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/maxedapps/agent-skills/create-slidesnpx skills add maxedapps/agent-skills --skill create-slidesgit clone --depth 1 https://github.com/maxedapps/agent-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/maxedapps/agent-skills/create-slides)<a href="https://agentmods.dev/skills/maxedapps/agent-skills/create-slides"><img src="https://agentmods.dev/badge/skills/maxedapps/agent-skills/create-slides.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 | $0.00158 | $0.01855 |
| Opus 5 | $0.00079 | $0.00928 |
| Sonnet 5 | $0.00032 | $0.00371 |
| Haiku 4.5 | $0.00016 | $0.00186 |
Grade A, and why
create-slides 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 3d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Slides
Critical rules
- No libraries, CDNs, frameworks, or build steps in the deck itself. It must
open directly from a local
index.html. - Never rebuild
core/slides.js. Navigation, key handling and thedata-enter/data-exitcontract are fixed. Extend by layering onSlidesRuntime.controller, the waycore/morph.jsdoes. - Never edit
core/slides.cssper deck. It owns structure, archetype layout and the reveal presets. Override intheme.css, or indeck.css. - Fonts must be inlined as data URIs (
tools/fonts.mjs).@font-facefiles are blocked overfile://, so a deck opened by double-click loses them. - Never invent facts, statistics, quotes, images, or licenses. Research current
claims with the
web-researchskill, cite sources, and record where every asset came from. - Derive tokens and content from the subject; derive the look from a template. Do not invent a new layout system mid-pass.
- Write semantic HTML: real headings, lists, figures, one
<section class="slide">per slide in DOM order. - "Use the space" ≠ stretching boxes to fill the viewport. It means stable hierarchy, content-sized modules, comfortable gaps, and intentional margin.
- Verify before reporting done.
npm run qafor the deck,npm run auditafter any recording. Never call a deck or an export finished on the strength of having looked at it. - User-owned copy is sacred. After the user edits text, change layout and CSS only — never rewrite their wording unless asked.
- State every assumption explicitly in the final report.
Workflow
- Inspect everything supplied — content, data, brand, delivery mode, and any script or captions the deck must back.
- Ask one grouped question covering only the real gaps. Always include the
look unless the user named a template or gave brand direction that settles
it. Defaults in brackets if you must proceed on assumptions:
- Look:
dark-marker(courses, tutorials) |light-editorial(talks, reports) |midnight-tech(developer content) |bold-keynote(pitches) |minimal-mono(research talks) — one line each, and say which you'd pick - Delivery: live talk | recorded video/tutorial | self-paced send
- Reveal model: multi-step | one-step staggered | none
- Density: sparse keynote | tutorial-comfortable
- Look:
- Research unknown or current facts before writing any slide body.
- Read
references/design.md. Outline the deck as titles only and check that sequence carries the message before writing any body copy. - Scaffold the deck:
assets/core/→core/,assets/skeleton.html→index.html- the chosen
assets/templates/<name>/→theme.css,fonts.json assets/tools/→tools/,assets/starter/*→ deck root (gitignore→.gitignore)- create an empty
deck.css npm install && node tools/fonts.mjsnpm run devrenders every archetype the template offers — read it before writing slides.
- Adapt tokens only to the subject, then write the slides. Read
references/web-slides.mdfor the DOM, composition and archetype contract, andreferences/motion.mdbefore setting any reveal or preset. - Verify:
npm run qa, and fix everything it reports. - Export if asked —
references/export.md:npm run pdf,npm run record/record:2k/record:4k, thennpm run audit. When the deck backs a recorded voiceover, time the reveals from the caption file: a sidecartimings/<video>.jsonper video, validated withnode tools/record.mjs --timing <file> --plan. Timings never go in the markup — the deck only gains adata-slidehandle per timed slide. - Report the files, how to open them, the controls, the template used, every assumption, and sources for any researched claim or asset.
What ships with it
34 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.
- assets/core/morph.js 3.7 KB runs code
- assets/core/slides.css 32 KB
- assets/core/slides.js 8.3 KB runs code
- assets/optional/router.js 4.3 KB runs code
- assets/skeleton.html 16 KB
- assets/starter/gitignore 28 B
- assets/starter/package.json 539 B
- assets/starter/vite.config.js 667 B runs code
- assets/templates/bold-keynote/fonts.json 198 B
- assets/templates/bold-keynote/template.md 1.5 KB
- assets/templates/bold-keynote/theme.css 4.6 KB
- assets/templates/dark-marker/fonts.json 205 B
- assets/templates/dark-marker/template.md 1.7 KB
- assets/templates/dark-marker/theme.css 4.5 KB
- assets/templates/light-editorial/fonts.json 200 B
- assets/templates/light-editorial/template.md 1.6 KB
- assets/templates/light-editorial/theme.css 3.7 KB
- assets/templates/midnight-tech/fonts.json 316 B
- assets/templates/midnight-tech/template.md 1.7 KB
- assets/templates/midnight-tech/theme.css 4.7 KB
- assets/templates/minimal-mono/fonts.json 106 B
- assets/templates/minimal-mono/template.md 1.6 KB
- assets/templates/minimal-mono/theme.css 4.9 KB
- assets/tools/audit-video.mjs 7.8 KB runs code
- assets/tools/export-pdf.mjs 1.7 KB runs code
- assets/tools/fonts.mjs 4.8 KB runs code
- assets/tools/qa.mjs 6.6 KB runs code
- assets/tools/record.mjs 28 KB runs code
- references/design.md 5.5 KB
- references/export.md 8.2 KB
- references/motion.md 7.9 KB
- references/templates.md 5.1 KB
- references/web-slides.md 9.5 KB
- scripts/slides-runtime.test.mjs 10.0 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.
- 3d ago First seen · 132 lines · 158 tokens per session scan A 15f15a841241
create-slides is a skill published in the GitHub repository maxedapps/agent-skills (58 stars, last pushed 19d ago), licensed MIT. It adds 158 tokens to every session and 1,855 once invoked, about $0.0008 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…