Loading...
Loading...
Found 2,156 Skills
Build Zerobus Ingest clients for near real-time data ingestion into Databricks Delta tables via gRPC. Use when creating producers that write directly to Unity Catalog tables without a message bus, working with the Zerobus Ingest SDK in Python/Java/Go/TypeScript/Rust, generating Protobuf schemas from UC tables, or implementing stream-based ingestion with ACK handling and retry logic.
Scaffold and build a full-stack web app: FastAPI backend (Python, uv, SQLModel, Postgres, Alembic, JWT + Google OAuth, boto3/S3) + React frontend (Vite, TypeScript, shadcn/ui + Tailwind, TanStack Router/Query/Table, Zod, Axios), wired with Docker Compose. Use this skill whenever the user wants to spin up, bootstrap, create, or design a new full-stack webapp; an API-first backend + SPA frontend; an admin/portal/dashboard app; file upload + S3; RBAC / role-based auth with seeded test users; local docker dev; or asks for a 'FastAPI + React' / 'Python + React' project. Runs mockup-first: marketing-design (brand/logo raster) + opendesign (HTML page mockups) before code, then ports the design to Tailwind/shadcn. Covers project structure, local setup, auth/RBAC, S3 uploads, and the gotchas that break these stacks.
Scan an experiment repo and generate a complete paper outline (H1/H2/H3) with user approval checkpoints at each level, then generate body text with evidence annotations, citations, and bilingual output. Python ML repos. 扫描实验仓库，逐级生成论文大纲（H1/H2/H3），每级用户确认后推进， 然后生成带证据标注、引用和双语输出的正文文本。
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Grades a specified set of test methods individually and produces a concise table mapping each test (fully-qualified name) to a letter grade (A–F), a score band, and a one-line note — designed to be posted as a PR comment. Use when the caller wants per-test feedback on a curated list of methods (for example, the new or modified tests in a pull request), not a suite-wide audit. Polyglot: .NET, Python, TS/JS, Java, Go, Ruby, Rust, Swift, Kotlin, PowerShell, C++. Input is a list of test methods (or method bodies / file+line spans); output is a compact markdown table plus a short summary. DO NOT USE FOR: full suite audits (use test-quality-auditor agent or test-anti-patterns), writing new tests (use code-testing-generator agent or writing-mstest-tests), fixing failures, or measuring code coverage.
Profile a model running on MAX to find where it spends time and whether the GPU is saturated. Use when the user asks to "profile my model," "where is my model spending time," "why is inference slow," "is my GPU being utilized," "how much GPU am I using," "get a kernel breakdown," "capture an nsys/rocprof/ncu trace of max serve," or wants to measure MAX inference performance. Works for any model MAX can run — built-in architectures and custom ones loaded with --custom-architectures — from a pip or pixi install (max generate, max serve, or a Python script) on NVIDIA or AMD GPUs. Decide cheapest-first: a GPU utilization check, then a kernel breakdown, then a single-kernel deep dive only when one kernel dominates.
Huawei Cloud CCE Metric analysis skill using the Python dispatcher with hcloud-backed cloud service queries. Use this skill when the user wants to: (1) query Pod/Node/CoreDNS/nginx-ingress/autoscaler/control-plane CPU, memory, disk, QPS, latency, request, connection, certificate, scaling, or error-rate metrics, (2) get resource usage TopN rankings, (3) query ECS/ELB/EIP/NAT cloud resource metrics, (4) aggregate cluster monitoring data with anomaly detection, (5) detect threshold-based resource anomalies. Trigger: user mentions "metric analysis", "指标分析", "CCE metrics", "CCE 指标", "AOM metrics", "AOM 指标", "CoreDNS metrics", "CoreDNS 指标", "nginx ingress metrics", "nginx-ingress 指标", "autoscaler metrics", "autoscaler 指标", "HPA metrics", "HPA 指标", "apiserver metrics", "etcd metrics", "controller manager metrics", "scheduler metrics", "control plane metrics", "控制面指标", "certificate expiration", "证书过期", "resource metrics", "资源指标", "CPU usage", "CPU 使用率", "memory usage", "内存使用率", "performance monitoring", "性能监控", "TopN", "resource ranking", "资源排名"
Use when a developer wants to iterate on ONE specific Agent Observability / LLM Obs trace whose output they didn't like — re-running that trace against their LOCAL code, seeing a concise diff of the old vs new output, and looping (change code → replay → diff) until satisfied. Invoked as /agent-observability-replay-trace <trace-id> [changes to test]. Signals: "replay this trace"; "iterate on a trace"; "this trace's output is wrong, fix it and re-run"; "re-run trace <id> with <change>"; pasting a trace id from the Agent Observability UI with a description of what to fix. It fetches the trace via the datadog-llmo MCP or the pup CLI, edits code, re-runs the app to emit a NEW trace, and diffs the two — no local server, no browser. For agents traced with ddtrace / LLM Obs (Python first-class), with JSON-serializable entry input. Do NOT use for: scored Experiments or the browser "Replay" button (that's agent-observability-replay-experiment), building an experiment from a dataset/CSV, writing evaluators, root-causing failed traces, or RUM/HTTP session replay.
Reconstruct Blender models from supplied reference sheets, branding templates, texture atlases, orthographic front/side/back/top views, or mascot/logo art where visual fidelity to the source is more important than a plausible generated object. Use when the user says the model must match a template, wireframe, texture pack, character sheet, mascot sheet, or brand asset exactly; also use after feedback like "does not look like the reference", "fit the texture 1:1", "wrong number of visible parts", or "compare against the template". Requires Blender MCP plus local Python with Pillow/OpenCV/numpy; pairs with blender-uv-texturing, wireframe-to-3d, blender-modeling, blender-materials, and blender-export.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Full OpenAI-compatible GPT Image 2 coverage across images/generations, images/edits, and responses with the image_generation tool. Use when the one-shot image helper is not enough - text-to-image, mask edits, multi-image batches, streaming, partial_images, and mixed text+image Responses flows. Reads .env and respects process environment variables; works with any OpenAI-compatible gateway.
Gemini-native Nano Banana image generation and editing across Nano Banana, Nano Banana 2, and Nano Banana Pro. Use when you need text-to-image, image-to-image edits, repeated local references, batch generation, dry-run request inspection, or a custom Gemini-compatible base URL such as a self-hosted gateway.