3.7K skills · sorted by relevance
Read CARLA Leaderboard result files to understand driving scores, route completion, and penalties. Investigate low scores, compare two runs, merge split results, or recalculate scores under version 2.0 or 2.1 rules without rerunning the simulation.
Run CARLA routes with a driving agent through ScenarioRunner, including scenarios available only in route mode. Inspect route contents, execute one or all routes, and obtain reports on completion, collisions, traffic lights, and other criteria.
Route fiction requests to the appropriate writing, analysis, research, or cover skill. You can also switch between book projects and open a local dashboard to browse and edit manuscripts and project files.
Create, update, and analyze Mixpanel dashboards using live report data. Summarize trends and relationships across metrics, adjust report layouts, and add text cards that explain findings alongside the charts.
Integrate Switchboard into Solana apps to access price feeds, custom external data, and verifiable random values. The guide includes TypeScript and Rust examples, plus Surge streaming for interfaces that need live price updates.
Write a board pre-read that's sent before the meeting so the meeting is about decisions, not status. Use when asked to prepare a board pre-read, a board update/package, or pre-meeting materials for a board. Produces a board pre-read — a TL;DR, the metrics dashboard vs. plan, what's working / what's not, the decisions and asks for the board, and risks — designed to be read in advance.
The English summary is being prepared. Showing the original description.
Generate storyboard image boards and matching video-generation prompt scripts for specific scenes in a short video plan. Use this skill whenever the user asks to create a storyboard, storyboard image, video prompt script, scene prompt, image-to-video prompt, shot board, or per-scene video-generation package, especially when they specify a scene number, duration, or an existing video plan. This skill saves outputs as storyboard/scene-XX.png and storyboard/scene-XX.md and enforces grid sizing, timing labels, and strict character, wardrobe, prop, and location continuity.
The English summary is being prepared. Showing the original description.
Firmware development for the Beetle — the CJMCU / DFRobot "Mini Arduino Leonardo" USB board (ATmega32U4 @ 16 MHz, 5 V, 21×28 mm, castellated pads) — its native USB (CDC serial + HID keyboard/mouse/joystick), Caterina bootloader and 1200 bps touch upload, ten exposed I/O pads, four PWM pins across Timer0/Timer1, five ADC channels, I2C on D2/D3, SPI on the back-side ICSP pads, 28 KB usable flash and 2.5 KB SRAM, and the PlatformIO + Arduino AVR core (`board = leonardo`) setup around them. Use when working on this board or any ATmega32U4 Leonardo/Micro/Pro-Micro-class clone: project setup, platformio.ini, why the board shows up as two different serial ports, uploads that fail or hang, recovering a bricked or HID-spamming board by shorting the ICSP reset pads, pin mapping and which pads are missing, PWM/timer conflicts, Servo and tone, USB HID keyboard projects, the SRAM budget, powering from the + pad, or debugging why something on the board does not work.
The English summary is being prepared. Showing the original description.
Build or improve a Coval dashboard with metric visualizations backed by real data. Creates new dashboards from scratch or rebuilds existing ones by analyzing usage patterns, metric frequency, and data density. Use when user says "create a dashboard", "build a dashboard", "improve my dashboard", "add widgets", "visualize my metrics", "make a performance dashboard", or "dashboard for my runs".
The English summary is being prepared. Showing the original description.
Create monitoring dashboards for Grafana, SigNoz, and similar platforms. Choose metrics around operational questions, organize panels by purpose, and define clear titles, units, filters, and thresholds to help operators assess health and bottlenecks.
Build a trading analysis dashboard as a single HTML file, with dense market panels and interactive charts. Include light and dark themes, Live/Demo controls, chart focus views, and a keyboard command menu for navigating the interface.
Prototype a single-screen kanban task board in HTML, with columns for work stages, task cards, assignee avatars, estimates, and filters. A sprint summary highlights progress, leading assignees, and blocked tasks for a team overview.
Build Grafana dashboards that show application and infrastructure health through request rates, errors, response times, and resource usage. Organize metrics into useful panels, add filters and alerts, and manage dashboard definitions as code.
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Includes PyTorch and TensorFlow logging examples for examining weight distributions, predictions, and performance bottlenecks during machine learning training.
Guide AI agents through Zoom MCP, a tool connection for searching meeting content and retrieving recordings, related assets, and transcript resources. Covers tool selection, authentication requirements, troubleshooting, and routing Docs or Whiteboard requests to separate services.
Prepare for board meetings, investor updates, and fundraising presentations by reviewing key numbers, rehearsing difficult questions, and shaping an honest business narrative. Includes preparation for individual directors and follow-up actions after the meeting.
Turn an electronics or IoT idea into a working breadboard prototype. Get board and software recommendations, a plan for viewing sensor readings, and time and cost ranges tailored to experience, budget, and location.
Query Prometheus metrics through Grafana and manage dashboards as JSON files. Use it to investigate current values and trends, add or adjust panels, and preview dashboard updates before applying them.
View and edit whiteboards embedded in 飞书 cloud documents. Export previews, SVG vector images, diagram source code, or structural data, and update boards using Mermaid, PlantUML, SVG, or the native OpenAPI format.
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Guides logging for PyTorch and TensorFlow, including weight distributions and performance profiling to investigate training problems and processing bottlenecks.
Check kanban boards, which organize tasks into columns, and retrieve task lists filtered by status, assistant, or board. Use the returned data to see task counts and review work in progress.
Build dashboards from verified product or business data, with clearly defined metrics, charts, and useful filters. Organize the view from headline results to supporting detail, and check data freshness, numerical consistency, and dashboard behavior before handoff.
Use the OpenServ Ideaboard API to find service ideas, register work in progress, and report completed implementations. It also covers proposing ideas, coordinating through comments, and sharing service URLs that accept payments through x402.
Launch a terminal or web dashboard to inspect Claude Code activity across projects. Browse sessions, search messages, track token usage and estimated costs, and check MCP servers that connect external tools to the agent.