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
| Security-first SOP for multi-tenant RAG systems. Activate when a calling agent is building, reviewing, or debugging any retrieval pipeline whose vector store is shared across more than one user, organisation, workspace, customer, or permission scope. Encodes the single non-negotiable rule — **filter at the vector store query, never after retrieval / never after rerank** — together with the per-vendor query-time filter APIs (Pinecone namespaces + `$eq`/`$in`, Weaviate `multiTenancyConfig` + tenant handle, Qdrant `is_tenant` payload index + `Filter.must`, Chroma `where`, pgvector RLS), and the cross-framework adapters (LlamaIndex `MetadataFilters`, LangChain `filter=` dict). Frame the work as preventing CVE-2024-41892 / EchoLeak / Slack-AI-class cross-tenant leakage, not as "adding a filter for relevance".
>- Decomposed, multi-criteria metric design for LLM pipelines. The metric IS the model — change the metric and the optimizer changes behavior. Decompose by default; bool during LLM-as-judge, llm as judge, eval metric, evaluation score, scoring function, rubric, RAGAS, G-Eval, judge bias, verbosity bias, how to evaluate LLM output.
>- Enhancement-overlay (C5) for RAG over long documents — the chunk-paradox resolution. Activate when a single fixed chunk size cannot satisfy both retrieval precision (small large chunks dilute embedding relevance into "topic averages". Encodes the core flip — large for synthesis context — and the SOP to pick a base chunk size, choose a horizontal (sentence-window) vs vertical (auto-merging / parent-child) expansion strategy, and measure the lift. Cross-links [[llamaindex]] for the full RAG SOP; this overlay supplies the missing "chunk-paradox-resolution" recipe that the framework docs (HierarchicalNodeParser, SentenceWindow) only describe in fragments. Medium-frequency for chunking strategy, parent document retriever, sentence window, small-to-big retrieval, hierarchical chunking, optimal chunk size.
>- Lifecycle SOP for **per-model prompt artifacts** — the compiled prompts, instructions, few-shot demos, edit-format pins, and embedding-bound indices that change behavior when the underlying LM, dataset, or framework version changes. Activate when adopting compiled prompts (DSPy, GEPA, BootstrapFewShot output), when supporting multiple LMs in production, when a provider deprecates a model snapshot, or when a framework deprecates a config surface (LlamaIndex `ServiceContext` → `Settings`, Aider edit-format defaults). Do NOT activate for one-off raw prompt edits or for truly model-agnostic system prompts that have deprecation, prompt per model, prompt breaks on new model, version compiled prompts.
>- Enhancement-overlay SOP for query-type routing — sending a query to the right index / tool / engine *before* retrieving, not after. Activate when a calling agent owns a retrieval or answering surface that fronts more than one handler (a summary index, a vector index, a vs "find the clause about X" vs "how many orders shipped in Q3". Encodes the one non- negotiable insight — **one retriever cannot serve all query types; route first, retrieve second** — plus the three router families (LLM/selector, embedding/semantic, keyword/rule), confidence-threshold + fallback discipline, and the cross-framework mapping (LlamaIndex `RouterQueryEngine` / `SelectorPromptTemplate`, Dify Question Classifier node, LangGraph conditional edges). This is an ENHANCE overlay over the per-framework skills — cross-link `[[llamaindex]]`, `[[agentsop-dify]]`, `[[agentsop-langgraph]]` for the deep
>- Enhancement-overlay SOP for the reranker stage of a RAG pipeline — the "retrieve wide, rerank narrow" discipline. Activate when a calling agent owns a retrieval pipeline whose the context window is under pressure from too many marginal chunks. Encodes the one non- negotiable insight — a cheap bi-encoder retrieves *wide* for recall, then a more expensive cross-encoder (which reads query + document *together*) reranks *narrow* for precision; keep top-N=20-50, rerank to top-k=3-5. Covers when to add a reranker (and when not to), N-vs-k tuning, model choice (Cohere/Voyage API vs bge-reranker local vs SentenceTransformer cross-encoder), latency/cost budgeting, and the cross-framework mapping (LlamaIndex node postprocessors, LangChain ContextualCompressionRetriever, Cohere/Voyage rerank APIs, local cross-encoders). This is an ENHANCE overlay over the per- framework skills — cross-link `[[llamaindex]]` and `[[agentsop-hybrid-retrieval]]` for the
>- Project-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API? Decide on two axes — VOLUME (a cost-crossover slider) and COMPLIANCE (a hard gate). Use at kickoff when choosing where to run inference, or when cost / data-residency pressure forces a re-evaluation.
Decision SOP for serving LLMs with vLLM. Covers PagedAttention mental model, quantization/parallelism/batching tradeoffs, OOM triage, and when NOT to use vLLM. Activates when a coder-agent is choosing or tuning an inference engine, debugging vLLM throughput/latency/OOM, or comparing vLLM against TGI/SGLang/TensorRT-LLM/llama.cpp.
