Results for “wrapper”

Work on the Android app — the thin WebView wrapper in `android/`. Use this whenever a task touches the Kotlin sources, the Gradle build, the WebView shell, the native settings screen, LMS server auto-discovery, the JS↔native bridge, app strings/i18n, or the Android CI/lint. Covers the "shell only, UI lives on the web" principle, the debug/release signing split, the static versioning F-Droid needs, and the min/target SDKs, so changes fit the wrapper.

The English summary is being prepared. Showing the original description.

You know AI wrappers get a bad rap, but the good ones solve real problems. You build products where AI is the engine, not the gimmick. You understand prompt engineering is product development. You balance costs with user experience. You create AI products people actually pay for and use daily.

The English summary is being prepared. Showing the original description.

Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS.

The English summary is being prepared. Showing the original description.

Build Java applications with tinystruct, including actions usable from both a terminal and the web. Get guidance on launcher generation, routing, JSON responses, database storage, tests, and MCP tools that agents can call.

• Build actions for both terminal and web use
• Generate missing project launcher scripts
• Implement JSON APIs and database storage

Research United States patents and trademarks using official USPTO records. Find patents, check application and trademark status, review examination documents and ownership transfer records, and keep search logs so findings can be checked and reproduced.

• Search patents by company, inventor, date, or classification
• Check patent application status and examination records
• Retrieve trademark status and documents

Investigate unreliable AI agents across 12 layers, including instructions, memory, tool execution, and display. Use code and logs to trace failures, rank findings by severity, and produce an ordered repair plan that prioritizes code changes.

• Investigating failures that appear only inside an agent application
• Tracing old conversation content leaking into new sessions
• Checking skipped or falsely claimed tool execution

Audit scheduled jobs, hooks, MCP servers, and external integrations using configuration files, logs, and recent runs. Distinguish configured tools from verified working ones, identify failures or overlap, and recommend what to keep, merge, remove, or fix next.

• Checking which automations are actually working
• Identifying broken jobs and authentication failures
• Finding duplicate hooks, scripts, and integrations

Use OpenAI Codex CLI to review code changes, challenge an implementation by looking for ways it could fail, or discuss technical questions. Three modes provide an independent opinion, with follow-up questions supported in ongoing consultations.

• Get an independent review of code changes
• Challenge code to uncover possible failures
• Continue a technical consultation with follow-up questions

Manage code changes across multiple AI agents and record their operations and outcomes. Use those records to find successful patterns, review past failures, and get suggestions for similar development or deployment tasks.

• Coordinate code changes across multiple AI agents
• Get deployment suggestions from past results
• Review failures from similar merge attempts

Review custom tabs, menus, lists, and similar controls for required ARIA child roles, which describe interface elements to assistive technology. Identify missing roles and structural wrappers that prevent screen readers from recognizing the items.

• Reviewing the structure of custom tabs and menus
• Investigating items missing from screen reader output
• Checking lists and selectors built with div or span elements

Read, analyze, modify, and visualize molecular structures with RDKit in Python. Calculate molecular properties, search for similar structures or specific structural patterns, apply reaction rules, and generate 2D or 3D coordinates with detailed control over processing.

• Calculating properties for a collection of molecules
• Searching for molecules with similar structures
• Filtering molecules by specific structural patterns

Process molecular datasets in Python through a simpler interface to RDKit, a chemistry toolkit. Convert and standardize structures, calculate molecular properties, compare and cluster compounds, generate 3D conformations, and visualize results for drug discovery workflows.

• Load and standardize molecular datasets
• Calculate molecular properties and similarities
• Cluster compounds and select diverse subsets

Generate client libraries for REST APIs, with authentication, retries, typed request and response models, error classes, and pagination helpers. Language-specific patterns and usage examples show how applications can call API resources.

• Create a Python client for a REST API
• Generate TypeScript request and response types
• Standardize retries and API error handling

Helps design focused AI products built on APIs such as OpenAI and Anthropic. Covers product strategy, prompts, model selection, user experience, usage tracking, and cost management for tools aimed at solving specific customer problems.

• Planning an AI SaaS product for a specific problem
• Designing prompts for product features
• Balancing model choices, costs, and user experience

Build cryptocurrency exchange integrations in Rust with CCXT. Follow examples for fetching prices and order books, placing orders, streaming live updates through WebSocket connections, and handling authentication and errors with typed results.

• Fetching exchange prices and order books in Rust
• Building order placement and cancellation workflows
• Streaming live prices through WebSocket connections

Get instructions for installing and reviewing the full ai-ready skill in Copilot CLI. This wrapper explains how to add the latest version, reload skills, and request repository preparation for AI contributions.

• Install the full skill in Copilot CLI
• Review the skill before loading it
• Update an existing skill installation

Simplify bloated AI-generated code by removing dead code, duplicated logic, and unnecessary layers while checking that existing behavior stays intact. Use a limited cleanup scope, verify changes with relevant checks, or request a review without edits.

• Removing duplicate logic and unused code
• Simplifying unnecessary wrappers without changing behavior
• Cleaning up only a specified set of changed files

Send questions, review requests, or implementation tasks to a supported local AI command-line tool through one shared command. The wrapper handles provider-specific options and saves the result as a Markdown file for later reference.

• Requesting a security review of a patch
• Seeking UX suggestions for a user flow
• Drafting an implementation plan for an issue

Clean up working code by identifying duplication, dead code, unnecessary layers, and error paths that hide failures. Preserve behavior with targeted tests, simplify the requested files in stages, and report verification results and remaining risks.

• Simplify bloated or repetitive AI-generated code
• Remove unused code and unnecessary wrappers
• Review fallback paths that hide errors

Research recommended practices for a chosen technology using official documentation and maintainer sources. Get a cited recommendation that explains version context, local project constraints, uncertainties, and the next steps for planning or implementation.

• Check official guidance for a chosen technology
• Research version-specific migration advice
• Gather evidence before implementation planning

Guide server-side Zoom integrations using Zoom Rivet SDK in JavaScript or TypeScript. Consult patterns for authentication, incoming event notifications, typed API calls, multiple modules, and webhook processing on AWS Lambda.

• Implementing Zoom authentication and token handling
• Building a Team Chat bot with API integration
• Combining multiple Zoom modules in one server

Embed Zoom meetings in an Electron desktop app using the Meeting SDK. The skill guides developers through initialization, token-based authentication, joining and starting meetings, settings controls, and integration with raw meeting data.

• Embed Zoom meetings in an Electron app
• Design authentication and meeting entry flows
• Organize SDK services, controllers, and events

Guide Zoom Virtual Agent integration into websites and mobile apps, covering embedded chat, conversation startup and cleanup, and handoff to live support. It also directs developers to platform references and knowledge-base synchronization workflows.

• Embed a support bot on a website
• Wrap web chat in an Android or iOS app
• Implement handoff from a bot to live support

Run final checks on reviewed SDK changes, covering code formatting, linting for code issues, type checking, and tests. Confirm completion only after every required check succeeds, with wrappers for macOS, Linux, and Windows.

• Verify runtime code changes after review
• Run final checks after test or build configuration changes
• Rerun required checks after fixing a failure