nlp skills

78 tagged nlp, measured the same way as everything else here.

Browse within: RAG 19generative-ai 18graph-rag 18information-retrieval 18Orchestration 12agent-framework 12llm-framework 12monorepo 12tools 12japanese 8awesome 7natural-language-processing 6academic-writing 5japanese-language 5

huggingface/transformers

Skill Claude CodeCodex

Fixes broken typing checks detected by ty, make typing, or make check-repo. Use when typing errors appear in local runs, CI, or PR logs.

165k 2d ago A 41 tokens original Apache-2.0

compromise-nlp

02

spencermountain/compromise

Skill Claude CodeCodex

Write correct code with the compromise JavaScript NLP library (the npm package compromise, imported as nlp). Use this whenever you are writing or editing JS/TS that imports compromise, calls nlp(...), or chains methods like .match(), .tag(), .people(), .verbs(), .nouns(), .numbers(), .normalize(), or .replace() — and…

12k 9d ago A 172 tokens original MIT

find-new-resources

03

taishi-i/awesome-japanese-nlp-resources

Skill Claude CodeCodex

Find Japanese NLP GitHub repositories and Hugging Face models/datasets that are NOT yet in awesome-japanese-nlp-resources. Suggests candidates to add for a given topic using WebSearch + WebFetch, then outputs contribution-ready markdown.

1.0k 8d ago B 48 tokens original CC0-1.0

research-issues

04

taishi-i/awesome-japanese-nlp-resources

Skill Claude CodeCodex

Investigate current challenges, limitations, and proposed solutions in Japanese NLP for a topic. Surveys the existing awesome-japanese-nlp-resources dataset to see what already exists, then web-researches known problems and ongoing efforts to produce a digestible issue report.

1.0k 8d ago B 52 tokens original CC0-1.0

similar-resources

05

taishi-i/awesome-japanese-nlp-resources

Skill Claude CodeCodex

Given a Japanese NLP GitHub repo or Hugging Face model/dataset (URL / owner/repo / tool name), find repositories or models/datasets that do the same or related processing. Mines the bundled dataset for content-similar items, then expands via web research across both GitHub and Hugging Face, then merges and re-ranks.

1.0k 8d ago B 70 tokens original CC0-1.0

ai-compass

06

tingaicompass/AI-Compass

Skill Claude CodeCodex

Search and answer questions from the local AI-Compass AI knowledge base. Use when the user asks about AI models, tools, agents, RAG, multimodal systems, evaluation, learning paths, project resources, or recent AI developments covered by this repository; distinguish weekly updates from long-term topic knowledge…

926 5d ago A 75 tokens

natural-japanese

07

coji/natural-japanese

Skill Claude CodeCodex

A Japanese-language writing guide for clear business documents, such as meeting notes, reports, manuals, proposals, emails, and slide outlines. It includes checks intended to reduce unnatural or machine-like writing.

523 16d ago A 603 tokens original MIT

decision

08

bibinprathap/VeritasGraph

Skill Claude CodeCodex

Full decision lifecycle in VeritasReason � record, query, find precedents (hybrid/advanced), analyze influence, explain, insights dashboard, list, and record exceptions. Uses AgentContext, ContextGraph, DecisionQuery, CausalChainAnalyzer, DecisionRecorder.

313 2d ago A 55 tokens

embed

09

bibinprathap/VeritasGraph

Skill Claude CodeCodex

Generate, inspect, and use node/text embeddings in VeritasReason — compute Node2Vec embeddings, find similar nodes, score link predictions, batch similarity, and pairwise similarity. Uses NodeEmbedder, SimilarityCalculator, LinkPredictor, and AgentContext. Sub-commands: compute, similar, similarity, predict-link…

313 2d ago A 0 tokens

visualize

10

bibinprathap/VeritasGraph

Skill Claude CodeCodex

Visualize the VeritasReason knowledge graph — topology, centrality, communities, paths, embeddings, decision insights, and temporal evolution. Uses GraphAnalyzer, CentralityCalculator, CommunityDetector, PathFinder, and ContextGraph analytics. Sub-commands: topology, centrality, community, path, decision-graph…

313 2d ago A 0 tokens

humanizer-ru

11

smixs/humanizer-ru

Skill Claude CodeCodex

A Russian-text editor that removes bureaucratic wording, filler, copied chatbot patterns and signs of AI writing while keeping facts and examples.

