5.6K skills · sorted by relevance
Build and review interfaces against WCAG 2.2 accessibility guidelines. Covers keyboard navigation, screen readers that read interface content aloud, accessible forms, mobile support, and display preferences, helping identify and fix barriers to using a website or app.
Estimate a venture’s market size using industry reports, customer counts and pricing, or willingness to pay. Organize results into total, serviceable, and realistically obtainable revenue opportunities to support business planning and investor presentations.
Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.
Integrate Zoom Virtual Agent into an iOS app using WKWebView, an embedded web browser. Covers Swift and Objective-C configuration injection, messages exchanged with web content, support handoff handling, and rules for opening links.
Draft customer replies using order details, payment status, support history, and refund policies, matching the owner's writing style. With connected tools, prepare approved refunds and identify Shopify orders that need attention before customers contact support.
Identify what a sales opportunity needs to reach its next stage or close. Use deal records and conversations to map missing requirements, assign owners and deadlines, and sequence the next actions with supporting evidence.
Review a sales opportunity using deal records, emails, and meeting notes. Get an evidence-based assessment of closing likelihood, missing information, risks, and prioritized next steps, with a comparison against the stage recorded in your sales system.
Maintain an application's supported language models by checking provider availability, adding models, and keeping documentation, live tests, and model-specific request settings aligned. It also checks provider model identifiers and candidates for the recommended list.
Analyze SaaS customer data with three Python tools that calculate account health, rank churn risk, and prioritize expansion opportunities. Use repeatable weighted scores to plan customer outreach and prepare quarterly business reviews.
Size support and operations teams using demand ranges and queueing calculations, which estimate how work waits for service. Assess workload imbalance and service target risks, then build a quarterly hiring plan that accounts for training time and attrition.
Check mesh files for 3D printing by measuring geometry and comparing it with process-specific design limits. Get findings on wall thickness, overhangs, and supports, plus build orientation options and concrete redesign guidance.
Find recurring questions in resolved Plain support tickets that existing knowledge articles do not cover. Draft articles from actual resolutions, avoid previously drafted topics, and open a pull request for human review.
Evaluate whether completed experiments support a research claim using a separate Codex reviewer. Identify unsupported conclusions and missing evidence, then determine whether to revise the claim, run additional experiments, or move toward paper writing.
Automate supported Chmeetings tasks through Rube MCP and Composio. Discover available operations, review their required inputs, verify the connection, and execute tasks with shared sessions for related steps and continued retrieval of paginated results.
Sort customer support tickets, emails, and chats into categories and priorities with brief reasons. Draft replies when requested, outline steps to reproduce issues, and prepare internal notes covering missing information, investigation needs, and next actions.
Maintain and validate OpenShell builds for Windows on x64 and ARM64 using MSVC, Microsoft's C++ toolchain. Check compilation, build executables, run tests on native hosts, and report artifacts and unsupported driver behavior.
Check whether a CARLA feature is usable in the current environment and has a verified procedure. Review known failures, inspect build settings, and identify differences between client, server, and source versions before planning work.
Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.
Turn stakeholder requests into measurable goals, customer problems, possible solutions, and experiments. Through guided discussion, compare feasibility, expected impact, and customer fit to choose a proof of concept: a small test of a proposed solution.
Prepare customer-facing teams before announcing a product or feature retirement. Create support FAQs, honest replacement comparisons, objection responses, and escalation guidance, with the scope adjusted from a short support note to a broader training pack.
Estimate the size of a market or business opportunity using traceable sources, explicit assumptions, and inspectable calculations. Compare scenarios, show how changing assumptions affects the estimate, and identify the evidence needed to improve confidence.
Look up an AI agent’s owner and profile using its blockchain identity, find ERC-8004 registry addresses, and generate an AgentCard JSON file describing services, supported trust models, and x402 support for registration.
Build token swaps and transfers within or across blockchains using the LI.FI REST API. Compare routes, prepare transactions, track transfer status, discover decentralized finance yields, and connect swaps or transfers with deposits into supported protocols.
Analyze an Amazon competitor by ASIN, its product identifier, using listing text, keywords, images, and reviews. Identify competitor strengths and unmet buyer needs, then turn those findings into positioning and product opportunities for your brand.