381 skills · sorted by relevance
Plan and troubleshoot large language and vision model training and inference. This guide uses hardware measurements to identify bottlenecks, address memory shortages and unstable training, and improve checkpointing, recovery, and performance across multiple GPUs and machines.
Download individual YouTube videos with a chosen quality, file format, and destination folder. Save video as MP4, WebM, or MKV, or download only the audio as MP3 using the included Python script.
Build Angular 17+ applications with standalone components, routing, and shared application state. Covers reactive data handling with RxJS, performance improvements, and unit and integration tests, with code and explanations of architecture choices.
Estimate inference memory for models on Hugging Face Hub without downloading their weights. Check GPU capacity for Safetensors or GGUF files, with optional estimates for the KV cache, memory used to retain attention data during generation.
Improve a web page’s loading speed, response to user actions, and visual stability. The skill guides targeted fixes for LCP, INP, and CLS, with code examples, measurement methods, and checklists for each metric.
Build or repair game inventory and equipment systems, including item pickup, stacking, drag and drop, and saving. It guides transfers that fully succeed or leave state unchanged, accessible controls, and tests for item loss or duplication.
Implement, debug, or review Nexent frontend pages and React components using existing architecture and UI guidance. Cover API connections, shared data and types, styling, and localization, with checks for loading states, errors, and affected behavior.
Strengthen interfaces for real usage by handling long text, network failures, empty data, and repeated submissions. Improve internationalization, meaning support for different languages and regional formats, alongside accessibility and recovery from errors.
Guides React and Next.js interface development with examples for reusable components, shared state, forms, and error handling. It also covers loading performance, animations, and keyboard access to help build maintainable, responsive interfaces.
Generate TRES Finance reports as CSV or XLSX files, including transaction ledgers, balances, and cost basis reports. Verify that the export was actually created, monitor its completion, and return a download link.
Search academic papers, researchers, institutions, and journals through the OpenAlex CLI. Explore citations and related work, examine publication trends, export reference records, and download available open access PDFs, which are freely accessible papers.
Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Automatically checks system RAM/GPU before loading the model, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model. For classical statistical time series models (ARIMA, SARIMAX, VAR) use statsmodels; for time series classification/clustering use aeon.
The English summary is being prepared. Showing the original description.
Use this skill when the user is doing hands-on DOCA DPA host-side work on a BlueField — creating the `doca_dpa` Core context, loading a DPACC-compiled DPA app image (`doca_dpa_app`), creating DPA threads, launching kernels via `doca_dpa_kernel_launch_update_*`, draining `doca_dpa_completion`, running `doca_dpa_cap_*` discovery, choosing between the DPA comm component (inter-DPA messaging) and the DPA verbs component (in-kernel RDMA), or debugging `DOCA_ERROR_*` from `doca_dpa_*`. Trigger even without "DOCA DPA" or "Data-Path Accelerator": "run compute on the DPA from my host", "DPA kernel hangs, no completion", "DOCA_ERROR_DRIVER on launch", "DOCA/DPACC version skew", or "does this BlueField expose a DPA". Route elsewhere for DPA-side kernel programming itself, DPACC compiler internals, host↔DPU messaging (doca-comch), host-side RDMA (doca-rdma), and GPU-initiated networking (doca-gpunetio).
The English summary is being prepared. Showing the original description.
Terminal security analysis for shell environments. This skill should be used when checking commands for supply-chain attacks before execution, scanning repositories for hidden content or config poisoning, scoring URLs for homograph attacks, setting up AI tool protection, inspecting Python package artifacts, governing untrusted tasks or Web3 commands, auditing browser extensions, creating provenance receipts, downloading and executing scripts safely, investigating why tirith blocked a command, managing trusted patterns, running security audits, configuring MCP gateway proxies, or working with threat intelligence databases. Also use when the user mentions "tirith", "pipe-to-shell", "homograph", "ANSI injection", "zero-width", "punycode", "terminal security", "shell hook", "cloaking detection", "supply chain attack", "bidi override", "invisible unicode", or "config poisoning". Even if the user does not explicitly name tirith, use this skill when they ask about protecting shell environments, intercepting dangerous commands, or hardening AI agent tool execution.
The English summary is being prepared. Showing the original description.
Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.
The English summary is being prepared. Showing the original description.
