Skip to content
Skills Library
Data & analytics · Analysis

analysis

/analysis

Runs reproducible data analysis and visualization in Python. Use for plots, charts, statistics, numpy/pandas/matplotlib/scipy work.

Repository
r4 ↗
Licence
Apache-2.0
Last repository change
10.11.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 10.11.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Runs reproducible data analysis and visualization in Python. Use for plots, charts, statistics, numpy/pandas/matplotlib/scipy work.

Original author description

Runs reproducible data analysis and visualization in Python. Use for plots, charts, statistics, numpy/pandas/matplotlib/scipy work.

How it works

  1. Working pattern
  2. Platform specifics the model must not rediscover
  3. Quality bar
Original SKILL.md headings · 30 lines, 186 words
SKILL.md preview
---
name: analysis
description: "Runs reproducible data analysis and visualization in Python. Use for plots, charts, statistics, numpy/pandas/matplotlib/scipy work."
allowed-tools: "python_exec file_read file_write"
metadata:
  x-r4-keywords: "plot, graph, chart, analyse, analyze, visuali, dataframe, numpy, pandas, matplotlib, scipy, statistics"
---

You do data analysis with short, reproducible Python.

## Working pattern

1. Inspect the data first (file_read for small files; for large/remote lab
   data hand off to the data_management skill's catalog tools instead of
   guessing paths).
2. python_exec for interactive exploration; when the analysis must be
   repeatable, write the script with file_write and say how to re-run it.
3. Save artifacts to files (CSV for tables, PNG for figures) and report the
   exact paths. Never leave results only in stdout when the user asked for
   a deliverable.

## Platform specifics the model must not rediscover

- Headless environment: use `matplotlib.use("Agg")` before `pyplot` import;
  never call `plt.show()`. Save with `fig.savefig(path, dpi=150,
  bbox_inches="tight")`.
- numpy/pandas/matplotlib/scipy are available; do not pip-install inside
  the companion. If a package is missing, report it instead of installing.
- Long computations: keep single python_exec runs short; split stages into
  separate calls with intermediate files so failures are resumable.

## Quality bar

- Show the key numbers, not just the plot
- State assumptions (null handling, filters, units) in one line
- Prefer a small printed summary table plus one figure over many figures

Versions

RepositoryScoreLicence
This page · R-CCS-HPBD/r490Apache-2.0
oscarks/spectionflow100MIT
cloudfieldcz/cf-powers100MIT
matteocervelli/llms100MIT
clawic/skills90MIT

Database snapshot: 13.11.2026 · package version f223a6b9eb2a (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100data-analysis
    Data Analysis Specialist - Analyzing datasets, visualizations, extracting insights. [VAD] EDA, statistical analysis, SQL queries, data visualization. Python-based analysis with pandas, numpy, matplotlib, seaborn, plotly. [NÄR] Use when: data analysis, statistics, visualization,…
  • 100scipy-analysis
    Scientific computing and statistical analysis with SciPy, NumPy, and pandas. Use when: (1) statistical hypothesis testing, (2) optimization problems, (3) signal processing, (4) numerical integration, (5) data manipulation and analysis. NOT for: symbolic math (use sympy-math),…
  • 100matplotlib-viz
    Scientific visualization via Matplotlib. Use when: user asks for plots, charts, or data visualization. NOT for: interactive dashboards or web-based charts.
  • 100data-science-expert
    Expert-level data science, analytics, visualization, and statistical modeling. Use when the user mentions analytics, visualization, statistics, pandas, or NumPy, or when the task involves Data Analysis, Machine Learning, Data Visualization, or Feature Engineering.
  • 100setup
    Creates the plugin's own Python environment and installs or upgrades mixpanel_headless (0.4.0 or newer) with pandas, numpy, matplotlib, seaborn, networkx, anytree, scipy, and pyarrow (Python 3.11+ only) on Python 3.10+, then checks the imports, mp help, and the credentials. Use…
  • 100python-data
    Data wrangling in Python with pandas and numpy — loading, cleaning, joining, reshaping, aggregating, dates and time zones, memory and speed. Use when writing or reviewing pandas or numpy code, when a DataFrame total does not match its source, or when a notebook is slow or runs out of memory.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.