ScienceClaw is an agent system for scientific work that completes tasks as typed, executable workflows and turns replay-verified improvements into reusable skills and operators. It is intended for AI-assisted research across natural and social science disciplines. The catalogue entries are its skills and instruction for use with the system.
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 beita6969/ScienceClaw --skill nltk-linguisticsgit clone --depth 1 https://github.com/beita6969/ScienceClawWrote 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/beita6969/scienceclaw/nltk-linguistics)<a href="https://agentmods.dev/skills/beita6969/scienceclaw/nltk-linguistics"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/nltk-linguistics/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/beita6969/scienceclaw/nltk-linguistics"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/nltk-linguistics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.00831 |
| Opus 5.5 | $0.00018 | $0.00332 |
| Sonnet 5.5 | $0.00009 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
nltk-linguistics 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NLTK Linguistics
Natural language processing and corpus analysis using NLTK.
Setup
import nltk
for pkg in ['punkt_tab', 'averaged_perceptron_tagger_eng', 'maxent_ne_chunker_tab',
'words', 'vader_lexicon', 'wordnet', 'stopwords']:
nltk.download(pkg, quiet=True)
Tokenization
from nltk.tokenize import word_tokenize, sent_tokenize
sentences = sent_tokenize(text)
words = word_tokenize(text)
POS Tagging
from nltk import pos_tag
from nltk.tokenize import word_tokenize
tagged = pos_tag(word_tokenize(text)) # list of (word, tag) tuples
# Tags: NN=noun, VB=verb, JJ=adjective, RB=adverb, DT=determiner
Named Entity Recognition
from nltk import ne_chunk, pos_tag, word_tokenize
tree = ne_chunk(pos_tag(word_tokenize(text)))
for subtree in tree:
if hasattr(subtree, 'label'):
entity = " ".join(word for word, tag in subtree.leaves())
print(f"{subtree.label()}: {entity}")
Sentiment Analysis (VADER)
from nltk.sentiment.vader import SentimentIntensityAnalyzer
sia = SentimentIntensityAnalyzer()
scores = sia.polarity_scores(text)
# Returns: {'neg': 0.0, 'neu': 0.5, 'pos': 0.5, 'compound': 0.6369}
# compound: -1 (most negative) to +1 (most positive)
Frequency Distributions and Concordance
from nltk import FreqDist, Text
from nltk.tokenize import word_tokenize
fdist = FreqDist(word_tokenize(text.lower()))
fdist.most_common(20) # top 20 words
t = Text(word_tokenize(text))
t.concordance('language', width=80) # keyword-in-context
t.collocations() # frequent bigrams
WordNet Lookups
from nltk.corpus import wordnet as wn
synsets = wn.synsets('bank') # all senses
defn = synsets[0].definition() # definition string
sim = wn.synset('dog.n.01').wup_similarity(wn.synset('cat.n.01')) # Wu-Palmer similarity
synonyms = [l.name() for s in wn.synsets('good') for l in s.lemmas()]
hypernyms = wn.synset('dog.n.01').hypernyms()
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 · 97 lines · 46 tokens per session scan A 7d503c4820e0
nltk-linguistics is a skill published in the GitHub repository beita6969/ScienceClaw (1,019 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 831 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
structure-prediction
Protein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…
running-openmed-ondevice
Run OpenMed models fully on-device with the MLX (Apple Silicon), CoreML (iOS/macOS), or ONNX/WebGPU (cross-platform/browser) backends, including convert-quantize-run workflows. Use when the user wants to deploy OpenMed at the edge, run NER/de-id on Apple Silicon, target iPhone/iPad/Mac, export to ONNX or WebGPU…