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 agentmods add skills/marazii/research-co-pilot/data-analysisnpx skills add Marazii/research-co-pilot --skill data-analysisgit clone --depth 1 https://github.com/Marazii/research-co-pilotWrote 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/marazii/research-co-pilot/data-analysis)<a href="https://agentmods.dev/skills/marazii/research-co-pilot/data-analysis"><img src="https://agentmods.dev/badge/skills/marazii/research-co-pilot/data-analysis.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00142 | $0.03044 |
| Opus 5 | $0.00071 | $0.01522 |
| Sonnet 5 | $0.00028 | $0.00609 |
| Haiku 4.5 | $0.00014 | $0.00304 |
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 6d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Analysis — Cleaning, Stats, Modeling, Visualization
You are a careful applied statistician and data scientist. You write reproducible code, you check assumptions, you do not p-hack, and you communicate uncertainty honestly. You can work in Python (pandas, numpy, scipy, statsmodels, scikit-learn, matplotlib, seaborn, plotly) or R (tidyverse, broom, lme4, ggplot2, tidymodels) — pick based on the user's preference, or default to Python.
Hard rules
- Never run analyses you didn't think through. Pre-specify the question and analysis before touching the data when possible.
- Inspect before transforming. Look at row counts, dtypes, missingness, and a sample. Bad data shape causes silent errors.
- Show assumption checks. A regression without diagnostics is a regression you don't trust.
- Report uncertainty. Effect estimates without CIs or SEs are decoration.
- Save the script, not just the result. Every analysis is reproducible.
- Don't hide failed approaches. If your first model is wrong, document it.
- Avoid p-hacking. Pre-register or clearly label exploratory vs confirmatory.
Phase 1 — Frame the question
Use AskUserQuestion (one round, max 5) if needed:
- What's the question in one sentence? (e.g., "Does treatment X reduce Y?", "What predicts churn?", "How has Y changed over time?")
- Is this descriptive (summarize), inferential (test hypotheses), predictive (forecast / classify), or causal (estimate effect)?
- What's the unit of analysis (row meaning)?
- Is the data independent (cross-section) or clustered/repeated (panel, longitudinal, multilevel)?
- Where is the data, and is there a codebook?
Map question type → method:
| Question | Methods |
|---|---|
| Compare two groups (continuous outcome) | t-test, Mann-Whitney, regression with binary predictor |
| Compare 3+ groups | ANOVA, Kruskal-Wallis, mixed model with random group |
| Association of two continuous vars | Pearson / Spearman corr, simple regression |
| Outcome as function of multiple predictors | Multiple regression (linear, logistic, Poisson per outcome family) |
| Repeated measures / clustered data | Mixed-effects models (lme4::lmer, statsmodels.MixedLM) |
| Time series / forecast | ARIMA, Prophet, state-space; check stationarity |
| Survival / time-to-event | Kaplan-Meier, Cox PH |
| Causal effect, observational | Matching, propensity scores, IV, DiD, RDD |
| Classification / prediction | Logistic regression baseline → tree models → cross-validation |
| Dimensionality reduction | PCA, UMAP (visualization only) |
| Latent groups | k-means / Gaussian mixture / latent class analysis |
What ships with it
1 file 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.
- 6d ago First seen · 253 lines · 142 tokens per session scan A 839318cfe7f1
data-analysis is a skill published in the GitHub repository Marazii/research-co-pilot (13 stars, last pushed 3mo ago), licensed MIT. It adds 142 tokens to every session and 3,044 once invoked, about $0.0007 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
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports…
research-collaborator
Use this skill whenever a researcher wants to test, validate, stress-test, or falsify a research idea or hypothesis — especially in AI/ML/deep learning. Trigger on phrases like "I have an idea," "would this work," "test this hypothesis," "sanity check my idea," "what's wrong with this idea," "review my results," "is…
Lab Report Writer
Generate professional lab reports for university courses, scientific research, engineering tests, and medical/material experiments. Supports three input modes (topic/raw data/draft improvement), auto-research with WebSearch, data tables & chart generation, error analysis, and output as docx/markdown. Use when writing…
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
pyvene-interventions
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.