← All skills
data-scientist
79 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a data skill usually connects to databases or online services with your credentials.
By magnus919/agent-skills (GitHub) · data · 172 stars · scanned at commit da4ce5c
Use for PhD-level expertise in data science, statistics, and machine learning: rigorous statistical analysis, experimental design, causal inference, advanced modeling, research methodology, or data science project leadership. Load when the user asks about statistical methods, experimental design, model selection, A/B testing, hypothesis testing, power analysis, regression, causality, Bayesian analysis, or research methodology. For insurance, actuarial, claims, reserving, solvency, credibility, …
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README.
Found in 19 places.
Show 16 more
- data-scientist/references/subagent-experiment-supervision.md, line 106
process = subprocess.Popen( - data-scientist/references/subagent-experiment-supervision.md, line 109
stderr=subprocess.STDOUT, - data-scientist/references/subagent-experiment-supervision.md, line 250
subprocess.run( - data-scientist/references/subagent-experiment-supervision.md, line 347
proc = subprocess.Popen(experiment_cmd, stdout=f, stderr=subprocess.STDOUT) - data-scientist/scripts/detect-compute.py, line 56
proc = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout) - data-scientist/scripts/detect-compute.py, line 60
except subprocess.TimeoutExpired: - data-scientist/scripts/detect-compute.py, line 117
"""Probe PyTorch availability and capabilities via subprocess.""" - data-scientist/scripts/test_campaign_protocol.sh, line 47
bash -c "grep -c '^## Phase' \"$REF\" | xargs test 8 -eq" - data-scientist/scripts/test_campaign_protocol.sh, line 55
bash -c "grep -c 'Entry criteria' \"$REF\" | xargs test 8 -eq" - data-scientist/scripts/test_campaign_protocol.sh, line 58
bash -c "grep -c 'Exit criteria' \"$REF\" | xargs test 8 -eq" - data-scientist/scripts/test_campaign_protocol.sh, line 61
bash -c "grep -c 'Failure modes' \"$REF\" | xargs test 8 -eq" - data-scientist/scripts/test_detect_compute.sh, line 144
r = subprocess.run([sys.executable, '/scripts/detect-compute.py', '--json'], capture_output=True, text=True) - data-scientist/scripts/test_detect_compute.sh, line 154
r = subprocess.run([sys.executable, '/scripts/detect-compute.py', '--json'], capture_output=True, text=True) - data-scientist/scripts/test_detect_compute.sh, line 163
r = subprocess.run([sys.executable, '/scripts/detect-compute.py', '--json'], capture_output=True, text=True) - data-scientist/scripts/test_detect_compute.sh, line 172
r = subprocess.run([sys.executable, '/scripts/detect-compute.py', '--json'], capture_output=True, text=True) - data-scientist/scripts/test_supervision_protocol.sh, line 57
bash -c "grep -c '| \*\*' \"$SUP\" || grep -c '^| \*\*' \"$SUP\" || grep -c 'OOM\|NaN\|ImportError\|Disk full\|cuDNN' \"$SUP\" | xargs test 7 -le"
Downloads and installs other software
The author does not mention this.
Found in 21 places.
Show 17 more
- data-scientist/references/data-science-coding-workflow.md, line 50
python -m pip install cookiecutter - data-scientist/references/data-science-coding-workflow.md, line 337
RUN pip install --no-cache-dir -r requirements.txt - data-scientist/references/docker-experiment-isolation.md, line 13
| Python dependency conflict | `pip install` breaks other projects | Isolated Python environment per container | - data-scientist/references/docker-experiment-isolation.md, line 27
RUN pip install --no-cache-dir \ - data-scientist/references/docker-experiment-isolation.md, line 278
pip install -r requirements.txt - data-scientist/references/docker-experiment-isolation.md, line 289
pip install -r requirements.txt - data-scientist/references/subagent-experiment-supervision.md, line 178
| **ImportError** | `ModuleNotFoundError: No module named 'X'` | `pip install X` and re-run | - data-scientist/scripts/Dockerfile, line 8
RUN pip install --quiet --no-cache-dir \ - data-scientist/scripts/assumption-diagnostics.py, line 32
print("Error: scipy and numpy required. pip install scipy numpy", file=sys.stderr) - data-scientist/scripts/assumption-diagnostics.py, line 303
print("Error: scipy + numpy required for data analysis. Install with: pip install scipy numpy", - data-scientist/scripts/assumption-diagnostics.py, line 310
print("Error: pandas required for CSV reading. pip install pandas", file=sys.stderr) - data-scientist/scripts/assumption-diagnostics.py, line 365
print("Error: statsmodels required for regression diagnostics. pip install statsmodels", - data-scientist/scripts/detect-compute.py, line 296
recs["notes"] = "Neither PyTorch nor scikit-learn detected. Install: pip install torch scikit-learn" - data-scientist/scripts/effect-size-calculator.py, line 54
print("Error: scipy required. pip install scipy numpy", file=sys.stderr) - data-scientist/scripts/model-comparison.py, line 71
print("Error: pandas and statsmodels required for --from-data. pip install pandas statsmodels", - data-scientist/scripts/power-analysis.py, line 37
print("Error: scipy and numpy are required. Install with: pip install scipy numpy", - data-scientist/scripts/test_detect_compute.sh, line 126
RUN pip install --quiet --no-cache-dir scikit-learn numpy psutil
and 1 more places
Connects to the internet
This is disclosed by the author in the skill's SKILL.md or README. Expected for a data skill.
Found in 2 places.
Safer alternatives
Low-risk skills in the same category (data) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'data-scientist' ] || [ -L ~/.agents/skills/'data-scientist' ]; then echo 'A skill folder named data-scientist already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/magnus919/agent-skills' "$d" && git -C "$d" checkout --quiet 'da4ce5c6823cce6da80f4e09c84998a4928402c1' -- 'data-scientist' && mkdir -p ~/.agents/skills && cp -R "$d"/'data-scientist' ~/.agents/skills/'data-scientist' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'data-scientist' ~/.claude/skills/'data-scientist' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for magnus919/agent-skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/magnus919/agent-skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-09 | da4ce5c | 79 |
| 2026-11-07 | 34a4d62 | 82 |