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 Orkas-AI/Orkas-Awesome-AgentSkills --skill html-pptgit clone --depth 1 https://github.com/Orkas-AI/Orkas-Awesome-AgentSkillsWrote 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/orkas-ai/orkas-awesome-agentskills/html-ppt)<a href="https://agentmods.dev/skills/orkas-ai/orkas-awesome-agentskills/html-ppt"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/html-ppt/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/orkas-ai/orkas-awesome-agentskills/html-ppt"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-awesome-agentskills/html-ppt.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 | $0.00003 | $0.00888 |
| Opus 5 | $0.00002 | $0.00444 |
| Sonnet 5 | $0.00001 | $0.00178 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
html-ppt 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 11d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML PPT
When to Use
Use when the user has a structured single-slide HTML file or small HTML slide family and wants an editable .pptx made of native PowerPoint objects.
Use only when the HTML matches an existing preset or when the user accepts adding a new preset first.
Do not promise arbitrary HTML/CSS fidelity. Do not use this as a screenshot exporter.
Current Presets
v9-architecture: header, title, summary box, driver panel, architecture stack, judgement chain.ai-runtime-page: header, title, lead box, input/output chips, runtime modules, support layers, base layer.
First-Run Setup
From the skill directory:
npm ci
npm run check-env
If npm ci fails because the lockfile is stale or unavailable, use npm install, then rerun npm run check-env.
Read references/setup.md when using the skill on a new machine or dependency state is unclear.
Workflow
- Inspect the HTML and identify the slide family.
- Read
references/preset-decision-rules.mdif preset fit is uncertain. - Reuse an existing preset only when the page family is genuinely close.
- If no preset fits, add a new preset instead of forcing a bad conversion:
- DOM extraction rules
- layout/render mapping rules
- QA/preflight rules
- Convert with the bundled Node script.
- Run preflight QA on the generated model.
- Open or preview the PPTX when visual fidelity matters. Check spacing, overflow, arrow direction, text wrapping, and object editability.
Commands
npm run check-env
node scripts/html_to_pptx.js <input.html> <output.pptx> [--preset=v9-architecture|ai-runtime-page] [--dump-model <file.json>]
node scripts/preflight_qa.js <model.json> [--preset=v9-architecture|ai-runtime-page] [--report <report.json>]
Return Format
For a successful conversion, return:
- generated
.pptxpath - preset used
- whether dependencies and QA passed
- visual review status
- known fidelity limitations
For unsupported HTML, return:
- why no preset fits
- whether a new preset is recommended
- the minimum extraction/layout/QA work needed before conversion
What ships with it
19 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.
- package-lock.json 17 KB
- package.json 591 B
- references/preset-decision-rules.md 6.1 KB
- references/preset-template.md 2.7 KB
- references/presets.md 1.3 KB
- references/qa-heuristics.md 3.7 KB
- references/roadmap.md 618 B
- references/setup.md 2.4 KB
- references/usage-principles.md 1.1 KB
- scripts/ai_runtime_preset.js 8.9 KB runs code
- scripts/check_env.js 3.0 KB runs code
- scripts/html_to_pptx_v9.js 21 KB runs code
- scripts/html_to_pptx.js 2.9 KB runs code
- scripts/layout_ai_runtime.js 2.6 KB runs code
- scripts/layout_template.js 1.5 KB runs code
- scripts/layout_utils.js 1.6 KB runs code
- scripts/layout_v9.js 8.3 KB runs code
- scripts/preflight_qa.js 15 KB runs code
- scripts/preset_template.js 3.9 KB runs 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.
- 11d ago First seen · 96 lines · 3 tokens per session scan A f53b2ba7adb3
html-ppt is a skill published in the GitHub repository Orkas-AI/Orkas-Awesome-AgentSkills (13 stars, last pushed 2mo ago), licensed MIT. It adds 3 tokens to every session and 888 once invoked, about $0.0000 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
download-media
Use when user wants to download, save, or extract media files such as photos, videos, and documents from Telegram messages.
viral-tech-reel-editor
End-to-end viral tech reel production for Instagram Reels and TikTok using 2026 trend grammar — retention-first pacing, punch-ins, 3D cinematic AI-generated shots, motion design graphics, proof b-roll, trending SFX, karaoke captions (Georgian/English), safe-zone layout, and QA-gated 1080x1920 export. This skill should…
branded-deck-builder
Builds PowerPoint decks on the user's own company template and checks every slide against written brand rules (colours with hex codes, fonts, logo placement, banned visuals). Use when the user asks for a branded, on-brand, CI-compliant or corporate-template presentation, or wants a deck that follows company design…
pptx
Create, read, edit, or combine PowerPoint (.pptx) decks, including layouts, notes, comments, and templates. Use when PowerPoint is an input or deliverable.
mermaid-tools
Extract Mermaid diagrams from Markdown and render PNG images with the bundled tools when a diagram image or batch conversion is needed.
word-cloud
Generate beautiful word clouds — static or animated — from any input source. Handles text extraction from PDF, DOCX, XLSX, PPTX, HTML, CSV, TXT and produces production-ready components. Includes light/dark theming, sentiment/POS color coding, shape masking, and multiple animation modes.