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 joao-aires/agent-skills-public --skill presentation-buildinggit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/presentation-building)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/presentation-building"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/presentation-building/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/joao-aires/agent-skills-public/presentation-building"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/presentation-building.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 | $0.00042 | $0.00598 |
| Opus 5.5 | $0.00017 | $0.00239 |
| Sonnet 5.5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
presentation-building 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 13d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build a presentation around its message
Create or refine a portable single-file HTML deck, with local attachments when needed. Establish the audience, purpose, key message, presentation setting and accepted visual identity before choosing slide layouts. Preserve the requested format and scope; this skill's HTML approach is a particular deliverable, not a requirement for all presentation work.
Shape the narrative and visual direction
Decide what the audience should understand or choose by the end, then arrange the argument that gets them there. Use supplied evidence to establish the situation, explain the consequential choice and support the recommendation. Give each slide a distinct contribution to that argument, with enough context that its main claim is understandable.
Choose the visual form after deciding what the slide needs to explain. A comparison needs common dimensions; a sequence needs meaningful order; a diagram needs relationships; an image needs a reason to carry attention. Preserve the author's voice and distinguish facts, illustrative examples and proposals. Remove repeated claims and divide dense material when doing so improves the explanation, without inventing a fixed slide count or card arrangement.
Derive typography, palette, density and motion from the brief. Reuse an accepted deck's identity during ordinary edits. The original dark scroll-driven profile is available as a starting point; its colors, title patterns and component counts are examples to adapt to the audience and content.
Construct with the existing resources
| Need | Resource |
|---|---|
| HTML construction or repair | Implementation guide: skeleton conventions, component catalogue, fullscreen behavior and known rendering issues. |
| A suitable starting document | Presentation skeleton. |
| Useful chronology or a requested timeline | Timeline addon; preserve its integration contract. |
What ships with it
3 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.
- 13d ago Changed · +8 lines f48aae231b96
- 16d ago Changed · -588 lines · -55 tokens per session 810bc85f7c16
- 20d ago Changed · +1 lines c498bb3681de
- 23d ago Changed · +8 lines d397df59f271
- 2mo ago First seen · 611 lines · 97 tokens per session scan A 2c8b4dd9f3f8
presentation-building is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed 7d ago), licensed MIT. It adds 42 tokens to every session and 598 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…