Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bestdeejay-design/agent-skillsnpx agentmods add skills/bestdeejay-design/agent-skills/presentation-craftWrote 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/bestdeejay-design/agent-skills/presentation-craft)<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/presentation-craft"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/presentation-craft/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/bestdeejay-design/agent-skills/presentation-craft"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/presentation-craft.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 | $0.00106 | $0.02589 |
| Opus 5.5 | $0.00042 | $0.01036 |
| Sonnet 5.5 | $0.00021 | $0.00518 |
| Haiku 4.5 | $0.00011 | $0.00259 |
Grade A, and why
presentation-craft 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
presentation-craft
Router, не генератор. Он не рисует слайды сам — он ведёт многоэтапный сценарий и на каждом этапе подключает нужный скилл (загрузкой его SKILL.md). Это прямой перенос проверенного паттерна «тонкий entry -> quality -> reviewer» (majiayu000/claude-skill-registry) и полного цикла guizang-ppt-skill на наш каталог.
Внешние базы, на которых выстроен роутер: op7418/guizang-ppt-skill (полный цикл 0->7, заблокированные темы, Node-валидаторы); Mathews-Tom/armory skills/marp-slides (ленивая подгрузка references, роутинг); majiayu000/claude-skill-registry (marp-authoring + marp-slide-quality + marp-slide-reviewer); anthropics/skills skills/pptx (fidelity-экспорт, validate.py, Visual QA); wanshuiyin/.../slides-polish (постраничный ревьюер против reference-визуала, версионирование).
Когда использовать
- Нужна презентация, которая не выглядит «шаблонной AI»: есть смысл, стиль, корректный UI/UX и проверка.
- Триггеры: «качественная презентация», «сделай стильную презентацию», «презентация с дизайн-системой», «не шаблонные слайды», «presentation craft».
Когда НЕ использовать
- Быстрый одностраничный набросок — бери сразу
presentation-maker. - Только верстка HTML-страницы —
frontend-perfection.
Канонический пайплайн (6 этапов)
Порядок и гейты — консенсус из anthropics/skills (pptx, frontend-design, theme-factory), guizang-ppt-skill, armory/marp-slides, majiayu000 trio, wanshuiyin/slides-polish.
Этап 0 — Intake (кларификация)
Сними неопределённость ДО генерации (guizang «7 вопросов» / armory «один запрос + дефолты»):
- Аудитория, цель (pitch / отчёт / обучение / имидж);
- Длительность -> число слайдов (~1 слайд/мин; для 10-мин доклада ≈ 8–12);
- Материалы (сайт, бриф, тексты) — если есть лендинг, сними контент через
web-scraper; - Стиль/бренд (если задан) или вольная на Этапе 2. Не переходи дальше без аудитории + цели + объёма.
Этап 1 — Narrative / смысл -> скилл docs-product + seo-content
docs-product: из материалов вытащи VISION/позиционирование/ценности -> структуру «зачем / что / доказательство» (дуга Hook -> Context -> Core -> Shift -> Takeaway).seo-content: читабельность (Flesch-KincoW), уберил воду, E-E-A-T.- Результат:
outline.md(форматpresentation-maker) с assertion-заголовками (полное предложение с глаголом + точка), одна идея/слайд, ≤6 буллетов. Гейт: заголовки — выводы, не темы; нет повторов; консистентность цифр между слайдами.
What ships with it
1 file 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.
- 1mo ago Changed · +8 lines 3b084c1be946
- 1mo ago First seen · 124 lines · 106 tokens per session scan A 5fa73d08899b
presentation-craft is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 2,589 once invoked, about $0.0004 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
form-filling
Fill out online forms (Google Forms, Typeform and similar) or PDF, Word and DocuSign forms; prepare a reviewable draft and get approval before submitting or sending.
xberg-extracting-tables
Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.
recipe-bulk-download-folder
List and download all files from a Google Drive folder.
xberg-extracting-with-ocr
Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning.
docx2pdf
A tool that converts Microsoft Word documents from .docx format to PDF, either one file or an entire folder.
google-apps-script
Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…