713 skills · sorted by relevance
Add a live adjustment panel to an HTML page so viewers can explore colors, text sizes, spacing, themes, and motion. Changes appear immediately and are saved in the browser for the next visit.
Improve an AI agent's harness, the software that organizes its work, while keeping the model fixed. Test changes in a sandbox, measure their results, and retain variants that pass tests and demonstrate improvement.
Configure a RuView sensing deployment, including WiFi settings, detection thresholds, processing on devices, and coordinated nodes. It covers device provisioning, server options, firmware variants, and Cognitum Seed integration to adjust how the system operates.
Browse and search OmniRoute's AI model catalog from the command line. Filter by provider or capability, check model aliases, validate compatible models before adding them, and maintain manually registered model details.
Audit website image file sizes against guidelines for photos, graphics, hero images, and thumbnails. Report oversized assets with target sizes, distinguish compression issues from dimension mismatches, and guide format conversion and delivery of smaller variants to mobile devices.
Read, query, filter, and write genomic files with pysam in Python. Extract regions, summarize variants, and count aligned bases while handling coordinate conventions, file indexes, headers, and the reference sequences needed to decode CRAM files.
Plan an A/B test to compare product changes, with a clear hypothesis, variants, sample estimates, and tracking checks. Define success metrics and stopping rules before launch, then document results and decisions.
Prepare GRPO reinforcement learning configurations for tasks with programmatically checkable answers, such as math, code, and structured output. Design and inspect reward functions, then select training variants when runs show instability or exploit flaws in scoring.
Resolve a design question by building a temporary, runnable prototype. Explore logic through clickable scenarios or compare three structurally different interface variants, then record the user's decision while keeping the prototype separate from production code.
Combine capabilities from multiple fine-tuned LLMs without retraining using mergekit. Choose a merging method, configure how models are blended, and evaluate the resulting model on tasks such as math, code generation, and conversation.
Run nf-core workflows on local sequencing files or public GEO/SRA datasets to analyze gene expression, genetic variants, or chromatin accessibility. The skill guides environment checks, sample table preparation, workflow configuration, execution, and output verification.
Turn a product description into a landing page with headlines, feature sections, pricing, FAQs, and calls to action. Receive Next.js/React components styled with Tailwind CSS, plus search metadata, structured data, and alternative copy.
Inspect and edit Figma files through JavaScript using the Plugin API. Create shapes, text, reusable components, and design variables, then check structure and screenshots as changes are made in small steps.
Update NemoClaw documentation after merged changes or audit it for outdated guidance. Verify current behavior against source and tests, edit the pages responsible for that guidance, and check affected links and generated variants.
Create paid-ad images from a validated creative brief and brand profile using a configured image provider. Check dimensions, text consistency, and platform requirements, then save approved variants with a manifest recording generation details and costs.
Find other occurrences of a known bug across a codebase by tracing its root cause. Gradually broaden search patterns, assess matching candidates, assign severity, and document findings with rules to help prevent recurrence.
Retrieve genes, genetic variants, clinical annotations, and dosing guidelines from the PharmGKB API, then turn the results into concise summaries. Save the full response when you need the underlying data.
Plan or run targeted DNA panel analysis using UMIs, barcodes that identify DNA molecules. Organize consensus reads, coverage checks, and low-frequency variant results with molecular support, filtering reasons, and explicit quality limitations.
Look up species information and archived genetic variants in the European Variation Archive. Uses focused API requests to return concise Markdown summaries, with raw JSON available when structured data is needed for further processing.
Create and maintain Code Connect templates that link published Figma components to existing code components. Map text, variants, visibility settings, and nested components so the displayed code snippets reflect the selected design properties.
Create and maintain Code Connect templates that link published Figma components to existing code components. Map text, variants, toggles, and nested components so code examples reflect the selected component's design settings.
Use JavaScript through Figma's Plugin API to inspect file structure and edit design elements, components, variables, and layouts. Follow incremental steps with font loading, returned element IDs, and visual checks to validate changes.
Build or update a Figma design system to match a codebase. Organize reusable design values, light and dark themes, component variants, and documentation, then check component structure, appearance, and bindings to those values.
Analyze successful Google and Meta ads to find useful patterns in headlines, body text, and calls to action. Generate new copy variants that preserve those patterns, with platform formatting, test priorities, and suggested pairings for comparison.