获取 Hugging Face 上的模型、数据集和 Space 的统计信息
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.
A specialized skill for embedding and extracting resilient watermarks in text by manipulating sentence lengths and using Fountain Codes. Use this when the user wants to add a hidden, robust watermark to text or verify an existing one.
能力蒸馏工作流——从用户批准的强模型访谈或真实任务轨迹中提取非显然的判断规则，形成可审计的 judgment packet，再交给 skill-audit 和 skill-creator 决定是否落成可加载 skill。当用户说“蒸馏这个模型的判断力”“把这次任务的关键决策固化下来”“模型窗口要关了，保留它在某类场景的判断”时使用。普通流程文档、直接写 SKILL.md、泛化最佳实践或未授权的会话日志扫描不使用本 skill。
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update 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.
Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model fine-tuning (SFT/DPO/RFT). USE FOR: azd ai agent, azd provision/deploy, deploy agent, hosted agent, create agent, add tool to agent, invoke agent, evaluate agent, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, agent optimizer, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, AI Services, create Foundry resource, provision, knowledge index, customize deployment, onboard, availability, fine-tune, SFT, DPO, RFT, training-data, grader, distillation, fine-tuned model, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
Advanced AI agent benchmark scenarios that push Vercel's cutting-edge platform features — Workflow DevKit, AI Gateway, MCP, Chat SDK, Queues, Flags, Sandbox, and multi-agent orchestration. Designed to stress-test skill injection for complex, multi-system builds.
End-to-end benchmark suite for vercel-plugin. Runs realistic projects through skill injection, launches dev servers, verifies everything works, analyzes conversation logs, and produces an improvement report for overnight self-improvement loops.
Run vercel-plugin eval scenarios in Vercel Sandboxes instead of local WezTerm panels. Provisions ephemeral microVMs with Claude Code + plugin pre-installed, runs benchmark prompts, extracts hook artifacts, and produces coverage reports.
Create and launch benchmark test projects to exercise vercel-plugin skill injection across realistic scenarios. Sets up isolated directories, installs the plugin, and spawns WezTerm panes running Claude Code with crafted prompts.
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
Corrects outdated LLM knowledge about the Vercel platform and introduces new products. Injected at session start.
Patterns for invoking the Apify CLI (`apify`) from agents. Covers authentication, creating/running/pushing Actors, calling Actors in the cloud, and reading results from datasets and key-value stores.
Machine learning and LLM engineering judgment, distilled from a stronger model - invoke when DECIDING whether/how to use ML or an LLM for a task (prompt vs RAG vs fine-tune vs classical); working with training/eval data or labels; building or reviewing evals for models and LLM features; designing RAG, structured output, or agent pipelines; or diagnosing why a model/LLM feature underperforms. Method-selection ladder, data and leakage discipline, eval-as-spec rules, LLM-era craft, and a trap catalog.
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt injection, jailbreak defense, output filtering), RAG architecture (chunking, hybrid retrieval, rerank), and prompt engineering / evaluation (RAGAS, LLM-as-Judge). Use when building AI agents, designing RAG pipelines, orchestrating multi-agent workflows, hardening LLM apps, or writing prompts.
Use Databricks built-in AI Functions (ai_classify, ai_extract, ai_summarize, ai_mask, ai_translate, ai_fix_grammar, ai_gen, ai_analyze_sentiment, ai_similarity, ai_parse_document, ai_prep_search, ai_query, ai_forecast) to add AI capabilities directly to SQL and PySpark pipelines without managing model endpoints. Also covers document parsing and building custom RAG pipelines (parse → prep_search → index → query).
Train ML models on Databricks. Use for: classification/regression/deep-learning (XGBoost, scikit-learn, LightGBM, PyTorch) with Optuna, @prod/@challenger aliases, batch scoring (spark_udf for plain models, fe.score_batch for feature-store-backed), custom PyFunc, custom ResponsesAgent (LangGraph + UC Function/Vector Search); UC feature tables + FeatureLookup + point-in-time joins + Lakebase online store; declarative Feature Views (create_feature, DeltaTableSource, RollingWindow/SlidingWindow/TumblingWindow, materialize_features, streaming Kafka features). NOT for: endpoint ops (databricks-model-serving), MLflow evaluation (databricks-mlflow-evaluation).
Generate realistic synthetic data using Spark + Faker (strongly recommended). Supports serverless execution, multiple output formats (Parquet/JSON/CSV/Delta), and scales from thousands to millions of rows. For small datasets (<10K rows), can optionally generate locally and upload to volumes. Use when user mentions 'synthetic data', 'test data', 'generate data', 'demo dataset', 'Faker', or 'sample data'.
