Engineering Advanced NLPTextML

NLP Engineer

Natural language processing: text classification, tokenization, retrieval, entity extraction, evaluation, and production NLP pipeline design.

An NLP engineering skill that frames language tasks around real business risk instead of immediately reaching for the largest model. It covers task definition, labeling, retrieval or extraction choices, evaluation by error bucket, and production monitoring for text systems.

Added Apr 12, 2026

$npx skills add johnefemer/skillfish --skill nlp-engineer

Capabilities Get Started Models & Context Works Great With

What This Skill Can Do

Concrete capabilities you get when you install this skill.

Frame NLP tasks and label taxonomies around business risk and error cost

Choose between rules, classical ML, embeddings, and transformer models

Build datasets, annotation guidance, and error-bucket evaluation loops

Design search, extraction, classification, and ranking pipelines

Tune thresholds for precision and recall tradeoffs and human review

Monitor drift, language variation, and production failure modes in text systems

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Claude Sonnet or GPT-4o recommended. Complex evaluation design and model-selection tradeoffs benefit from stronger models.

Context Window

SKILL.md is concise (~3KB). Fits in 32K context; dataset slices, label guides, and eval output together benefit from 64K+.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Works Great With

These skills complement NLP Engineer for end-to-end coverage. Install them together for better results.

AI Engineer

Build production AI applications: LLM integration, function calling, streaming, embedding pipelines, guardrails, cost optimization, and evaluation.

AILLM

LLM Architect

LLM system design: model selection, fine-tuning strategies, inference optimization, context window management, multi-model routing, and cost analysis.

LLMFine-tuning

Data Analyst

Data analysis workflows: pandas/SQL patterns, statistical analysis, visualization (matplotlib, plotly), dashboard design, A/B test analysis, and business metrics.

Data AnalysisPandas

Senior ML Engineer

ML model deployment, MLOps pipelines, LLM integration, and cost optimization.

MLMLOps

$ skillfish add johnefemer/skillfish --all # install all skills at once

Ready to try NLP Engineer?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.