Results for “wan”

Automates computational chemistry through Rowan's Python API, including molecular property prediction, structure optimization, and protein–ligand binding predictions. Submits cloud calculations, handles batches of molecules, tracks workflow status, and retrieves results without a local compute cluster.

• Batch prediction of molecular pKa values in Rowan
• Optimizing molecular structures and comparing conformers in Rowan
• Predicting protein–ligand binding and complex structures in Rowan

Assess LoRaWAN and sub-GHz wireless devices by capturing signals, examining packet formats, and checking key reuse and replay weaknesses, where recorded messages are resent. It covers IoT networks, fixed-code remotes, and proprietary radio protocols.

• Reviewing LoRaWAN keys and frame counters
• Testing fixed-code remotes for replay weaknesses
• Analyzing proprietary wireless packet formats

Monitor model training through WandB metrics to detect invalid numbers, worsening loss, and declining evaluation results. Ambiguous trends receive a Codex review, while stopped runs retain key metrics and the reason for stopping.

• Check loss and evaluation trends during model training
• Detect NaN values and diverging loss
• Review flat or noisy training metrics

Guides LLM compression through pruning, which removes selected model weights. Covers Wanda and SparseGPT methods without retraining, accuracy comparisons, and structured weight patterns that can accelerate inference on compatible hardware.

• Trying model compression without retraining
• Comparing accuracy before and after pruning
• Choosing between Wanda and SparseGPT

Reduce LLM weight usage through pruning, which removes selected model parameters. Explore Wanda and SparseGPT for compression without retraining, choose hardware-friendly patterns for faster inference, and compare the compressed model's accuracy with the original.

• Compressing an LLM without retraining
• Comparing pruning methods
• Exploring faster inference on supported hardware

Track machine learning experiments with SwanLab by recording training settings, metrics, and media such as images and audio. Learn to compare runs, inspect training charts, and connect existing training code to local, cloud, or self-hosted dashboards.

• Comparing experiments with different training settings
• Viewing training metrics in a local dashboard
• Logging sample images and audio alongside metrics

Collect experiment reports from issues and organize them in an existing Markdown index. It places entries in relevant sections, merges WandB experiment links into existing records, and checks for duplicate entries and formatting inconsistencies.

• Adding new experiment reports to an index
• Sorting uncategorized experiments
• Merging WandB links into existing entries

Monitor machine learning training through WandB or training logs. Check for invalid numbers, worsening metrics, and stalled improvement, then report whether to continue, wait, or stop, preserving evidence and notes when stopping a run.

• Monitoring loss and evaluation metrics during training
• Investigating invalid numbers or diverging training
• Assessing whether stalled training should continue

Add file-based observability, tracing, and run analysis to LLM/agent experiments — per-turn transcripts, tool calls and results, reasoning traces, token/cost accounting, per-episode artifacts, plus terminal viewers and a run-comparison report. Platform-agnostic: one small adapter covers OpenAI, Gemini/Vertex, Anthropic, LiteLLM, Tinker, vLLM, or any custom inference stack, and the same tooling then works unchanged. Use this skill whenever the user wants observability, tracing, logging, or run tracking for model experiments; asks why an agent failed a task or wants to replay/debug/diff an episode; wants to compare models, arms, or ablations; wants to instrument a new folder, repo, or platform ("add observability here", "do the same for Tinker/Gemini/OpenAI"); wants to import or tie in existing experiment results so old runs show up alongside new ones; or wants eval runner scripts where many models share one protocol. Reach for this even when they only say "log what the model is doing", "I can't tell what happened in this run", or "set up traces for this experiment".

The English summary is being prepared. Showing the original description.

Clean up after (or abandon) a Rails upgrade. Drop NextRails.next? and NextRails.current? branches and retire dual-boot scaffolding (Gemfile.next, Gemfile.next.lock, conditional Gemfile groups), keeping either the next or the current version. Trigger when the user says they are done with the upgrade, want to clean up dual-boot, want to drop NextRails branches, want to finish the upgrade, want to abandon or revert the upgrade attempt, want to roll back to the current Rails version, or want to pause this upgrade hop. Based on FastRuby.io's "Finishing an Upgrade" methodology, extended with an abandon/pause path.

The English summary is being prepared. Showing the original description.

Spin up a working LiveAvatar demo from a curated catalog — clones the reference repo, installs dependencies, provisions the LiveAvatar account, and fills the env file, then hands off the parts only a human can do. Use when: (1) User wants to try, test, see, or demo LiveAvatar, (2) User asks what LiveAvatar demos or examples exist, (3) User wants a sales agent / lead-qualification avatar, (4) User wants a LiveKit agent driving a LiveAvatar avatar, (5) User wants an avatar joining their own LiveKit room, (6) User wants a speech-to-speech avatar, a GPT-Live demo, a language-learning or tutor avatar, a customer-support avatar, a poker coach / game-style avatar, or an avatar with on-screen visuals/overlays, (7) User says "run the LiveAvatar demo", "show me LiveAvatar", "get me started with LiveAvatar", or "clone the LiveAvatar example", (8) User is evaluating LiveAvatar and wants something running before writing their own integration.

