An analysis workflow for running specified statistical models in R and producing publication-ready regression tables. A regression estimates relationships between variables while accounting for selected controls or fixed effects.

Use it to run the main models, estimate results, apply fixed effects and clustered standard errors, and render regression tables.

It keeps the analysis tied to the project specification or preregistration and requires key modelling choices to be confirmed first.

analyze — Skill by matthewdigiuseppe

Install

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.

agentmods

npx agentmods add skills/matthewdigiuseppe/mstack/analyze

Any agent

npx skills add matthewdigiuseppe/MStack --skill analyze

Clone the repo

git clone --depth 1 https://github.com/matthewdigiuseppe/MStack

Made for: Claude Code, Codex.

Or install mstack, the plugin that ships this one along with the rest of its 38 skills, 1 hook.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,131 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00067	$0.01131
Opus 5	$0.00034	$0.00566
Sonnet 5	$0.00013	$0.00226
Haiku 4.5	$0.00007	$0.00113

Measured 3d ago against content hash 0a17f56f8112, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze 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 3d 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.

skills/analyze/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mstack:analyze

Stage: analyze Voice: analyst (anchored to r-coding-skills)

When to invoke

After /mstack:data-clean produces a stable analytic dataset and /mstack:codebook has flagged any data issues. If the project is preregistered, the primary spec is in prereg/osf-prereg.md — this skill executes it.

Procedure

Load context.
- .mstack/config.yaml for primary spec (the one-line description).
- prereg/osf-prereg.md if it exists — the primary analysis section is the contract.
- .mstack/identification-review-*.md for the identifying assumption.
- .mstack/learnings.jsonl for variable names and conventions.
- data/clean/analytic.rds and data/codebook.md.
Confirm the spec with the user before writing code:
- Outcome variable, treatment / IV, controls.
- Fixed effects (which dimensions, why).
- SE clustering (which level, justified by the dependence structure).
- Sample restrictions (must match prereg if preregistered).
- Software / package (default: fixest::feols for OLS / FE; marginaleffects for AMEs; modelsummary for tables).
Apply R conventions — the r-coding-skills skill if the user has it installed, otherwise ${CLAUDE_PLUGIN_ROOT}/references/r-conventions.md.
Write code/02-analyze.R.
- Header: purpose, inputs, outputs, run order, link to prereg if applicable.
- Load the cleaned dataset; do not re-clean.
- Fit the primary model first and store it as m_primary.
- Fit any pre-specified secondary models, named m_<descriptor>.
- Save model objects to output/models/ as .rds for reuse by 03-figures.R and 04-tables.R.
- Print a one-line summary of each model to a log file at output/analyze-log.md.
Write code/04-tables.R to render output/tables/:
- Table 1 — descriptive statistics for the analytic sample.
- Table 2 — the primary specification (the table the paper is built around).
- Table 3+ — pre-specified secondaries.
- Use modelsummary::modelsummary() with output = "latex". Save .tex files; the manuscript \inputs them.
- Standard errors clustered as specified. Stars only if the journal demands them; default is coefficient + 95% CI.

Read the full file on GitHub · 82 lines

Changes

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.

3d ago First seen · 82 lines · 67 tokens per session scan A 0a17f56f8112

Subscribe to this mod's changes

analyze is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 6d ago), licensed MIT. It adds 67 tokens to every session and 1,131 once invoked, about $0.0003 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.

Analytics and metrics Scientific

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 tokens

overleaf-sync

Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…

wanshuiyin/Auto-claude-code-research-in-sleep · 97 tokens

mixed-precision

Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.

aiming-lab/AutoResearchClaw · 25 tokens