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 DougTrajano/pydantic-ai-skills --skill data-analysisgit clone --depth 1 https://github.com/DougTrajano/pydantic-ai-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/dougtrajano/pydantic-ai-skills/data-analysis)<a href="https://agentmods.dev/skills/dougtrajano/pydantic-ai-skills/data-analysis"><img src="https://agentmods.dev/badge/skills/dougtrajano/pydantic-ai-skills/data-analysis/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/dougtrajano/pydantic-ai-skills/data-analysis"><img src="https://agentmods.dev/badge/skills/dougtrajano/pydantic-ai-skills/data-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00051 | $0.00666 |
| Opus 5 | $0.00026 | $0.00333 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
data-analysis 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Analysis Skill
Answers questions about a bundled sales dataset (resources/sales.csv): 96 rows
covering six months, four regions, four product categories and three sales
channels.
This is the reference skill for exercising sandbox executors. Both scripts are standard library only and read their data from the skill folder, so they do real work with no network, no third-party packages and no host access — exactly the shape a sandbox is meant to run.
When to Use This Skill
- "Which region had the highest revenue?" →
aggregate - "What were average units sold per category?" →
aggregate - "How many rows are in the dataset and what does revenue look like?" →
profile_dataset - "Compare online versus retail sales in the north" →
aggregatewith filters
Skill Scripts
profile_dataset
Reports dataset shape, column names, summary statistics for every numeric column (count, sum, mean, median, stdev, min, max) and distinct-value counts for the categorical ones.
column(optional): Profile a single numeric column instead of all of them
Exits 2 for an unknown column.
aggregate
Groups rows and aggregates a numeric column, optionally filtered and truncated.
group-by(required): Column to group by —month,region,category,channelmetric(optional): Numeric column to aggregate, defaultrevenueagg(optional):sum(default),mean,median,min,max,countwhere(optional, repeatable): Filter ascolumn=value, e.g.region=northtop(optional): Keep only the highest N groups
Exits 2 for an unknown column or malformed filter, 1 when no rows match.
Usage Examples
Revenue by region, highest first:
- group-by: region
Top 3 categories by units sold, online only:
- group-by: category
- metric: units
- agg: sum
- where: channel=online
- top: 3
Average revenue per month in the west:
- group-by: month
- agg: mean
- where: region=west
Data Source
resources/sales.csv is generated sample data, included so the skill is
self-contained and deterministic. It is not real sales data.
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 · 81 lines · 51 tokens per session scan A af20a8bdb33b
data-analysis is a skill published in the GitHub repository DougTrajano/pydantic-ai-skills (369 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 666 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 2026-08-30.
Other skills, from other repositories
document-processor
Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.
attendance-signin-sheet
A spreadsheet generator for printable attendance or meeting sign-in sheets. It turns a list of names into rows with columns such as signatures, dates, departments, or employee IDs.
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or…
research-brief
Turn sourced web findings into a concise PDF brief and an auditable XLSX evidence table.
business-data-structuring
Inspect messy CSV/XLSX tables and create a reviewed clean business dataset with normalized headers, types, dates and amounts. Use for preparing a table; do not operate CRM entities or turn the preparation step into business analysis.
data-loader
Load data from files (Excel, JSON, CSV) into databases. Use when user needs to import data files into any database system. Database-agnostic - supports SQL Server, PostgreSQL, MySQL, SQLite, and others.