Build RAG / unstructured-document evaluation datasets and demo documents (e.g. for Knowledge Assistant) on Databricks: generate synthetic PDFs locally, upload to Unity Catalog volumes, and pair each document with test questions for retrieval evaluation.
Databricks Vector Search endpoints and indexes for RAG and semantic search; covers index types, search modes, end-to-end RAG patterns
Generates a comprehensive client health overview across all accounts. Reads CRM data, support tickets, usage metrics, billing, and engagement logs. Calculates health scores, trend direction, and RAG status per client. Outputs a sorted risk report with recommended actions.
Identifies upsell and cross-sell opportunities within existing customer accounts. Analyzes product usage, feature gaps, team growth, industry benchmarks, and competitive pressure to surface revenue expansion plays scored by potential, effort, and likelihood. Generates an expansion-playbook.md with account-by-account opportunities, recommended pitch, timing, and approach.
Multi-dimensional rep evaluation: activity, conversion, velocity, deal size. Peer benchmarking and coaching priority identification.
Implement proven sales methodologies (MEDDIC, BANT, Sandler, Challenger, SPIN) across your team. Generate framework-specific questions, score deals, train reps, and enforce consistent qualification. Use when implementing or optimizing sales processes.
Custom training plans by goal (strength, cardio, flexibility). Progressive overload programming, rest day optimization, home vs gym adaptations, deload weeks.
仅当用户显式调用 `$grill-me`，或明确要求“追问我”“挑战这个方案”“拷打这个设计”时使用。通过高强度逐问逐答检验方案或设计，并同步维护领域模型、术语表和 ADR。不要因普通设计讨论自动触发。
> Choose a model architecture for a medical-imaging research question before scaffolding. Maps the task (classification, segmentation, detection, transfer), modality and dimensionality, labelled-data scale, and class imbalance to a shortlist of architectures, each grounded in its source paper with a when-to-use, a medical-imaging use, a reference implementation, the typical validation setup, and the matching model-scaffold template. Covers the foundational curriculum (ResNet, DenseNet, EfficientNet, ViT, Swin; U-Net, 3-D U-Net, Attention/Residual U-Net, nnU-Net (+ ResEnc/MedNeXt/STU-Net), Mask R-CNN; SAM/MedSAM, nnInteractive/VISTA3D interactive-3D, TotalSegmentator, BiomedCLIP, DINO/MAE/SimCLR; and graph neural nets — GCN/GraphSAGE/GAT/GIN/BrainGNN — for brain connectomes). It teaches archetypes and the task-to-architecture logic (including the "scale the CNN, new≠better" rigour caveat), not a live SOTA leaderboard.
> Design and validity review for studies that benchmark one or more AI systems against a human-expert panel as the reference. Covers the evaluation question and arm definition, decoupled multi-dimensional rubrics with anchors, planted calibration probes, reviewer-panel construction, inter-rater reliability targets, LLM-as-judge versus human-as-judge adjudication, construct-independence guards, and a structured rating-export schema. Use before data collection on an AI-vs-expert evaluation.
> Produce or audit the interpretability/explainability analysis of a medical-imaging model — Grad-CAM / Grad-CAM++ / attention-rollout / saliency / integrated-gradients — so it clears the rigor quantitative localisation metric against ground truth (IoU / pointing game / Dice) instead of eyeballed examples, a cohort-level result rather than cherry-picked cases, and attribution framing rather than "proof the model is correct". Emits an explainability-report manifest and a deterministic rigor gate. Integrates captum / pytorch-grad-cam; it does not reimplement them, and never runs a model on real patient data.
Generate a citable data dictionary / codebook from a tabular dataset (CSV/TSV/Excel/Parquet/Stata/SAS). Profiles every variable — role, type, units placeholder, level frequencies, range/quantiles, missingness — and emits codebook.md + codebook.json. Flags coded variables whose level meanings are unknown as [NEEDS DICTIONARY] rather than guessing them, feeding /define-variables and the dictionary-first workflow.
> Design or audit a model-agnostic evaluation harness for an LLM or multimodal LLM on a clinical task (radiology report generation, visual question answering, clinical text extraction/classification) — the adjudicated reference standard, clinical-efficacy metrics (RadGraph-F1 / CheXbert-F1 beyond BLEU/ROUGE), faithfulness and hallucination, pretraining-contamination of public benchmarks, prompt-sensitivity and determinism, answer-matching, and a reader study — and gate the plan for those axes. Works on a closed API or open weights. Never fabricates outputs or scores, and never reports n-gram overlap as clinical correctness.
> Vet the concrete third-party model a study will be built on — this repository, this revision, this checkpoint — not the architecture family. Records a model dossier (source and version pin, licence and the file it was read from, intended use, pretrained-weight provenance, model task vs study task, reported validation, what the model was developed on, your evaluation arms) and evaluation arm sitting on the benchmark the model was developed or tuned on, so the arm reads like validation while being closer to a training-set score. Also an evaluation set inside a pretraining corpus, an unstated or use-incompatible licence, an unpinned revision, and a hardware claim never executed. It vets an artifact; it never downloads or runs one.
