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 kinhluan/skills --skill slide-automationgit clone --depth 1 https://github.com/kinhluan/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/kinhluan/skills/slide-automation)<a href="https://agentmods.dev/skills/kinhluan/skills/slide-automation"><img src="https://agentmods.dev/badge/skills/kinhluan/skills/slide-automation/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/kinhluan/skills/slide-automation"><img src="https://agentmods.dev/badge/skills/kinhluan/skills/slide-automation.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 | $0.00059 | $0.05571 |
| Opus 5 | $0.00030 | $0.02786 |
| Sonnet 5 | $0.00012 | $0.01114 |
| Haiku 4.5 | $0.00006 | $0.00557 |
Grade A, and why
slide-automation 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 10d 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 — 750 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slide Automation
From markdown to deck — reproducible, version-controlled presentations.
This skill automates the creation of research presentations from structured content. It eliminates manual copy-pasting, ensures consistency, and makes slides version-controllable alongside your research.
"Your slides should be as reproducible as your experiments." — Researcher's Maxim
1. When to Automate Slides
Use Cases
| Scenario | Tool | Output |
|---|---|---|
| Paper → Conference talk | python-pptx | .pptx with figures auto-inserted |
| Thesis → Defense slides | LaTeX Beamer | .pdf with precise typography |
| Markdown → Quick deck | Marp | .html or .pdf from markdown |
| Web-based presentation | reveal.js | Interactive HTML slides |
| Recurring reports | python-pptx | Template-based monthly updates |
When NOT to Automate
- One-off, highly designed pitch deck → Use Keynote/PowerPoint manually
- Creative storytelling presentation → Manual design for emotional impact
- Rapid iteration with designer → Figma/Sketch collaboration
2. Tool Comparison
| Tool | Format | Best For | Learning Curve | Collaboration |
|---|---|---|---|---|
| python-pptx | .pptx | Data-heavy, figure-rich talks | Low | Git-friendly |
| LaTeX Beamer | Academic defense, math-heavy | Medium | Git-friendly | |
| Marp | .md → .pdf/.html | Quick markdown-based decks | Very low | Git-friendly |
| reveal.js | .html | Interactive web presentations | Low | Git-friendly |
| Quarto | .qmd → multiple | Reproducible research reports | Medium | Git-friendly |
3. python-pptx: PowerPoint from Python
3.1 Basic Structure
from pptx import Presentation
from pptx.util import Inches, Pt
from pptx.dml.color import RgbColor
from pptx.enum.text import PP_ALIGN, MSO_ANCHOR
# Create presentation
prs = Presentation()
prs.slide_width = Inches(13.333) # 16:9
prs.slide_height = Inches(7.5)
# Add title slide
blank_layout = prs.slide_layouts[6] # Blank layout
slide = prs.slides.add_slide(blank_layout)
# Add title
title_box = slide.shapes.add_textbox(Inches(1), Inches(2.5), Inches(11.333), Inches(1.5))
tf = title_box.text_frame
tf.text = "Federated Learning for Medical AI"
p = tf.paragraphs[0]
p.font.size = Pt(44)
p.font.bold = True
p.font.color.rgb = RgbColor(0x1a, 0x1a, 0x1a)
p.alignment = PP_ALIGN.CENTER
# Add subtitle
sub_box = slide.shapes.add_textbox(Inches(1), Inches(4.2), Inches(11.333), Inches(1))
tf = sub_box.text_frame
tf.text = "Privacy-Preserving Collaborative Training"
p = tf.paragraphs[0]
p.font.size = Pt(24)
p.font.color.rgb = RgbColor(0x66, 0x66, 0x66)
p.alignment = PP_ALIGN.CENTER
# Save
prs.save('presentation.pptx')
What ships with it
3 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.
- 10d ago First seen · 750 lines · 59 tokens per session scan A 2bab40b65ff1
slide-automation is a skill published in the GitHub repository kinhluan/skills (4 stars, last pushed 14d ago), licensed MIT. It adds 59 tokens to every session and 5,571 once invoked, about $0.0003 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
pdf-report
Generate a branded, audience-structured marketing report — executive summary, campaign report, channel deep-dive, competitor report, or monthly/quarterly review — assembled via pdf-generator.py with brand colors, logo, and fonts, and previewed for adjustments before finalizing. Pulls data from campaign-tracker.py…
domain-driven-design
DDD tactical patterns for complex business modeling including entities, value objects, aggregates, domain services, repositories, specifications, and bounded contexts. Python dataclass implementations with TypeScript alternatives. Use when building rich domain models, enforcing invariants, or separating domain logic…
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
documentation-patterns
Technical documentation patterns for READMEs, ADRs, API docs (OpenAPI 3.1), changelogs, and writing style guides. Use when creating project documentation, writing architecture decisions, documenting APIs, or maintaining changelogs.
report-deck
Turn Fullstory research findings into a presentation-ready report — slide structure, speaker notes, and export to PPTX or PDF. Use when the user asks for a deck, slides, presentation, or report from their analytics.
parse-calendar
Parse a monthly content calendar from DOCX, XLSX, Notion, or pasted text into structured calendar-data.json — the source of truth every downstream skill reads. Triggers on "/parse-calendar", "parse the calendar", "import this calendar", "here is the month", "load the content plan", "calendar to JSON", or whenever a…