Machine Learning Claude Skills
1 780 machine learning skills from 282 authors. They train and fine-tune models, build embeddings, run RAG and measure quality. Half of them fit into 2 252 tokens or less — that is what one costs your context window when the agent loads it. 424 ship runnable scripts rather than instructions alone. 10 of them cannot work without an MCP server, most often rube. We also found 397 copies of these same skills sitting in other people's repositories — counted once here, not 397 times.
1 780 unique 282 authors 5 updated this month 189 from vendors
>- Evaluate urban designs against comprehensive criteria drawn from all major global standards, certification systems, and theoretical frameworks. Generates detailed scorecards and improvement recommendations. Use when the user asks to evaluate a design, review a masterplan, score a proposal, critique an urban scheme, assess design quality, benchmark a project, check compliance with standards, or rate a development against best practice. Covers Jan Gehl 12 Quality Criteria, Ian Bentley 7 Responsive Environments qualities, PPS 4 Placemaking qualities, LEED-ND prerequisites, BREEAM Communities categories, Healthy Streets indicators, CPTED principles, Universal Design compliance, and biophilic design patterns.
>- Estimate construction costs, infrastructure costs, soft costs, and total development costs for urban design projects. Covers building construction cost per m2 by typology, infrastructure cost per linear meter and per dwelling, site preparation, landscaping, professional fees, and financial feasibility analysis. Use when the user asks about project cost, construction cost, infrastructure budget, development feasibility, cost per unit, cost per m2, capital expenditure, opex, cost benchmarking, value engineering, phasing costs, or any question about how much an urban design project or its components will cost. Also use for preliminary budget estimation, order-of- magnitude costing, cost comparison between design alternatives, or cost optimization of masterplans.
Chainlink Confidential AI Attester: submit private documents to an LLM inside an AWS Nitro Enclave and get back a cryptographically attested result — raw documents never leave the TEE. Use for these hackathon scenarios: (1) undercollateralized DeFi lending — upload a bank statement, get an attested approved/denied JSON decision without exposing financials on-chain; (2) accredited investor verification — check SEC Rule 501 qualification from brokerage statements privately; (3) KYC/AML screening — analyse ID docs and transaction history inside a TEE, return a pass/fail with flags; (4) proof of reserves — verify custodian balance reports against claimed reserves; (5) any use case where an AI must read sensitive user documents and the result needs a cryptographic proof of what model ran on what data. Trigger on: private inference, attested AI, TEE inference, confidential AI, or undercollateralized lending / KYC / accredited investor mentioned alongside document analysis.
Use for BetterTogether, prompt plus weight optimization, fine-tuning sequences, and strategy chains like p -> w -> p.
Use for DSPy retrieval with dspy.Embedder, dspy.Embeddings, FAISS indexes, semantic search, and local or hosted embedding models.
Use for BootstrapFinetune, fine-tuning DSPy models, teacher-student distillation, weight optimization, and lower-cost deployment.
Use for RAG pipelines, retrieval augmented generation, ColBERTv2, context retrieval, multi-hop RAG, and grounded DSPy answers.
Configure ASE MACE calculator adapter settings for ASE workflows. Use when ASE workflow tasks require MACE backend setup including model path/version, device/precision, stress availability, and inference controls.
> A command-line utility for converting and manipulating over 50 atomic simulation data formats, including outputs from DFT and MD software (VASP, LAMMPS, Gaussian, QE, CP2K, ABACUS, etc.). USE WHEN you need to convert structural or trajectory files between different computational chemistry formats, or when parsing raw simulation outputs into structured training datasets (e.g., deepmd/raw, deepmd/npy, deepmd/hdf5) for DeePMD-kit.
Prepare, explain, validate, and run DP-GEN simplify workflows for reducing repeated or redundant DeepMD datasets. Use when the user wants to generate or modify `param.json` and `machine.json`, run `dpgen simplify param.json machine.json`, organize repeated simplify experiments, or inspect simplify outputs.
Run Python inference with DeePMD-kit models using the DeepPot API. Use when the user wants to load a trained/frozen DeePMD model (.pth or .pb) or a built-in pretrained model (e.g., DPA-3.2-5M) in Python, predict energy/force/virial for atomic configurations, evaluate descriptors, or calculate model deviation between multiple models. Also covers using `dp test` CLI for batch evaluation against labeled data.
Train DeePMD-kit models with progressive disclosure. Use when the user wants to train a DeePMD-kit potential, prepare an input.json, choose between model families such as se_e2_a/DeepPot-SE and DPA3, run `dp train`, monitor learning curves, freeze checkpoints, or test trained models. Start with model selection and read only the selected model reference under `models/` when model-specific configuration is needed.