Integrate Bunny.net services (CDN, Storage, Stream, DNS, Edge Scripting, Shield, Magic Containers, Optimizer, Database). Use when building with Bunny.net APIs, deploying to Bunny CDN, uploading files to Edge Storage, managing video streaming, configuring DNS zones, writing edge scripts, setting up WAF/DDoS protection, deploying containers, or optimizing images. Triggers on "bunny", "bunnycdn", "b-cdn", "pull zone", "edge storage", "bunny stream".
The English summary is being prepared. Showing the original description.
Run a submission-readiness preflight on a manuscript before arXiv upload. Use when the user is preparing an arXiv submission, asks to check a paper before uploading, mentions hallucinated or fake references, leftover LLM meta-comments / prompts in text, placeholder data (TODO, TBD, XX%), AI-use disclosure, scholarly integrity, research integrity, or arXiv moderation risk — even if they don't say "preflight". Also trigger on phrases like "check my paper before arXiv", "verify my references", "scan for AI artifacts", "scan for LLM residue", "is my submission ready", or "review .tex/.bib before submit".
The English summary is being prepared. Showing the original description.
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. **Trigger when user asks to:** - Store or search vector embeddings in PostgreSQL - Set up semantic search, similarity search, or nearest neighbor search - Create HNSW or IVFFlat indexes for vectors - Implement RAG (Retrieval Augmented Generation) with PostgreSQL - Optimize pgvector performance, recall, or memory usage - Use binary quantization for large vector datasets **Keywords:** pgvector, embeddings, semantic search, vector similarity, HNSW, IVFFlat, halfvec, cosine distance, nearest neighbor, RAG, LLM, AI search Covers: halfvec storage, HNSW index configuration (m, ef_construction, ef_search), quantization strategies, filtered search, bulk loading, and performance tuning.
The English summary is being prepared. Showing the original description.
Run Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML models. Covers Modal app setup, GPU selection, data downloading inside functions, and result handling.
The English summary is being prepared. Showing the original description.
Train GPT-2 scale models (~124M parameters) efficiently on a single GPU. Covers GPT-124M architecture, tokenized dataset loading (e.g., HuggingFace Hub shards), modern optimizers (Muon, AdamW), mixed precision training, and training loop implementation.
The English summary is being prepared. Showing the original description.
Fetches Twitter/X post and Article content — text, author, engagement metrics and embedded media — downloading images locally and generating complete Markdown with image references. Use when retrieving a tweet's text or an X Article with images, or pulling post metadata for a Markdown/PKM record. Preferred over Jina alone for X Articles with images.
The English summary is being prepared. Showing the original description.
Anti-slop skill for PRODUCT UI - dashboards, data tables, forms, multi-step flows, settings, list/detail, app shells. The agent reads the surface, budgets the frame first, and ships dense interfaces that are correct at every edge case (overflow, long labels, empty/error/loading states, i18n expansion, keyboard/a11y). House-system-first; maps to Carbon/Polaris/Atlaskit/Fluent/Primer/Material3/Radix-shadcn/Ant. The counterpart to taste-skill, which owns landing/portfolio/marketing.
The English summary is being prepared. Showing the original description.
Use for full-manuscript prose polish of an Academy of Management Journal (AMJ) manuscript — front-loading the argument, active voice, structure, and AOM house style. Polishes language and structure; it does not create the theoretical contribution (amj-contribution-framing) or fix the analysis (amj-data-analysis).
The English summary is being prepared. Showing the original description.
Loads, converts, and manipulates Hi-C contact matrices in cooler format (.cool/.mcool/.scool) and Juicer .hic, using cooler (Python + CLI), hic2cool, and hictk. Covers the single-resolution mcool URI (file.mcool::/resolutions/<bp>), the load-bearing divisive-vs-multiplicative weight-naming rule (KR/VC/VC_SQRT auto-divisive vs cooler's multiplicative weight), what survives .hic<->.cool conversion (FRAG matrices and norm vectors do not), raw-vs-balanced coarsening, the .pairs upper-triangle/chromsize-order contract, and chrom-naming/bin-table provenance. Use when loading a cooler, converting .hic to .mcool, selecting a resolution, building a cooler from pairs or a matrix, coarsening/zoomifying, importing Juicer norm vectors, or debugging all-NaN balanced matrices and chr1-vs-1 empty fetches.
The English summary is being prepared. Showing the original description.