MCP App StoreMCP App Store
from prompt-cache-skills107
Automatically enables prompt caching for supported models in the Continue agent, reducing input costs and improving latency.
This skill provides a set of patches to flip the default prompt caching behavior in the Continue IDE extension from opt-in to enabled. It ensures that supported models (like Claude via Anthropic or Bedrock) utilize prompt caching by default, significantly reducing token costs for multi-turn conversations.
Use this skill when you want to optimize the performance and cost of a Continue installation, specifically for users who are unaware of the manual configuration required to enable caching.
Anthropic.ts and Bedrock.ts to change the default caching strategy to systemAndTools and auto-enable conversation message caching.cache_control markers are being sent and cache reads are occurring.Continue
This skill has not been reviewed by our automated audit pipeline yet.
Claude Code (Clawdbot)
Wrapper to run the local Claude Code CLI in headless or interactive (tmux) modes for code analysis, refactors, tests, and structured output.
Anthropic Security Basics
Practical security practices for Anthropic Claude integrations: API key management, input validation, prompt-injection defenses, and output scanning.
Portfolio Optimization
Select and balance project portfolios using constraint-based mathematical optimization to maximize value under budget, resource, and strategic constraints.
Debugging
Tools and API patterns to diagnose and improve agent matchmaking, profiles, and conversations on inbed.ai for better compatibility and engagement.
ABAP Performance — HANA
ABAP performance best-practices for SAP S/4HANA: push data-intensive work to HANA, use CDS/AMDP, and prefer set-based SQL over ABAP loops.
Image to 3D Pipeline
Convert 2D images into optimized, rigged 3D models (GLB/FBX) and animations using Hunyuan3D, Mixamo and cleanup tools — fast pipeline for web and game assets.
Rspack Guidance
Comprehensive guidance for configuring, using, and migrating to Rspack (a fast Webpack-compatible bundler), including examples and troubleshooting.
Model Deployment (SageMaker & Bedrock)
Generates deployment code and a Jupyter notebook to deploy LoRA fine-tuned Nova or OSS models (from SageMaker Serverless Model Customization) to SageMaker endpo