> Generate the documentation an engineer-built medical-imaging model must carry — a Model Card (Mitchell et al. 2019), a Datasheet for its dataset (Gebru et al. 2021), and a METRIC-informed data-quality pass — filled from user-supplied facts, then verify every required section is present and non-empty before the card ships to a repo, Hugging Face card, or manuscript supplement. Never fabricates numbers, provenance, consent, or licence; unfilled fields stay flagged. Ships a deterministic completeness gate. Model Card and Datasheet are documentation standards vendored here as templates, not counted reporting checklists.
> Generate a reproducible, runnable PyTorch training repo for a medical-imaging task — segmentation, classification, detection, image-to-image synthesis, self-supervised pretraining, or fine-tuning a pretrained backbone (transfer learning) — the missing middle link between choosing an architecture and validating a trained model. Emits a patient-level seed-locked split as an auditable artifact, a task-appropriate model, train and evaluate scripts that seed every RNG and infer under eval mode, a config, requirements, a reproducibility record, and a Methods stub with VERIFY placeholders (no fabricated numbers). Fine-tuning mode adds a frozen-then-unfrozen schedule, discriminative learning rates, and a pretrained-weight provenance record. The reproducibility guarantees hold by construction, so the build is leakage-safe before any training runs. Integrates with MONAI, nnU-Net, TorchIO, timm, and torchvision — it does not reimplement them.
> Compute and report task-correct held-out metrics for a trained medical-imaging model — segmentation (Dice plus a boundary metric such as HD95 or NSD, per structure), classification (AUROC plus AUPRC and sensitivity/specificity with bootstrap CIs at the deployment prevalence), detection (FROC or mAP with a stated IoU criterion), interactive/promptable segmentation (the interaction-count, convergence, and per-case-time axes a static Dice omits), or generative/synthesis image evaluation (similarity plus the downstream-task efficacy similarity alone cannot establish) — plus calibration and subgroup slices. Emits a per-case results table that analyze-stats turns into publication tables, and gates the metric choice against Metrics Reloaded, CLAIM 2024, and Park et al. 2024 (no pixel accuracy for segmentation, no bare accuracy under imbalance, no static Dice for an interactive method, no similarity-only claim for a generative model). Numbers come only from executed code, never hand-typed.
> Design or audit the clinical-validation study for an engineer-built medical-imaging model (segmentation, classification, or detection) before the validation report or manuscript is written. Covers patient-level split disjointness and the data-leakage taxonomy, tuning-on-test, internal versus genuine external validation, comparator design, single-run versus multi-seed variance, task-correct metric selection, test-set sizing, and CLAIM 2024 / TRIPOD+AI / STARD-AI reporting fit. Ships a deterministic split-leakage gate that proves patient disjointness by set arithmetic on the emitted split-assignment table. Does not build or train models — it integrates with MONAI / nnU-Net, it does not replace them.
> Design or audit the data-preparation stage of a medical-imaging model — DICOM/NIfTI intake, resampling and intensity normalisation, and the augmentation plan — so the pipeline is leakage-safe before model-scaffold builds the training repo. Emits a declarative preprocessing manifest and a dataset-level normaliser fit on non-train data, any data-fitted transform run before the split, and the same patient's slices crossing splits. Integrates MONAI / TorchIO transforms; it does not reimplement them, and it never runs preprocessing on real patient data.
> Profile a medical-imaging dataset before any modelling decision is made — the acquisition grid, voxel spacing and orientation spread, the intensity domain, which label values are actually present, how much of the volume the target occupies, and how large the target is in millilitres — then gate that profile against the researcher's declared plan. Catches, at the point where it is carries no ground truth, labels whose grid does not match their image, a stray label index, a target occupying a fraction of a percent while accuracy is planned as a metric, and acquisition heterogeneity nobody declared a resampling decision for. Emits a dataset-profile JSON and a deterministic gate that reads it (stdlib-only, so an audit travels with the JSON). It describes the data and audits the plan against it; it does not preprocess, split, or train.
Dataset version control for research reproducibility. Builds a deterministic content-hash manifest of a dataset (file SHA-256 + tabular schema + per-column value hashes), verifies a later copy against it to detect drift (schema change, row-count change, value changes), and diffs two manifests. Use to prove an analysis ran on the intended data, lock a dataset version, or reproducibility-lock bundled demos.
入力・出力・成功基準・決定事項・未解決条件を明確化し、下流エージェントが推測せず実行できるようにする。LLM向けのプロンプト・ハンドオフ・計画成果物・レビュー・レポート・生成指示を記述または改訂する時に使用。