Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Covers USDZ rendering, NCore conversion, 3D Gaussian splatting, gRPC sensor simulation, carline adaptation, and PhysicalAI Hugging Face datasets. Excludes SimReady and infrastructure setup.
Handles workflow selection, preflight checks, submit-time interpolation, monitoring, and output retrieval. Supports video enrichment and pseudo-labeling workflows.
维护 Claude physics 的 LLM Wiki 知识库。适用于整理物理笔记、论文、题目、推导、方法页、论文页和综合讲义页，并将资料沉淀为结构化 Obsidian Markdown 页面。
Covers fixed and variable timesteps, render interpolation, mass, gravity, and drag. Addresses tunneling with continuous collision detection and configures collision layers and masks.
Uses live repository search to locate existing PhysicsNeMo resources for forecasting, surrogates, downscaling, inverse problems, and other physics-focused tasks. Provides navigation guidance without authoring code or handling installation.
Provides an internal helper contract for invoking the pi-companion runtime from Claude Code.
Runs the Pi coding agent CLI (pi) as a background implementer for requested tasks or queues. Keeps diff review and integration with the delegating agent.
Run the paper SPY put-credit factory from Pi (pi.dev). Status, dry-run, exits, scorecard. No live, no MCP install, no iron-condor entries.
Maintains task_plan.md, findings.md, and progress.md, with lifecycle hooks supplying selected planning context. Automatic recovery reads project planning files; explicit catch-up supports local session metadata or bounded excerpts. Intended for research or work needing five or more tool calls.
Provides internal guidance for composing prompts that Pi runs can handle reliably. Covers coding, review, diagnosis, and research tasks, with DeepSeek as the default model.
Provides internal guidance for presenting output from Pi helpers back to the user.
Recommends libraries from a curated, opinionated list for specific frontend tasks. Covers OTP inputs, command menus, drag and drop, toasts, charts, state, styling, and more; runs only when explicitly invoked.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name