Fine-tune a DPA3 model in DeePMD-kit using the PyTorch backend. Use when the user wants to adapt a pre-trained DPA3 model to a new downstream dataset. Supports fine-tuning from a self-trained DPA3 model (.pt checkpoint), from a multi-task pre-trained model, or from a built-in pretrained model downloaded via `dp pretrained download` (e.g., DPA-3.1-3M, DPA-3.2-5M, DPA-3.3-1M). Covers single-task and multi-task fine-tuning workflows.
> A standardized CLI wrapper for RDKit 3D/2D conformer generation that samples multiple conformers per molecule (ETKDGv3, default 10), optimizes each with a force field (MMFF94s/UFF), keeps the lowest-energy conformer, automatically falls back to 2D layout on total embedding failure with a printed warning, and writes results to SDF or XYZ format. USE WHEN you need to generate 3D (or 2D fallback) molecular geometries from SMILES datasets (.csv/.smi) for downstream tasks such as docking, visualization, or 3D-descriptor computation.
> A standardized CLI wrapper for Uni-Mol molecular ML workflows that handles representation extraction (embeddings), model training (regression/classification), and property prediction with built-in RDKit SMILES validation. USE WHEN you need to generate molecular embeddings, train machine learning models for chemical properties, or run predictions on SMILES datasets (.csv/.smi) using the Uni-Mol framework.
| Trigger this skill when the user works on AI Product Manager — LLM application / generative AI / agent product 的产品经理实战 problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「AI 产品经理」「AI PM」「LLM 产品」「Generative AI product」「RAG 产品」
| 触发词：「K12 体育培训」「青少年体育培训」「少儿体适能」「中考体育」「体育中考」
| Trigger this skill when the user works on LLM agent infra problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「agent framework」「LLM agent」「agent infra」「multi-agent orchestration」「agent runtime」
| 触发词：「personal trainer」「personal training」「健身私教」「私教」「私人教练」
Guide for Vercel AI SDK v5 implementation patterns including generateText, streamText, useChat hook, tool calling, embeddings, and MCP integration. Use when implementing AI chat interfaces, streaming responses, tool/function calling, text embeddings, or working with convertToModelMessages and toUIMessageStreamResponse. Activates for AI SDK integration, useChat hook usage, message streaming, or tool calling tasks.
Use this skill to synthesize closed-form, automatically verifiable benchmark Q/A by exploring a tool environment, building a reusable exploration graph, and mining multiple hard questions from that graph. Use for: building a benchmark, writing eval items, generating evaluation data, closed-form QA, verifiable-answer datasets, synthesising eval data. Applies to any domain with callable tools. Do not use for open-ended writing, subjective scoring, or pure labeling.
>
Apply Vipassana meditation principles to LLM processing — equanimous scanning, non-reactive observation, impermanence awareness (anicca), and breaking the sankhara chain of conditioned reactions. Trigger on "meditate on", "observe without reacting", "see clearly", "practice vipassana", "scan equanimously", "what's really going on here", "non-reactive analysis", "observe without judgment". Also trigger when the user wants bare attention rather than jumping to conclusions, wants to dissolve fixation loops, or asks Claude to apply contemplative processing. Apply proactively when conversations show reactive thinking, craving for particular outcomes, or aversion to uncomfortable truths. Synergizes with cognitive-variability, embodied-navigation, and shifting-perspective skills.
Debug AI agents and LLM applications via Langfuse MCP. Use when investigating traces, exceptions, slow generations, sessions, prompt versions, datasets, or evaluation sets. Triggers on "langfuse", "traces", "debug AI", "find exceptions", "what went wrong", "why is it slow", "datasets", "evaluation sets".
Use this skill when the user wants to build AI applications with Weaviate. It contains a high-level index of architectural patterns, 'one-shot' blueprints, and best practices for common use cases. Currently, it includes references for building a Query Agent Chatbot, Data Explorer, Multimodal PDF RAG (Document Search), Basic RAG, Advanced RAG, Basic Agent, Agentic RAG, and optional guidance on how to build a frontend for each of them.
Search, query, and manage Weaviate vector database collections. Use for semantic search, hybrid search, keyword search, natural language queries with AI-generated answers, collection management, data exploration, filtered fetching, data imports from PDF/CSV/JSON/JSONL files, create example data and collection creation.
