196 skills · sorted by relevance
Build image classification and search workflows by comparing images with text descriptions. Covers classification without additional training, similarity scoring, batch processing, and storing image representations in a vector database for retrieval.
Find PhysicsNeMo models, data loading pipelines, and examples for machine learning tasks involving physical systems. The skill checks current repository files, presents relevant alternatives, and suggests a reading order without writing training code.
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
The English summary is being prepared. Showing the original description.
Builds and deploys containerized workloads on Elastic Kubernetes Service (EKS), Elastic Container Service (ECS), Fargate, and ECR (Elastic Container Registry). Covers general EKS knowledge, Karpenter, AWS Load Balancer Controller and leveraging various open source Kubernetes projects with EKS. Covers general ECS knowledge, task definitions, Fargate services, ECS Exec, ECS Express Mode and ECS Managed Instances. Covers general Elastic Beanstalk knowledge, Elastic Beanstalk configuration and platforms supported by Elastic Beanstalk. Covers general ECR knowledge, ECR repository setup and lifecycle policies. Includes recommending, enabling, and reading Amazon ECS Action Logs to troubleshoot control-plane failures (deployment rollback/circuit-breaker, task placement, scaling, task replacement). Applies when deploying, debugging, or optimizing containers on AWS. Should be used instead of relying on internal knowledge for these services.
The English summary is being prepared. Showing the original description.
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
The English summary is being prepared. Showing the original description.
Assess compliance with the EU General-Purpose AI (GPAI) Code of Practice under the AI Act (Regulation (EU) 2024/1689). Use when asked to determine GPAI model provider obligations, assess Code of Practice compliance, evaluate transparency or copyright requirements for GPAI models, check systemic risk obligations, build a GPAI compliance roadmap, or prepare for AI Office requests. Covers all three Code chapters (Transparency, Copyright, Safety & Security), the 12 commitments and their measures, systemic risk classification (Article 51), provider obligations (Articles 53 and 55), open-source exemptions, enforcement timeline, Commission/AI Office supervision, and DACH-specific overlays such as BSI cybersecurity and works council implications. Triggers on phrases like "GPAI compliance", "Code of Practice assessment", "GPAI model obligations", "systemic risk evaluation", "AI Act transparency requirements", "GPAI copyright policy", "general-purpose AI compliance".
The English summary is being prepared. Showing the original description.
Delegate code review to a subagent running a specific model. Use ONLY when user explicitly names a model to review changes ("review with opus", "use sonnet to review", "review with gemini"). The root agent reconstructs changes from conversation history and spawns a subagent with the code-review skill using the specified model. Do NOT use for general code review (use code-review skill instead), for reviewing PRs from git history, or when no model is specified by the user.
The English summary is being prepared. Showing the original description.
Use when refining a draft user prompt before sending it to a coding agent. Decomposes goal/context/constraints/acceptance/output-format, detects ambiguity and model-coupled framing, then emits a model-agnostic rewrite. Supports --analyze, --score, and --deep. NOT for prompts from scratch (mk:brainstorming), plans/reviews (mk:elicit), implementation plans (mk:plan-creator), or general codebase scouting (mk:scout).
The English summary is being prepared. Showing the original description.
Turn audio and video into text with Whisper, including Japanese and other supported languages. This skill covers transcription, English translation, timestamped subtitles, model selection, and batch processing, with guidance on hardware needs and recognition limitations.
Design a RAG pipeline that retrieves documents to support AI answers. Analyze document splitting, select embedding models and vector databases, and evaluate retrieval quality using test queries and known relevant documents.
Evaluate AI models and agents on Google Cloud using test datasets and scoring criteria. Generate simulated user scenarios, analyze failures, and compare results across changes to guide improvements to prompts and code.
Guides image classification and search with OpenAI's CLIP by comparing images with text descriptions, without additional training. Includes batch processing, image-text matching, and category-based checks for potentially inappropriate images.
Turn recorded audio and video into text or timestamped subtitles with Whisper. This skill covers transcription across 99 languages, language detection, translation into English, batch processing, and model selection for available computing resources.
