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 xlsxgit 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/xlsx)<a href="https://agentmods.dev/skills/hkuds/deeptutor/xlsx"><img src="https://agentmods.dev/badge/skills/hkuds/deeptutor/xlsx/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/xlsx"><img src="https://agentmods.dev/badge/skills/hkuds/deeptutor/xlsx.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 | $0.00088 | $0.01997 |
| Opus 5.5 | $0.00035 | $0.00799 |
| Sonnet 5.5 | $0.00018 | $0.00399 |
| Haiku 4.5 | $0.00009 | $0.00200 |
Grade A, and why
xlsx 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.
recalculate through `exec` using `subprocess.run` and a How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excel (.xlsx) workbooks
Runtime
Use exec with complete Python source (language: python). Prefer creating,
saving, reopening, and validating the workbook in one call; later calls can
revise the same relative filename. Follow the turn's User workspace
instructions for locating inputs, output boundaries, and presenting the
finished file.
Use openpyxl for cells, formulas, styles, charts, merged cells, multi-sheet workbooks, number formats, and streaming large sheets. It is declared by every supported DeepTutor installation. Do not assume pandas is installed: it exists in the Docker runner but is not a direct dependency of every pip/source install.
THE critical gotcha: openpyxl writes formulas but never computes them
ws["B10"] = "=SUM(B2:B9)" stores the formula string. openpyxl has no formula
engine — the cached value stays empty (or stale, on an edited file). So:
- A workbook you create/edit with openpyxl opens fine in Excel/LibreOffice (they recompute on open), but its cached values are wrong until then.
- Anything reading cached values first —
data_only=True, another pandas/openpyxl pass, or a downstream tool — sees blanks/stale data.
Pick by what the deliverable needs:
- Static numbers (most common). If the user just needs correct values and
the sheet need not stay live, compute in Python and write the number, not
a formula string:
ws["B10"] = sum(c.value for c in ws["B2:B9"][0]). Correct immediately, no recalc needed. - Live model (formulas that recompute on the user's later edits). Write real
formulas, and reference cells not literals (
=B5*(1+$B$6), not=B5*1.05). openpyxl can't set the cached value too. Ifshutil.which("soffice")succeeds, recalculate throughexecusingsubprocess.runand a relative_recalc/directory, replaceout.xlsxwith the recalculated copy, then remove_recalc/. Never use/tmpor search for a desktop installation. A later exec call can see the same bare filename. If LibreOffice is absent, warn that formulas populate when the user opens the file in Excel.
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 · +1 lines 9f5e476f8692
- 1mo ago Changed · +20 lines c95194668210
- 1mo ago First seen · 191 lines · 88 tokens per session scan A 2edae4de61eb
xlsx is a skill published in the GitHub repository HKUDS/DeepTutor (41,899 stars, last pushed yesterday), licensed Apache-2.0. It adds 88 tokens to every session and 1,997 once invoked, about $0.0004 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
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-financial-model
Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value'…
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.
surfsense-documents
Make or change a Word document (.docx), a PDF, a PowerPoint deck (.pptx) or an Excel workbook (.xlsx) by writing a Python script that surfsenserenderdocument runs, optionally starting from a source's own Word or PowerPoint file. Load it whenever the user asks for one of these, or for a change to one you made.
surfsense-data
Work out numbers from spreadsheet and CSV sources (.xlsx, .csv, .tsv) by writing a pandas script that surfsenseanalyzedata runs: totals, averages, trends, rankings, comparisons, cleaning, and charts that can go into a document. Load it whenever the user asks for figures from a table, or a chart of one.
potpie-resource-spreadsheet
Use when the user asks to ingest a spreadsheet or CSV (cost report, inventory, tracker, export) into Potpie so agents can search and cite it. Teaches the extraction-script flow: one section per sheet, header-repeated row chunks, potpie resource import, summaries that carry the key figures, and — critically — deriving…