The English summary is being prepared. Showing the original description.

Use W&B to record machine learning experiments, visualize training, and compare results. The skill also covers automated searches for training settings and version tracking for datasets and models, helping teams share experiments and trace their inputs.

• Logging training metrics and viewing progress in real time
• Comparing experiments with different training settings
• Searching automatically for better training settings

Set up W&B to record machine learning metrics and settings, visualize training progress, and compare experiments. Includes automated searches for training settings, version tracking for datasets and models, and shared reports for team collaboration.

• Recording and visualizing training metrics
• Comparing experiments with different training settings
• Automatically searching for better training settings

Set up W&B to record machine learning metrics and settings, visualize training progress, and compare experiments. Includes automated searches for training settings, version tracking for datasets and models, and shared reports for team collaboration.

• Recording and visualizing training metrics
• Comparing experiments with different training settings
• Automatically searching for better training settings

Fetch YouTube transcripts to summarize, quote, or analyze what a video actually says. Also search videos and channels, search within a channel, and retrieve playlist videos through an external API.

• Summarizing a video's spoken content
• Finding passages to quote from a video
• Searching for videos within a channel

Extend / continue a video temporally with Pusa 2.2 in ComfyUI. Temporal flowmatching (the flowmatch_pusa scheduler + WanVideoAddPusaNoise) on the WanVideoWrapper stack with WAN 2.2 T2V A14B (HIGH/LOW) models and the Pusa V1 LoRAs, conditioning on the loaded clip via WanVideoEncode so the existing motion carries into the continuation. Covers the kijai wanvideo_2_2_14B_Pusa_extension graph, model/LoRA slots + downloads, noise/length/scheduler settings, chaining multiple extensions, VRAM tiers, gotchas, and the extend→upscale handoff.

The English summary is being prepared. Showing the original description.

Expert knowledge for Azure Virtual WAN development including troubleshooting, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring VWAN hubs, P2S/Always On VPN, BGP/IPsec routing, ExpressRoute/SD-WAN, or Private Link, and other Azure Virtual WAN related development tasks. Not for Azure Virtual Network (use azure-virtual-network), Azure VPN Gateway (use azure-vpn-gateway), Azure ExpressRoute (use azure-expressroute), Azure Traffic Manager (use azure-traffic-manager).

The English summary is being prepared. Showing the original description.

Socratic questioning partner named Gadfly for deep learning through dialogue. Use this skill when the user wants to learn, understand, or explore a topic through questions rather than explanations. Trigger when the user says "teach me about...", "help me understand...", "I want to learn...", "ask me questions about...", "quiz me", "Socratic method", "Gadfly", or wants to deeply understand something through dialogue rather than passive reading. Also trigger when the user provides a text or document and wants to be questioned about it, or wants to check their own understanding of a concept.

The English summary is being prepared. Showing the original description.

Authoritative reference for working with the released Wandelbots NOVA API v2 in the wandelbots-nova Python SDK. Use whenever a task touches the NOVA API, the generated `wandelbots_api_client` models (`nova.api.models.*`), motion planning requests (`plan_trajectory`, `MotionGroupSetup`, `LimitSet`, `LimitsOverride`), robot limits, or torque/velocity/acceleration/jerk limits. Reach for this skill before guessing field names or assuming a field exists — the installed client reflects the RELEASED API, while nightly specs may contain unreleased fields. Especially relevant for controller-reported limits (e.g. KUKA torque) and any "does field X exist / how is it forwarded to the planner?" question.

The English summary is being prepared. Showing the original description.

Find and identify the CCSPlayerPawn_SnapViewAngles function in CS2 server binary using IDA Pro MCP. Use this skill when reverse engineering CS2 server.dll or libserver.so to locate the non-virtual SnapViewAngles method, anchored on the "setang" console-command usage string and its non-teleport call branch. Emits a unique IDA-style byte signature and a func YAML. Trigger: CCSPlayerPawn_SnapViewAngles, SnapViewAngles

The English summary is being prepared. Showing the original description.

Track machine learning experiments in W&B, record training settings and metrics, and compare results in dashboards. Automate searches for training settings and keep version histories for models and datasets.

• Comparing accuracy across training runs
• Monitoring training progress in dashboards
• Searching for better training settings

Run molecular property predictions, explore molecular shapes, and estimate how compounds bind to proteins through a cloud Python API. Process compound batches and connect modeling steps without maintaining local high-performance computing infrastructure.

• Predicting properties across a compound library
• Exploring molecular shapes and tautomeric forms
• Estimating how compounds bind to proteins

Turn research results into figures and tables for papers using pubfig and pubtab. Choose an appropriate presentation, convert Excel tables to LaTeX, export assets, and check readability, labels, and consistency before submission.

• Choosing a chart that communicates research findings
• Converting an Excel table to LaTeX for a paper
• Preparing a summary figure with a companion table

Review existing R scripts for code quality, reproducibility, domain correctness, and coding standards. Produce a separate report for each script, plus a severity-based summary of findings and the three most critical issues, without changing source files.

• Checking whether an analysis script is reproducible
• Reviewing R code against coding conventions
• Auditing several related R scripts