Use Neo4j GenAI Plugin ai.text.* functions and procedures for in-Cypher embedding generation, text completion, structured output, chat, tokenization, and batch ingestion. Covers ai.text.embed(), ai.text.embedBatch(), ai.text.completion(), ai.text.structuredCompletion(), ai.text.aggregateCompletion(), ai.text.chat(), ai.text.tokenCount(), ai.text.chunkByTokenLimit(), and provider configuration for OpenAI, Azure OpenAI, VertexAI, and Amazon Bedrock. Requires CYPHER 25. Replaces deprecated genai.vector.encode(). Use when writing pure-Cypher GraphRAG, embedding nodes in-graph, generating structured maps from prompts, or calling LLMs inside Cypher queries. Does NOT handle neo4j-graphrag Python library pipelines — use neo4j-graphrag-skill. Does NOT handle vector index creation/search — use neo4j-vector-index-skill.
Create and manage Neo4j vector indexes, run vector similarity search (ANN/kNN), store embeddings on nodes or relationships, use SEARCH clause (Neo4j 2026.01+, preferred) or db.index.vector.queryNodes() procedure (deprecated 2026.04, still works on 2025.x), configure HNSW and quantization options, pick similarity function and embedding provider dimensions, and batch-update embeddings. Use when tasks involve CREATE VECTOR INDEX, vector.dimensions, cosine/euclidean search, embedding ingestion pipelines, semantic or structural nearest-neighbor lookup, or hybrid search (vector + fulltext, multiple vector sources, or graph-derived scores). Does NOT handle GraphRAG retrieval_query graph traversal — use neo4j-graphrag-skill. Does NOT handle fulltext-only/keyword-only search — use neo4j-cypher-skill. Does NOT compute GDS graph embeddings (FastRP, Node2Vec) — use neo4j-gds-skill.
> Find insurance payments, total annual premiums, and compare to benchmarks.
Behavioral guardrails to reduce common LLM coding mistakes with a caution-first approach.
> Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".
> Audits any domain's AI-readiness by using curl to directly probe robots.txt, llms.txt, and llms-full.txt, then scores each file against a structured checklist and delivers a formatted report with pass/warn/fail findings and actionable fixes. Use this skill whenever a user provides a domain or URL and wants to know if llms.txt or llms-full.txt is available, discoverable, or properly structured. Trigger on phrases like "check llms.txt for", "does this site have llms.txt", "find llms.txt", "check llms for this url", "audit llms.txt", "is llms-full.txt available", or any time a user shares a domain/docs URL and wants AI-readiness checked. Also trigger when the user wants to verify GEO/AEO readiness of a documentation site.
> Audits any domain's AI-readiness by using curl to directly probe robots.txt, llms.txt, and llms-full.txt, then scores each file against a structured checklist and delivers a formatted report with pass/warn/fail findings and actionable fixes. Use this skill whenever a user provides a domain or URL and wants to know if llms.txt or llms-full.txt is available, discoverable, or properly structured. Trigger on phrases like "check llms.txt for", "does this site have llms.txt", "find llms.txt", "check llms for this url", "audit llms.txt", "is llms-full.txt available", or any time a user shares a domain/docs URL and wants AI-readiness checked. Also trigger when the user wants to verify GEO/AEO readiness of a documentation site.
Redis LangCache guidance for semantic caching of LLM responses on Redis Cloud — calling search/set via the SDK or REST API, tuning the similarity threshold, separating caches per task type, and filtering with custom attributes. Use when caching LLM completions or RAG answers to cut API cost and latency, building a cache-aside layer in front of OpenAI / Anthropic / etc., tuning hit rate vs precision, or splitting one app's LLM workloads into multiple LangCache caches.
Interactive copilot that offloads grunt work to a cheaper engine while Claude orchestrates. Greets each session with your live token limits and a driving mode (auto-pilot / you-drive / hybrid), auto-conserves when your Claude window runs hot, and picks models by live benchmarks. Triggers: outsource, offload, delegate, conserve tokens, use GLM/Devin/Codex, or get a second opinion.
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, and streaming row updates. Designed to work alongside HF MCP server for comprehensive dataset workflows.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. Triggers on: 'create a skill', 'new skill', 'make a skill for', 'improve this skill', 'test this skill', 'skill eval', 'optimize skill description', or /hk-skill-creator.
Load when a task needs current library, framework, SDK, API, CLI, or cloud-service documentation; fetch docs instead of relying on training data or ordinary repo evidence.
Analyze datasets and turn them into narrative reports with charts, audits, comparisons, and statistical summaries. Use for exploratory analysis and executive-ready outputs.
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).