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 LeoLin990405/r-analytics-skill --skill stmgit clone --depth 1 https://github.com/LeoLin990405/r-analytics-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/leolin990405/r-analytics-skill/stm)<a href="https://agentmods.dev/skills/leolin990405/r-analytics-skill/stm"><img src="https://agentmods.dev/badge/skills/leolin990405/r-analytics-skill/stm/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/leolin990405/r-analytics-skill/stm"><img src="https://agentmods.dev/badge/skills/leolin990405/r-analytics-skill/stm.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 | $0.00021 | $0.01059 |
| Opus 5 | $0.00010 | $0.00530 |
| Sonnet 5 | $0.00004 | $0.00212 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade A, and why
stm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stm
Structural Topic Models with covariates.
Basic Usage
library(stm)
# Prepare documents
processed <- textProcessor(texts, metadata = df)
out <- prepDocuments(processed$documents, processed$vocab, processed$meta)
# Fit STM
model <- stm(
documents = out$documents,
vocab = out$vocab,
K = 10, # Number of topics
data = out$meta
)
With Covariates
# Topic prevalence varies by covariate
model <- stm(
documents = out$documents,
vocab = out$vocab,
K = 10,
prevalence = ~ party + s(year), # Topic prevalence formula
data = out$meta
)
# Topic content varies by covariate
model <- stm(
documents = out$documents,
vocab = out$vocab,
K = 10,
content = ~ party, # Topic content formula
data = out$meta
)
# Both
model <- stm(
documents = out$documents,
vocab = out$vocab,
K = 10,
prevalence = ~ party + s(year),
content = ~ party,
data = out$meta
)
Model Selection
# Search for optimal K
search_result <- searchK(
out$documents,
out$vocab,
K = c(5, 10, 15, 20),
data = out$meta,
prevalence = ~ party
)
# Plot diagnostics
plot(search_result)
Extract Results
# Top words per topic
labelTopics(model)
# FREX words (frequent and exclusive)
labelTopics(model, frexweight = 0.5)
# Topic proportions
model$theta
# Word-topic probabilities
model$beta
Visualization
# Topic quality
topicQuality(model, out$documents)
# Topic correlation
topicCorr(model)
plot(topicCorr(model))
# Word cloud
cloud(model, topic = 1)
# Topic prevalence
plot(model, type = "summary")
# Topic labels
plot(model, type = "labels")
# Perspectives (compare topics)
plot(model, type = "perspectives", topics = c(1, 2))
Covariate Effects
# Estimate effect of covariates
effect <- estimateEffect(
formula = 1:10 ~ party + s(year),
stmobj = model,
metadata = out$meta
)
# Plot effect
plot(effect, covariate = "party", topics = 1:5,
model = model, method = "difference",
cov.value1 = "Democrat", cov.value2 = "Republican")
# Continuous covariate
plot(effect, covariate = "year", topics = 1,
model = model, method = "continuous")
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.
- 9d ago First seen · 222 lines · 21 tokens per session scan A 9aeb73ab4eb0
stm is a skill published in the GitHub repository LeoLin990405/r-analytics-skill (5 stars, last pushed 6mo ago), licensed MIT. It adds 21 tokens to every session and 1,059 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
bio-applied-molecular-evolution
Test Hardy-Weinberg equilibrium, simulate Wright-Fisher drift/selection, and compute dN/dS, Tajima's D, and Fst with NumPy/SciPy. Use for neutral theory, molecular clock divergence time, selection scans, or effective population size (Ne) questions.
advanced-string-structures
Build tries, Aho-Corasick, and suffix arrays with Kasai LCP to index DNA/text and match many patterns in one pass. Use for genome motif scanning, k-mer indexing, longest-repeat search, or BWA/FM-index groundwork.
ai-science-esm2-embeddings
Generate ESM2 protein embeddings (fair-esm/transformers) and predict structure with ESMFold. Use when embedding sequences, scoring mutations zero-shot, annotating protein function, or doing fast MSA-free structure prediction.
ai-science-geneformer-scgpt
Tokenize scRNA-seq via Geneformer gene-rank or scGPT expression-bin encoding; annotate cell types, simulate in-silico knockouts. Use for foundation-model cell annotation, Geneformer/scGPT tokenization, or perturbation prediction.
ai-science-zero-shot-mutation
Score protein point mutations zero-shot with ESM-1v/ESM-2 masked-LM log-odds, ensembled, benchmarked on ProteinGym DMS. Use when predicting mutation effects, ranking missense variants, scoring VUS fitness with no labels.
bio-applied-advanced-ngs
Assemble genomes de novo: greedy OLC, de Bruijn graph/Eulerian path, N50/L50/NG50 stats, SPAdes/Flye/hifiasm CLI usage. Use when choosing k-mer size, picking an assembler for Illumina/ONT/HiFi reads, or scoring contiguity.