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 aaronvanston/skills-presentations --skill presentation-notesgit clone --depth 1 https://github.com/aaronvanston/skills-presentationsWrote 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/aaronvanston/skills-presentations/presentation-notes)<a href="https://agentmods.dev/skills/aaronvanston/skills-presentations/presentation-notes"><img src="https://agentmods.dev/badge/skills/aaronvanston/skills-presentations/presentation-notes/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/aaronvanston/skills-presentations/presentation-notes"><img src="https://agentmods.dev/badge/skills/aaronvanston/skills-presentations/presentation-notes.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 | $0.00067 | $0.00644 |
| Opus 5.5 | $0.00027 | $0.00258 |
| Sonnet 5.5 | $0.00013 | $0.00129 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
presentation-notes 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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presentation Notes
Generate speaker notes designed for natural, conversational delivery — not scripts to read verbatim.
Philosophy
- Riff from headlines — the slide is the prompt, not the script
- Add context verbally — explain the "why" that isn't on screen
- Tell stories — concrete examples land better than abstractions
- Acknowledge the room — react to the audience, don't just broadcast
- Land the key point — each slide has ONE thing to remember
Note Format
Speaker notes should be scannable prompts, not paragraphs.
Per-slide structure:
## Slide: [Headline]
**Key point:** [The ONE thing they must remember]
**Open with:** [First sentence or hook]
**Talk track:**
- [Bullet prompt 1]
- [Bullet prompt 2]
- [Bullet prompt 3]
**Transition:** [Bridge to next slide]
Example:
## Slide: Speed is a feature
**Key point:** Being fast isn't just nice — it's a competitive advantage.
**Open with:** "This slide captures something we keep rediscovering..."
**Talk track:**
- Every time we ship faster, customers notice and tell us
- Our competitors take months for changes we do in days
- Speed compounds — fast shipping builds momentum and morale
**Transition:** "So how do we protect that speed as we scale? That's what this next section is about..."
Notes by Slide Type
Statement slides — Focus on the story behind the statement: what led to this conclusion, what's the implication, why does it matter?
Question slides — Pause and let it land. Don't rush to answer your own question. Acknowledge the tension, then bridge to your answer.
Data slides — Contextualize the numbers: what story does the data tell? What surprised you? What would be concerning if different?
Section dividers — Keep it brief: quick framing of what's coming and how it connects to what came before.
Recap slides — Don't re-present. Touch each point quickly, add one synthesis insight, set up the "so what."
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.
- 1mo ago First seen · 83 lines · 67 tokens per session scan A 0cdedad29a0e
presentation-notes is a skill published in the GitHub repository aaronvanston/skills-presentations (15 stars, last pushed 8mo ago), licensed MIT. It adds 67 tokens to every session and 644 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 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.