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 skills add robustagile/six-sigma-in-r-skill --skill six-sigma-rgit clone --depth 1 https://github.com/robustagile/six-sigma-in-r-skillWrote 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/robustagile/six-sigma-in-r-skill/six-sigma-r)<a href="https://agentmods.dev/skills/robustagile/six-sigma-in-r-skill/six-sigma-r"><img src="https://agentmods.dev/badge/skills/robustagile/six-sigma-in-r-skill/six-sigma-r/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/robustagile/six-sigma-in-r-skill/six-sigma-r"><img src="https://agentmods.dev/badge/skills/robustagile/six-sigma-in-r-skill/six-sigma-r.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00339 | $0.01921 |
| Opus 5.5 | $0.00136 | $0.00768 |
| Sonnet 5.5 | $0.00068 | $0.00384 |
| Haiku 4.5 | $0.00034 | $0.00192 |
Grade A, and why
six-sigma-r 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 1mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Six Sigma in R
Produce correct, runnable R code for Six Sigma and statistical-process-control problems. The skill is organized by task, not by statistical method — a user rarely asks for "a chi-square test", they ask "is my defect rate different from the target?". Map the request to the right technique, then emit code.
Before writing code: confirm two choices
Different users want different output shapes. Before producing code, ask the user once per session (skip if the request already makes it obvious, or if the user has answered previously):
- Script or function?
- Script: a self-contained, top-to-bottom
.Rfile with the user's data (or a clearly marked placeholder) baked in. Run-it-and-see. - Function: a reusable
my_cpk(x, lsl, usl)-style definition the user can drop into their project and call on arbitrary data.
- Script: a self-contained, top-to-bottom
- Plot output: file or inline?
- File: wrap plot calls in
png(filename="...")/dev.off()— good for scripts run from the terminal. - Inline: no device wrapper — plot renders in the user's RStudio / Quarto / notebook session.
- File: wrap plot calls in
If the user phrases the request as "write me a function that…", default to function + inline and don't ask. If they say "a script to analyze this CSV", default to script + file. Ask only when ambiguous.
Plotting: base R by default
Use base R graphics (plot, barplot, boxplot, hist, pie, abline, lines, points, segments) as the default. Base R covers every chart this skill produces — including horizontal bars (barplot(..., horiz=TRUE)), stacked bars (pass a matrix), and Pareto overlays. Base R has no external dependency and keeps scripts short.
Use ggplot2 only when the user explicitly asks for it, when they mention tidyverse / ggplot, or when a visualization genuinely benefits (e.g. grouped scatter with color aesthetics). When you do use ggplot2, load it explicitly with library(ggplot2) at the top.
Map: what the user wants → which reference to read
The references below contain the working code templates. Read the one that matches the task before emitting code — don't guess formulas from memory, especially for control-chart limits and capability indices, where the constants matter.
What ships with it
12 files 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.
- references/anova.md 3.6 KB
- references/capability_sigma_level.md 4.2 KB
- references/charts_visualization.md 5.5 KB
- references/control_charts.md 6.9 KB
- references/correlation_regression.md 3.2 KB
- references/descriptive_stats.md 1.8 KB
- references/distributions.md 2.4 KB
- references/hypothesis_tests.md 5.2 KB
- references/method_by_data_shape.md 6.9 KB
- references/method_by_dmaic.md 7.0 KB
- references/method_by_problem.md 5.7 KB
- references/sample_size_power.md 3.4 KB
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.
- 1mo ago First seen · 72 lines · 339 tokens per session scan A 14d6406dfcbe
six-sigma-r is a skill published in the GitHub repository robustagile/six-sigma-in-r-skill (12 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 339 tokens to every session and 1,921 once invoked, about $0.0014 per session on Opus 5.5. 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
add-yardstick-metric
Guide for creating new yardstick metrics. Use when a developer needs to extend yardstick with a custom performance metric, including numeric, class, probability, ordered probability, survival (static, dynamic, integrated, linear predictor), and quantile metrics.
neuropixels-analysis
Analyzes Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when…
onekgpd
Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which…
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
statistical-analysis
Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required…
biopython
Provides Biopython workflows for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Supports batch processing, custom molecular-biology pipelines, BLAST automation, structure analysis, and motif analysis.