Total 51,117 skills
Showing 12 of 51117 skills
ProdPad integration. Manage data, records, and automate workflows. Use when the user wants to interact with ProdPad data.
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
Structured visual QA verdict for screenshot-to-reference comparisons
Workbooks CRM integration. Manage data, records, and automate workflows. Use when the user wants to interact with Workbooks CRM data.
Build, refactor, or review macOS menubar apps that use Tuist and SwiftUI. Use when creating or maintaining LSUIElement menubar utilities, defining Tuist targets/manifests, implementing model-client-store-view architecture, adding script-based launch flows, or validating reliable local build/run behavior without Xcode-first workflows.
Assist developers in writing clean, maintainable code following software engineering best practices. Use when conducting code reviews, refactoring code, enforcing coding standards, seeking guidance on clean code principles, or integrating automated quality checks into development workflows.
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Find LinkedIn profiles of decision makers at target companies using Extruct's company_people_finder. Takes a company table, adds a people finder column, and produces a linked child people table with names, roles, and LinkedIn URLs. No external API credits — uses Extruct's index only. Triggers on: "find linkedin", "find people", "find contacts", "find decision makers", "people search", "linkedin search", "who to contact", "find profiles".
Use when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
Interpret Qwilr engagement signals and decide what to do next. Use when a prospect viewed or didn't view a proposal, analyzing Qwilr analytics, understanding proposal engagement patterns, figuring out why a buyer went dark after a proposal, deciding when to follow up after sending a proposal, understanding read receipts on proposals, or seeing who viewed a Qwilr quote.