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 agentscope-ai/QwenPaw-Data --skill data-science-analysisgit clone --depth 1 https://github.com/agentscope-ai/QwenPaw-DataWrote 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/agentscope-ai/qwenpaw-data/data-science-analysis)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw-data/data-science-analysis"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/data-science-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/agentscope-ai/qwenpaw-data/data-science-analysis"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw-data/data-science-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 | $0.00237 | $0.02884 |
| Opus 5 | $0.00118 | $0.01442 |
| Sonnet 5 | $0.00047 | $0.00577 |
| Haiku 4.5 | $0.00024 | $0.00288 |
Grade A, and why
data-science-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 9d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Science Analysis
A single, domain-agnostic workflow for answering quantitative questions from local datasets. Data files may live in any directory the task provides (e.g., input/, data/, the current working directory, or an explicit path in the prompt); first identify that data directory, then apply the workflow to it. The steps below apply to any domain (archeology, biomedical, environmental, legal, wildfire, astronomy/heliophysics/space weather, and beyond) and to any file type (tabular CSV/Excel or scientific array/binary formats like .npz, .fits, .h5). Domain-specific gotchas are flagged inline and detailed in references/domain-notes.md.
Core Principles
| Principle | Why |
|---|---|
| Python for all arithmetic | Prevents LLM math errors |
| Read files directly in scripts | Never hardcode numbers from manual inspection—they drift and break |
| Consult the data dictionary first | Map every prompt term to exact columns/categories; never guess |
| Single consolidated script | For multi-step analysis, avoid many small .py files and inline python3 -c |
| Print intermediate results | Catches silent filtering/join errors before they reach the answer |
| Recompute derived metrics from raw | Never trust pre-calculated rates/percentages in source files |
| Round only at the final step | Intermediate rounding compounds error |
Workflow
1. Discover & Profile
- Identify the data directory the task provides (e.g.,
input/,data/, the current working directory, or an explicit path given in the prompt), then glob all files under it (e.g.,<data_dir>/**/*) — data files, data dictionaries, metadata, format specs (.fmt,.text,README), helper scripts. Avoid overly restrictive filename filters that might exclude the correct data. Restrict data access to this directory. - Read data dictionaries / README / format specs first. Map every prompt term (e.g., "damaged", "generally unsafe", "tumor") to its exact column or category — never guess. Cross-reference discovered schemas against format specs to confirm column mappings and units.
- Inspect raw structure before loading: read the first (and last) 10–20 rows raw (
header=None) to locate the true header row, metadata/summary/footer rows, delimiters, timestamp formats, and encoding quirks (BOM →utf-8-sig). - For Excel, list
sheet_namesviapandas.ExcelFile; prioritize README/Legend/Metadata sheets, then preview each data sheet. - For scientific/binary files (
.npz,.fits,.h5), print all keys and array shapes to identify the correct arrays before use. - Print exact column names and sample values; use names—not indices—for all downstream selection.
What ships with it
5 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.
- 9d ago First seen · 139 lines · 237 tokens per session scan A f26de8995e15
data-science-analysis is a skill published in the GitHub repository agentscope-ai/QwenPaw-Data (67 stars, last pushed yesterday), licensed Apache-2.0. It adds 237 tokens to every session and 2,884 once invoked, about $0.0012 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
neo4j-knowledge-graph
Use when designing, importing, querying, or modernizing Neo4j knowledge graphs from CSV, Excel, pandas, Cypher, py2neo, the official neo4j Python driver, vector indexes, or GraphRAG workflows.
docutranslate
Use when translating documents locally via LLM — PDF, Word, Excel, Markdown, SRT subtitles with format preservation. DocuTranslate: LLM-powered multi-format local file translation tool with MCP server support.
active-directory-attacks
Provide comprehensive techniques for attacking Microsoft Active Directory environments. Covers reconnaissance, credential harvesting, Kerberos attacks, lateral movement, privilege escalation, and doma.
accelerate
Run PyTorch training across GPUs with minimal changes.
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…