143 2d ago A 263 tokens original MIT

humanizer-ru

12

Vladimir-Human/humanizer-ru

Skill Claude CodeCodex

A Russian-language editing tool that checks text for signs it was generated by a machine and can rewrite it in a more natural style when asked.

120 +2 2d ago A 164 tokens original MIT

swarmauri/swarmauri-sdk

Skill Claude CodeCodex

Add an experimental standalone Swarmauri package under pkgs/experimental. Use when Codex needs experimental package scaffolding, planning-stage metadata, optional workspace membership, README branding, entry points when discoverable, registry decisions, tests, and validation.

103 20d ago A 60 tokens original Apache-2.0

swarmauri/swarmauri-sdk

Skill Claude CodeCodex

Add a Swarmauri plugin package under pkgs/plugins. Use when Codex needs plugin package scaffolding, swarmauri.plugins or explicit resource entry points, third-class citizenship when appropriate, README branding, pyproject metadata, tests, and validation.

103 20d ago A 58 tokens original Apache-2.0

swarmauri/swarmauri-sdk

Skill Claude CodeCodex

Add a first-class standalone Swarmauri package under pkgs/standards. Use when Codex needs package scaffolding, workspace membership, pyproject metadata, Swarmauri or Tigrbl branding, entry points, first-class citizenship registry rows, exports, tests, and validation.

103 20d ago A 69 tokens original Apache-2.0

salsi

16

pooooooriya/salsi

Skill Claude CodeCodex

Write Persian with Persian words. Use when writing, editing, translating or reviewing Persian (Farsi) prose — articles, documentation, posts, essays, UI copy — to replace loanwords with Persian equivalents while leaving technical terminology, proper nouns and code untouched. Also use when the user asks for پارسی سره…

69 19d ago C 84 tokens

humanize-mba-text

17

stephenlzc/humanize-mba-text-skill

Skill Claude CodeCodex

A Chinese-language rewriting tool for making AI-generated text sound more natural in the style of a Chinese MBA thesis. It focuses on practical, evidence-based, academically structured writing.

40 1mo ago A 108 tokens original MIT

legal-advisor

19

Lethe044/hermes-legal

Skill Claude CodeCodex

You are Hermes Legal Advisor — an autonomous contract analysis agent. You read contracts so humans do not have to worry they missed something important. You are not a lawyer. You are an extremely thorough reader who knows what to look for, remembers every contract you have ever analyzed, and gets sharper with every…

22 5mo ago A 0 tokens original MIT

en-zh-max

20

3060226349kk-cmd/en-zh-max

Skill Claude CodeCodex

Use when the user wants 英译中 / 英译汉 / English to Chinese / translate to Chinese, or to polish translationese out of a Chinese draft. Also when producing 英中对照 bilingual output. Not for Chinese-to-English, pure Chinese writing polish, or single-word lookups.

21 1mo ago A 64 tokens original MIT

finnish-humanizer

21

Hakku/finnish-humanizer

Skill Claude CodeCodex

Tunnistaa ja poistaa AI-generoidun suomenkielisen tekstin tunnusmerkit. Tekee tekstistä luonnollisempaa ja ihmisen kirjoittaman kuuloista. Käytä pyyntöihin humanisoimaan tai "tee paremmaksi".

19 4mo ago A 63 tokens original MIT

untell

22

ssamba1/untell

Skill Claude CodeCodex

Audit an AI detector and measure what its verdict is worth, using a closed-loop detector-feedback rewrite as the instrument (the "untell" skill). Use when the user wants to check whether text reads as AI-generated, find out why a detector flagged something, measure a detector's false-positive rate on human writing…

19 10d ago A 135 tokens original MIT

decompose-mcp

23

echology-io/decompose

Skill Claude CodeCodex

Decompose any text into classified semantic units — authority, risk, attention, entities. No LLM. Deterministic.

10 3mo ago A 30 tokens original MIT

kkarpushin/tone-of-voice

Skill Claude CodeCodex

Reverse-engineers an author's Tone of Voice from their texts into a reusable voice profile. Metrics-grounded 8-level linguistic analysis: voice attributes, scales, lexical code, syntactic DNA, Do/Don't, per-context and per-language adaptation, blind validation test. Works on posts, articles, speech transcripts…

5 7d ago A 127 tokens original MIT