Loading...
Loading...
Found 150 Skills
Use when "Modal", "serverless GPU", "cloud GPU", "deploy ML model", or asking about "serverless containers", "GPU compute", "batch processing", "scheduled jobs", "autoscaling ML"
Use BEFORE and AFTER running trading engine simulations. Helps with: (1) SETUP - choosing configs, selecting segments via segment collections, batch sizing (recommend 2,000-3,000 runs); (2) EXECUTION - running batch simulations with --collection; (3) ANALYSIS - comprehensive diagnostics after runs. Triggers on: 'run simulations', 'test configs', 'batch simulation', 'analyze sim results', 'which configs to test', 'how many segments', 'simulation setup'.
Implement Documenso rate limiting, backoff, and request throttling patterns. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for Documenso. Trigger with phrases like "documenso rate limit", "documenso throttling", "documenso 429", "documenso retry", "documenso backoff".
Optimize Daft UDF performance. Invoke when user needs GPU inference, encounters slow UDFs, or asks about async/batch processing.
>
Convert Mermaid code blocks in .mmd or .md files to animated GIFs with customizable animation styles (progressive, highlight walk, pulse flow, wave).
Use when batch-resolving approved todos, especially after code review or triage sessions
Batch create professional certificates with customizable templates for courses, achievements, and awards. Supports CSV input and PDF export.
Generate whiteboard hand-drawn animation videos from images. Convert any color image into an animation consisting of two stages: line art drawing and coloring, with hand overlay effect, output H.264 MP4 video. Supports both single and batch modes. Triggered when users say "turn the picture into a whiteboard animation", "whiteboard animation", "batch whiteboard animation".
Run fact-grounded image generation batches for short-form video production, especially persona images, first-frame candidates, and light consistency edits. Use this when persona and concept inputs already exist and you need local image assets, prompt records, and reusable model-call metadata. This skill should stay anchored to benchmark-backed persona locks and should save both raw provider responses and normalized local asset manifests.
Extract frames from videos at specific timestamps or intervals, find best frames, and generate thumbnail grids for previews.
Expert in creating, editing, and automating Word documents (.docx) using python-docx and docx.js. Use when generating Word documents, modifying existing docx files, or automating document workflows.