Choose and implement machine learning methods for estimating causal effects with many control variables or effects that differ across groups. Guidance covers DML, causal forests, and related methods, including diagnostics and limits on interpretation.
Find academic papers, statistics, and technical documentation with citations for writing and fact checking. The skill selects a search or reasoning model based on the question, supporting both straightforward lookups and comparisons across studies.
Use when the model setup, equilibrium concept, or proof architecture is the bottleneck for an American Economic Journal: Microeconomics (AEJ: Micro) manuscript — the central skill for a theory-first paper. Builds the model to the AEJ: Micro bar (clean, general, well-motivated result); it does not check whether your theorem is correct.
The English summary is being prepared. Showing the original description.
Via modeling: pads, antipads, ground return vias, GRV placement, and signal integrity for high-speed layer transitions. TRIGGER: user asks to model a via, design a via transition, place ground return vias, analyze via performance, or check signal integrity through layer transitions. Invoke BEFORE writing code — only viaSingleEnded exists (no viaDifferential), and the location format is non-obvious. SKIP: general signal integrity without vias (use matlab-analyze-em), transmission line design (use matlab-design-pcb-transmission-line), PDN analysis (use matlab-analyze-pcb-pdn), material/stackup setup only (use matlab-manage-pcb-material).
The English summary is being prepared. Showing the original description.
Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.
The English summary is being prepared. Showing the original description.
Microbiome time series simulation with generalized Lotka-Volterra model, Self-Organized Instability (SOI), and other models. Hubbell's Neutral model is used to determine the abundance matrix. The resulting abundance matrix is applied to (Tree)SummarizedExperiment objects.
The English summary is being prepared. Showing the original description.
Create a repository-grounded AppSec threat model covering assets, trust boundaries, attackers, abuse paths, and mitigations. Use only for explicit threat-modeling requests, not general architecture or code review.
The English summary is being prepared. Showing the original description.
Answer a hard question by fanning it out to a PANEL of models running in parallel — each answering independently with web search and bash, none seeing the others' work — then having Opus 4.8 judge every response into a structured analysis (consensus, contradictions, partial coverage, unique insights, blind spots) and write a final answer grounded in it. The panel is two independent Opus 4.8 runs (slug opus4.8-4.8), Opus 4.8 + GPT-5.5 via codex (opus4.8-gpt5.5), Opus 4.8 + Gemini 3.1 Pro via agy (opus4.8-gemini3.1pro), or all three (opus4.8-gpt5.5-gemini3.1pro). Opus always judges and writes the final answer — the pipeline can't be reversed. Runs on local CLI subscriptions (no metered API), and saves a timestamped provenance .md per run. Use this whenever the user asks to "run it through Fusion", says /fusion, wants a multi-model / panel / ensemble answer, wants a question cross-checked across models, or wants a higher-confidence answer with consensus and blind spots surfaced — even if they don't say "fusion". General-purpose: any topic (research, law, strategy, technical, personal). Best for high-stakes research, design calls, and debugging where being confidently wrong is expensive.
The English summary is being prepared. Showing the original description.
Produce short-form video with Pika (pika.art) — its effect-driven tools (Pikaffects, Pikadditions, Pikaswaps, Pikaframes, Pikascenes, Pikatwists) and audio-driven lip sync (Pikaformance), plus text-to-video and image-to-video. Use when a task calls for playful, stylized, meme-able social clips, or for applying generative effects and object swaps to real uploaded footage, and when deciding whether Pika is the right engine versus a higher-fidelity model. Covers model versions, credit/plan economics, the fal.ai API route, prompt construction, iteration/repair, capability limits, and consent/rights rules for uploaded real-person media. Not a general "best video model" chooser.
The English summary is being prepared. Showing the original description.
Select, integrate, and operate multi-model image-generation gateways with model-specific schema discovery, version policy, asynchronous jobs, webhooks, spend approval, safe inputs and artifacts, data-governance review, and billing observability. Use for comparing or building against fal.ai, Replicate, or Together AI image APIs, including controlled failover; do not use for direct model-provider APIs, local inference, training, dedicated endpoint provisioning, video generation, or general image editing.
The English summary is being prepared. Showing the original description.
Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".
The English summary is being prepared. Showing the original description.