← All skills
analyze-stats
80 / 100 · Low risk
Fine to try.
By Aperivue/medsci-skills (GitHub) · research · 379 stars · scanned at commit e0ea3b0
Use when data needs statistical analysis. Runs reproducible Python/R code for Table 1, diagnostic accuracy, agreement, regression, survival, propensity score, survey-weighted and repeated-measures models, with publication tables. Sample size is /calc-sample-size; pooling studies is /meta-analysis.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this.
Found in 13 places.
Show 10 more
- skills/analyze-stats/scripts/analysis_run_challenge/verify.sh, line 23
assert subprocess.run(audit, capture_output=True).returncode == 0 - skills/analyze-stats/scripts/analysis_run_challenge/verify.sh, line 29
check = subprocess.run(audit, capture_output=True, text=True) - skills/analyze-stats/tests/test_analysis_run.py, line 257
proc = subprocess.run([sys.executable, str(run.CODE["runner"]), "compare", - skills/analyze-stats/tests/test_analysis_run.py, line 296
proc = subprocess.run(base + ["run", "--project-root", str(self.root), "--data", "data.csv", - skills/analyze-stats/tests/test_analysis_run.py, line 301
proc = subprocess.run(base + ["audit", "--project-root", str(self.root), "--out", "runs/cli"], capture_output=True, text=True) - skills/analyze-stats/tests/test_analysis_run.py, line 314
proc = subprocess.run(command, capture_output=True, text=True) - skills/analyze-stats/tests/test_analysis_run.py, line 319
proc = subprocess.run(command, capture_output=True, text=True) - skills/analyze-stats/tests/test_generated_code.sh, line 131
bash -c "sed -n 78p '$REFS/test_selection.md' | grep -q \"Welch's t-test\*\* by default\"" - skills/analyze-stats/tests/test_generated_code.sh, line 133
bash -c "sed -n 142p '$REFS/propensity_score.md' | grep -q 'LogisticRegression. is L2-penalised by default (C = 1.0)'" - skills/analyze-stats/tests/test_stats_templates.sh, line 178
run = subprocess.run([sys.executable, f"{WORK}/dx.py"], capture_output=True, text=True)
Downloads and installs other software
The author does not mention this.
Found in 10 places.
Show 7 more
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'analyze-stats' ] || [ -L ~/.agents/skills/'analyze-stats' ]; then echo 'A skill folder named analyze-stats already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Aperivue/medsci-skills' "$d" && git -C "$d" checkout --quiet 'e0ea3b0be3bf529aa0b94ee5fd8450e78848932c' -- 'skills/analyze-stats' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/analyze-stats' ~/.agents/skills/'analyze-stats' && 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/'analyze-stats' ~/.claude/skills/'analyze-stats' (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 Aperivue/medsci-skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/Aperivue/medsci-skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-13 | e0ea3b0 | 80 |
| 2026-11-07 | cc462bc | 100 |