DeepTutor is a personalized tutoring system that uses AI agents and learning resources to support ongoing, interactive study. Learners use it for activities such as reading, research, guided courses, and building mastery paths. The catalogue entries provide skills and instructions for working with DeepTutor.
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 HKUDS/DeepTutor --skill pptxgit clone --depth 1 https://github.com/HKUDS/DeepTutorWrote 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/hkuds/deeptutor/pptx)<a href="https://agentmods.dev/skills/hkuds/deeptutor/pptx"><img src="https://agentmods.dev/badge/skills/hkuds/deeptutor/pptx/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/hkuds/deeptutor/pptx"><img src="https://agentmods.dev/badge/skills/hkuds/deeptutor/pptx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00076 | $0.02814 |
| Opus 5.5 | $0.00030 | $0.01126 |
| Sonnet 5.5 | $0.00015 | $0.00563 |
| Haiku 4.5 | $0.00008 | $0.00281 |
Grade A, and why
pptx scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run([soffice, "--headless", "--convert-to", "pdf", str(deck)], check=True) How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pptx
Work with PowerPoint .pptx files using python-pptx (preinstalled). A .pptx
is a ZIP of XML parts; python-pptx handles the structure so you rarely touch XML.
Drop to raw OOXML only for the few things the library can't express (see Advanced).
Use exec with complete Python source (language: python). Keep asset creation,
deck generation, reopening, and structural verification in one call when
possible; later calls can revise the same relative filename. Follow the turn's
User workspace instructions for locating inputs, output boundaries, and
presenting the finished deck.
Mental model
- A presentation has slides; each slide is built from a layout; layouts
live on slide masters. Layouts define placeholders (title, body,
picture, etc.) by
idxand type. - A slide holds shapes: placeholders, text boxes, pictures, tables, charts.
- Shapes with text expose
.text_frame→.paragraphs→.runs. A run is the unit that carries formatting (font, size, bold, color). - Units are EMU. Use the helpers:
from pptx.util import Inches, Pt, Emu.
Read / extract
from pptx import Presentation
prs = Presentation("deck.pptx")
print(len(prs.slides), prs.slide_width, prs.slide_height) # EMU dims
for i, slide in enumerate(prs.slides, 1):
print(f"--- slide {i} (layout: {slide.slide_layout.name}) ---")
for shape in slide.shapes:
if shape.has_text_frame:
print(shape.text_frame.text) # \n-joined paragraphs
elif shape.has_table:
for row in shape.table.rows:
print([c.text for c in row.cells])
if slide.has_notes_slide:
notes = slide.notes_slide.notes_text_frame.text
if notes:
print("NOTES:", notes)
Iterate slide.placeholders to see placeholder idx / placeholder_format.type.
For a fast text-only dump, just collect shape.text_frame.text across slides.
Create from an outline
List the layouts first — indices vary by template. With the default template, layout 0 = Title, 1 = Title+Content, 5 = Title Only, 6 = Blank.
from pptx import Presentation
from pptx.util import Inches, Pt
prs = Presentation() # or Presentation("template.pptx") to inherit a theme
for idx, lay in enumerate(prs.slide_layouts):
print(idx, lay.name, [(p.placeholder_format.idx, p.name) for p in lay.placeholders])
# Title slide
s = prs.slides.add_slide(prs.slide_layouts[0])
s.shapes.title.text = "My Deck"
s.placeholders[1].text = "Subtitle" # idx from the listing above
# Title + bullets
s = prs.slides.add_slide(prs.slide_layouts[1])
s.shapes.title.text = "Agenda"
tf = s.placeholders[1].text_frame
tf.text = "First point" # first paragraph
for line, lvl in [("Second", 0), ("Sub-point", 1)]:
p = tf.add_paragraph()
p.text = line
p.level = lvl
prs.save("out.pptx")
Always set text via placeholders/shapes — never hand-write bullet glyphs (•);
indentation/bullets come from the layout via paragraph.level.
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 · +30 lines 72e6ecbc8b31
- 1mo ago First seen · 221 lines · 76 tokens per session scan A ee60d40ee6ff
pptx is a skill published in the GitHub repository HKUDS/DeepTutor (41,639 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 2,814 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
markitdown
Converts heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
ppt-master
AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable Brand/Style/Layout/Deck workspaces, filling native PPTX templates, and enhancing finished PPTX files. Use when the user asks to create, generate, reconstruct, regenerate, beautify, redesign…
morph-ppt
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style…
officecli-academic-paper
Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper'…
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
officecli
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.