source notes listing the sources or assumptions used.
- Create the dashboard as standalone HTML/CSS/JavaScript rather than raw React unless the environment explicitly supports React build output.
- Preserve a clean professional design spirit:
- Clean card-based layout.
- Interactive concept selection.
- Search/filter for use cases where useful.
- Professional, clear tone with plain-language explanations, analogies, practical examples, and clear distinctions between concepts, benefits, limitations, and governance.
- Use this content schema when adapting the original code:
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 · 107 lines · 121 tokens per session scan A 7e32f6cee9fe
topic-explainer is a skill published in the GitHub repository pnp/sharepoint-skills (107 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 1,264 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
build-flow
Create or modify a Power Automate flow headlessly with the power-automate MCP tools. Use when asked to create a flow, add or change an action, bind a connector, or start a flow that will not start. Encodes the definition rules and the create-bind-start sequence that make headless authoring work.
debug-flow
Diagnose a failing Power Automate flow with the power-automate MCP tools. Use when a flow run failed, a flow that worked yesterday broke, failures are intermittent, or the user asks why their flow is not working. Walks the loop from finding the failed run to attributing the cause and verifying the fix.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
skill-copilot-provider
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode.
bf-to-agents-sdk-dotnet-migration
Use when migrating a Bot Framework .NET SDK bot to Microsoft 365 Agents SDK. Triggered by projects that depend on packages: Microsoft.Bot.Builder or Microsoft.Bot.Builder.Integration.AspNet.Core that want to migrate to Agents SDK.