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 khalilbenaz/claude-skills-collection --skill nlp-pipeline-designergit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/nlp-pipeline-designer)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/nlp-pipeline-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/nlp-pipeline-designer/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/khalilbenaz/claude-skills-collection/nlp-pipeline-designer"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/nlp-pipeline-designer.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 | $0.00133 | $0.02525 |
| Opus 5 | $0.00067 | $0.01262 |
| Sonnet 5 | $0.00027 | $0.00505 |
| Haiku 4.5 | $0.00013 | $0.00252 |
Grade A, and why
nlp-pipeline-designer 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NLP Pipeline Designer
Guide opérationnel pour concevoir et implémenter des pipelines NLP production-ready, de la tokenization aux tâches avancées.
Étape 1 — Cadrer la tâche et choisir l'approche
Questions à trancher avant tout code :
| Critère | Approche légère | Approche Transformer |
|---|---|---|
| < 10 k exemples annotés | TF-IDF + sklearn | SetFit / few-shot |
| Latence < 50 ms | DistilBERT, FastText | Non |
| Corpus français | CamemBERT, FlauBERT | XLM-RoBERTa si multilingue |
| Généralisation zero-shot | Non | NLI (MNLI) ou GPT-4o |
| Tâche extractive simple | regex + spaCy rules | Rarement utile |
Tâches → modèles recommandés (2026) :
- Classification texte :
CamemBERT-base(FR),DeBERTa-v3-base(EN) - NER :
spaCy fr_core_news_lg(règles + statistique),bert-base-multilingual-casedfine-tuné - Sentiment :
nlptown/bert-base-multilingual-uncased-sentiment, ou zero-shotfacebook/bart-large-mnli - Summarization :
facebook/bart-large-cnn,moussaKam/barthez-orangesum-abstract(FR) - QA extractif :
deepset/camembert-base-squad2(FR)
Étape 2 — Prétraitement du corpus
import re, unicodedata
from langdetect import detect
def clean_text(text: str) -> str:
text = re.sub(r"<[^>]+>", " ", text) # strip HTML
text = unicodedata.normalize("NFC", text) # normalise unicode
text = re.sub(r"http\S+|www\.\S+", "[URL]", text) # masque URLs
text = re.sub(r"\s+", " ", text).strip()
return text
# Chunking pour textes longs (sliding window)
def chunk_text(text: str, max_tokens: int = 400, overlap: int = 50) -> list[str]:
words = text.split()
chunks = []
for i in range(0, len(words), max_tokens - overlap):
chunks.append(" ".join(words[i : i + max_tokens]))
return chunks
Points critiques :
- Ne pas supprimer les stopwords avant un Transformer (il les utilise pour le contexte).
- Conserver la casse pour la NER (majuscules = signal fort pour les entités).
- Annoter la langue avant tout pipeline multilingue :
detect(text)→ filtrer/router.
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 · 245 lines · 0 tokens per session scan A 0b9fc536a75f
nlp-pipeline-designer is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 18d ago), licensed MIT. It adds 133 tokens to every session and 2,525 once invoked, about $0.0007 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
saelens
Train sparse autoencoders to interpret model features.
nnsight-remote-interpretability
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
transformer-lens-interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
LQF_Machine_Learning_Expert_Guide
LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
scientific-data-preprocessing
⚠️ CRITICAL USER EXPERIENCE-BASED SKILL - ALWAYS CONSULT BEFORE DATA PREPROCESSING ⚠️ Prevents catastrophic errors (88.9% error rate in V1.0 case study) through multi-level feature analysis, data leakage detection, and semantic validation. MANDATORY for: data preprocessing, feature engineering, standardization…