Machine Learning Skills

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).

このスキルを使用して、パフォーマンスベースラインを測定し、PR前後の回帰を検出し、スタック代替案を比較します。

LLM APIの使用量のコスト最適化パターン — タスクの複雑さによるモデルルーティング、予算追跡、リトライロジック、プロンプトキャッシング。

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.

日本語翻訳：このファイルは pytorch-patterns 用の日本語翻訳が必要です

作为代理工程师，采用评估优先执行、分解和成本感知模型路由进行操作。

Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

创建和更新宣传文稿、一页简介、投资者备忘录、加速器申请、财务模型和融资材料。当用户需要面向投资者的文件、预测、资金用途表、里程碑计划或必须在多个融资资产中保持内部一致性的材料时使用。

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.

Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm. Use this skill whenever the user is building any system that picks "the top K items for a (user, context)" — social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking.

批量查看和切换子 agent 的模型配置，用于统一调整多 agent 的 provider/model 设置。

添加和配置第三方 API 中转站供应商到 OpenClaw。当用户需要添加新的 API 供应商、配置中转站、设置自定义模型端点时使用此技能。支持 Anthropic 兼容和 OpenAI 兼容的 API 格式。

Semantic Similarity Index for disease research literature using PubMedBERT embeddings

Smart LLM router — save 67% on inference costs. Routes every request to the cheapest capable model across 41 models from OpenAI, Anthropic, Google, DeepSeek, and xAI.

Design irresistible offer packages with real salary benchmarks, negotiation playbooks, and competitive counter-strategies. Co-designed with Siku (司库). Includes total compensation calculator, negotiation scripts, and BATNA analysis.

Legal contract analysis using CUAD dataset (41 risk categories). Supports NDA, SaaS, M&A, employment, payment/merchant, and finder/broker agreements. Identifies red flags, suggests redlines, compares to market standards.

Audit OpenClaw token usage, purge stale sessions, and optimize inference speed. Use when the user sends /optimize, /audit, asks to purge sessions, or wants a token/workspace audit.

生成 Agent 与 Cron 的模型配置状态报告，展示主模型、fallback 链和任务分配情况。

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.

模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时，自动切换到备用模型，确保服务连续性。支持多供应商、多优先级的智能模型选择，提供健康监控、自动重试和错误恢复机制。

检查已配置模型供应商的连通性、延迟和可用性，用于快速诊断模型侧故障。

调度远程 Ollama GPU 资源执行批量 embedding 或推理任务，提升多机环境下的算力利用率。

TCM meridian inference engine — health scoring from 6-meridian measurements

蒸馏Aaron Ross思维模式的实用框架——预可售、销售分工模型、可预测收入

蒸馏查理·芒格《穷查理宝典》——多元思维模型、逆向思维、25种误判心理学、Lollapalooza效应、能力圈决策框架

蒸馏Dan Koe Human 3.0框架——四象限发展模型、三级意识进化、相位成长体系、超级人类90天计划

蒸馏 Charlie Munger（Berkshire Hathaway）思维模式的实用框架：多元思维模型、反向思考、lollapalooza效应