data-clean

A reproducible process that turns original datasets into a ready-to-analyze dataset. It records joins, exclusions, recoding, derived variables, and row counts in an R script while leaving the original files unchanged.

In plain words
What is it for?
Use it to clean, merge, recode, filter, and transform raw data into an analytic file for research analysis.
Why use it?
It makes data preparation traceable and repeatable, reducing hidden manual edits and helping detect unexpected changes in the data.

Skill for Claude CodeCodex

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/data-clean
Any agent
npx skills add matthewdigiuseppe/MStack --skill data-clean
Clone the repo
git clone --depth 1 https://github.com/matthewdigiuseppe/MStack

Made for: Claude Code, Codex.

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,004 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.

ModelPer sessionOnce invoked
Fable 5 $0.00073 $0.01004
Opus 5 $0.00036 $0.00502
Sonnet 5 $0.00015 $0.00201
Haiku 4.5 $0.00007 $0.00100

Measured 2d ago against content hash 111f5e25e401, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-clean 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 2d 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/data-clean/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mstack:data-clean

Stage: build Voice: data-engineer (anchored to r-coding-skills)

When to invoke

After /mstack:data-acquire has populated data/raw/ and the provenance log. Run before any analysis. Re-run when the analytic dataset changes.

Procedure

  1. Read the provenance log at data/raw/PROVENANCE.md (or whatever /mstack:data-acquire wrote). If missing, stop and tell the user to run /mstack:data-acquire first — undocumented raw data is not cleanable.

  2. Apply R conventions. Use the r-coding-skills skill if the user has it installed; otherwise follow ${CLAUDE_PLUGIN_ROOT}/references/r-conventions.md. Either way: tidyverse style, here::here() paths, snake_case, no setwd(), package versioning notes.

  3. Plan the pipeline. Before writing code, list (in chat) the cleaning steps:

    • Reads (which raw files).
    • Joins (key, type, expected row count).
    • Recodes (variable, mapping).
    • Drops (rule, expected row count, justification).
    • Derived variables (formula).
    • Final analytic unit (e.g., country-year, individual-wave).
    • Output file(s).

    Get user confirmation on the plan before writing code. If .mstack/learnings.jsonl already specifies conventions (variable names, exclusions), apply them automatically and note which.

  4. Write code/01-clean.R. Conventions:

    • Header comment block: purpose, inputs, outputs, run order.
    • library() calls grouped at top.
    • Each step in its own block, preceded by a one-line comment.
    • Every drop and join logged with nrow() before/after and a stop-if-unexpected check (e.g., stopifnot(nrow(df) == expected)).
    • Save final dataset(s) to data/clean/ as .rds (preferred) plus a .csv mirror for portability.
    • Save a session-info dump to data/clean/session-info.txt for replication.
  5. Run the script with Rscript code/01-clean.R. Capture stdout/stderr. If it errors, fix and re-run; do not declare done with errors outstanding.

  6. Sanity checks on the cleaned dataset:

    • Row counts match the plan.
    • No fully-missing columns.
    • Key variables in expected ranges.
    • Unit of analysis is unique (stopifnot(!anyDuplicated(df[, key_cols]))).
    • Print a summary() and a head/tail snapshot to a log file at data/clean/clean-log.md.

Read the full file on GitHub · 77 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.

  1. 2d ago First seen · 77 lines · 73 tokens per session scan A 111f5e25e401

Subscribe to this mod's changes

data-clean is a skill published in the GitHub repository matthewdigiuseppe/MStack (14 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 1,004 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

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