MCP App StoreMCP App Store
from domain-driven-design-skills34
Compare Gemini File API vs Inline document approaches to optimize performance, caching, and document upload strategies.
This skill provides a comprehensive framework for benchmarking the performance of Gemini AI models when handling documents. It specifically compares two primary methods of data ingestion: the File API (uploading once and reusing cached URIs) and Inline delivery (sending raw bytes with every request).
Use this skill when optimizing LLM performance for document-heavy workloads, determining the break-even point for caching documents via the File API, or auditing token usage and query latency in production-like scenarios.
-docs, -rounds, -max-docs) and interpreting key metrics like speedup factors and break-even analysis.Designed for agents with Bash and Read capabilities, specifically those integrating with the Gemini API (e.g., Gemini CLI, custom AI agents).
This skill has not been reviewed by our automated audit pipeline yet.
Convex Component Authoring
Guide for creating and publishing self-contained, reusable Convex components with proper isolation and dependency management.
Java Concurrency Expert
Applies modern Java concurrency best practices, from Virtual Threads and Structured Concurrency to deadlock avoidance.
Cloverleaf Ledger Downloader
Downloads ledger transactions from the Cloverleaf property management portal as CSV files.
GitHub Runner Setup & Maintenance
Manage self-hosted GitHub Actions runners with dedicated user isolation and systemd integration.
Python Testing Practices
Comprehensive guide for modern Python testing, including property-based testing with Hypothesis and fuzzing with Atheris.
Technical History Researcher
Specialized research for open source project histories, developer biographies, and technical community archives.
Jest Test Generator
Automatically generates comprehensive Jest unit tests for JavaScript and TypeScript modules, including mocks and edge cases.
QA Fixes Applicator
Systematically applies prioritized fixes for high-severity issues, NFR failures, and test coverage gaps identified during quality reviews.
Root Cause Analysis Analyst
An evidence-based methodology for isolating true root causes from contributing factors using a rigorous three-test isolation process.
Quality Lead (TotalAud.io)
Specialist for testing and validation, focusing on test suite execution, mobile UX standards, and accessibility checks for the TotalAud.io workspace.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Go Data Structures
Authoritative guidance on choosing and using Go built-in and standard-library data structures, with practical best practices for slices, maps, arrays, container
Prompt Engineering Patterns
A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat
AIML Spambot Benchmark (ISC)
Benchmark template for evaluating spam-detection models using anchored spam campaign examples (contains harmful anchoring content).
React Development Expert
Provides authoritative React guidance on hooks, state patterns, Server Components, performance optimization, and common architectural patterns.
Algolia Cost Tuning
Practical guide to reduce Algolia billing by auditing records/requests, switching to virtual replicas, multi-query usage, caching, and cleanup strategies.
Code Mode for MCP Servers
Add a sandboxed code mode tool to an MCP server so LLMs run small processing scripts against large API responses and only the script output enters the model con
Code Reviewer
Perform structured, prioritized code reviews that find correctness, security, performance, reliability, and testing issues and provide concrete fix suggestions.