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/luccapinto/agentic-data-kit/building-html-presentationsnpx skills add luccapinto/agentic-data-kit --skill building-html-presentationsgit clone --depth 1 https://github.com/luccapinto/agentic-data-kitWhat 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 | $0.00103 | $0.01892 |
| Opus 5 | $0.00051 | $0.00946 |
| Sonnet 5 | $0.00021 | $0.00378 |
| Haiku 4.5 | $0.00010 | $0.00189 |
Grade A, and why
building-html-presentations 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 2d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: building-html-presentations
Build presentations as code so they are versionable, diffable, and reproducible. This skill
covers when to use each format and gives starters you copy and fill with real content. Pair it
with applying-visual-identity to make the output on-brand.
Pick the format first
| Output | Use when | Engine | Export |
|---|---|---|---|
| Slide deck | Live readout / meeting; linear narrative, fixed canvas | reveal.js (default) | HTML, PDF (?print-pdf) |
| Flexible / scrollable deck | Slides that hold more than one screen and need in-slide scroll + buttons to switch visuals | custom vanilla JS (flex-deck.html) |
HTML |
| Interactive site | Self-serve exploration; one long scrolling page with anchors | single static HTML page (interactive-site.html) |
HTML |
| Designed report PDF | Polished consulting-style document (action titles, exhibits) | HTML print template (report-pdf.html) |
PDF (print) |
| Quick handout PDF/PPTX | Plain Markdown deliverable, no custom design | Marp (Markdown → PDF/PPTX) | PDF, PPTX |
| Editable PowerPoint | The deliverable must be a native, editable .pptx |
→ use the generating-pptx skill (python-pptx) |
PPTX |
Default to reveal.js: most mature, pure HTML/CSS (easy theming from DESIGN.md), and it
exports to PDF — so one source covers deck + site + print. Reach for Marp only when the
deliverable is fundamentally a document (Markdown-only, clean PDF/PPTX, no interactivity).
Slidev is a fine choice for fully technical audiences already on Node/Vue — mention it,
don't default to it.
Workflow
- Audience & format. Exec → fewer slides, takeaway titles, no code. Technical → allow detail/appendix. Choose deck vs site vs PDF (table above) and say which.
- Outline before slides. Agree the storyline (5–9 beats) before writing HTML. Lead with the conclusion (BLUF), then evidence, then "so what / next".
- Apply the brand. If a
DESIGN.mdexists, loadapplying-visual-identityand map its tokens to CSS variables (see that skill). Otherwise use the neutral defaults in the starter. - Build from a starter (
templates/), drop in real numbers and charts, keep it self-contained (works offline; pin CDN versions or vendor the files). - Export if needed (see the export note below).
What ships with it
7 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.
- 2d ago First seen · 100 lines · 103 tokens per session scan A 60aadf24238d
building-html-presentations is a skill published in the GitHub repository luccapinto/agentic-data-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,892 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
release-dbt-mcp
Release a new version of dbt-mcp to PyPi.
fact-checking
Review and validate claims using counter-hypothesis testing. Use when verifying technical content, checking references, validating API endpoints, or performing quality assurance on deliverables.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.
agentic-workflow-designer
Conversational skill that interviews users to design new agentic workflows.
security-review
How to review PRs for security — credentials, injection, workflow permissions, supply chain, git operation safety.