1.1K skills · sorted by relevance
Manage how context, the text supplied to an AI, is compressed with RTK filters. Preview compression on real prompts, validate and install filter files, and inspect filter loading diagnostics.
Audit website images and guide conversion to WebP and AVIF, formats that reduce image transfer size. Identify affected files, add fallback images, and review dimensions and loading behavior alongside the impact on initially visible content.
Audit JavaScript page redirects, confirm their impact on loading time with performance measurements, and identify where server-side 301 or 302 redirects can replace them. Get specific findings and an explanation of loading and search indexing concerns.
Audit a page’s HTTP requests to find unnecessary network activity behind slow loading. Confirm bottlenecks with performance measurements, then suggest changes such as combining files, grouping icons, or embedding resources needed for the initial display.
Review website images and reduce file sizes while limiting visible quality changes. Check compression, formats, display dimensions, loading behavior, and delivery settings, then recommend suitable tools or build automation and verification in browser DevTools.
Review HSTS, a browser policy that keeps site connections on HTTPS. Check response headers, policy duration, and subdomain coverage, guide server or CDN configuration, and explain the precautions needed before enabling browser preloading.
Investigate chains of dependent resource requests that delay a page’s first display. Use performance measurements to identify bottlenecks, then reduce waiting by embedding essential CSS or preloading important assets discovered late in the chain.
Audit page speed in a real browser to find delays in loading, script execution, and layout. Use measured results to identify bottlenecks, compare device and connection conditions, and guide performance improvements.
Review large JavaScript bundles to find code that can load later. Suggest dynamic imports, which load modules when needed, and page-level splitting, with loading states for heavy libraries and features outside the initial view.
Review CSS loading that delays a page’s first visible content. Help inline essential styles and defer other stylesheets, using preload and media conditions, while checking rendered layouts at different screen widths and interaction states.
Review the loading order of CSS and JavaScript to address rendering delays and flashes of unstyled content. Suggest changes to the document head, script loading, and critical styles, while checking layouts across screen sizes and interaction states.
Audit browser caching to reduce repeated downloads when people revisit a site. Check cache headers for static files and HTML pages, then suggest suitable storage durations and validation settings based on measured loading problems.
Review links and external resources for domains that ad blockers commonly block. Find navigation and loading failures, test behavior with uBlock Origin, and suggest direct links, self-hosted scripts, or server-side forwarding where appropriate.
Review external integration points for breaking changes that could disrupt existing use. Examine app-server APIs, command-line parameters, configuration loading, and session resumption from saved records, continuing beyond the first issue to cover possible failure paths.
Design how an AI agent finds and loads tools as needed. Compare discovery approaches, organize large tool collections, and assess tool selection accuracy, token costs, and cache reuse without placing every tool definition in the initial context.
Manage Zotero reference libraries through Python: search, create, update, and delete references, organize collections and tags, upload PDF attachments, and export citation data. Guidance covers both remote libraries and access through a running local Zotero app.
Plan and review PufferLib reinforcement learning workflows, where agents learn through rewards. Covers version-specific environment checks, parallel execution, training and evaluation plans, plus checkpoint inspection before loading saved models.
Use PathML for local pathology image research, from loading whole-slide images and splitting them into tiles to preprocessing and quality checks. Plan multiplex measurements, analyze spatial relationships between cells, and run model inference in bounded batches.
Build and check clinical machine learning workflows with PyHealth, from loading electronic health records, signals, or images to training and evaluation. Includes patient-level data splits, prediction task checks, model checkpoints, and medical code mapping.
Analyze Neuropixels neural recordings with SpikeInterface, from loading and preprocessing to motion correction and spike sorting, which separates signals by neuron. Calculate quality metrics, review candidate units, and export plots and data for further inspection.
Guide Angular development, code review, and refactoring with prioritized performance rules. Review rendering efficiency, loading time, and bundle size—the amount of code delivered to browsers—alongside data fetching and server-rendered page setup.
Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.
Reconstruct frontend behavior from served JavaScript, build manifests, and source maps, which link built code to source. Trace loaded modules, recover route and API references, and identify the smallest asset sequence that explains observed behavior.
Build Next.js applications with App Router patterns for page structure, data fetching, caching, and progressive page loading. Covers server and browser component responsibilities, route design, Server Actions, and migration from Pages Router.