Convex Agents Context

Name: Convex Agents Context
Availability: InStock
Author: sstobo

Configure per-call context options for LLM generations with memory injection and cross-thread search.

25|4|Updated Oct 18, 2025

Search Tags:#context #search #LLM #RAG #agents #memory #threading

Ready to run

npx skills add https://github.com/Sstobo/convex-skills --skill convex-agents-context

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Convex Agents Context
Source: https://github.com/Sstobo/convex-skills/tree/main/convex-agents-context
Command: npx skills add https://github.com/Sstobo/convex-skills --skill convex-agents-context

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill customizes what information the LLM receives for each generation by controlling message history, memory injection, cross-thread search, and summarization.

Core Features & Use Cases

Configure per-call context options to tailor prompts for specific tasks.
Enable cross-thread context search to retrieve relevant history across multiple conversations.
Inject memories, profiles, or examples to guide the agent's behavior consistently over time.

Quick Start

Use this skill to tailor the agent's context for multi-thread conversations and memory-aware prompts.

Frequently Asked Questions about Convex Agents Context

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I control LLM context and message history for agents?▼

You can control LLM context by customizing message history, enabling cross-thread search, and injecting memories to tailor the exact information the LLM receives for each generation call.

Can I retrieve relevant context across multiple conversation threads?▼

Yes, cross-thread context search allows you to retrieve relevant history across multiple conversations, ensuring agents have the necessary background information from different threads.

How do I inject memories or profiles to guide agent behavior consistently?▼

You can inject memories, profiles, or examples into the LLM context to guide the agent's behavior consistently over time, tailoring prompts for specific tasks and maintaining continuity.

Is it possible to override context options for individual LLM calls?▼

Yes, you can configure per-call context options to override default settings, allowing you to tailor prompts and context dynamically for specific tasks within multi-thread conversations.

What's the best way to fetch context manually for memory-aware prompts?▼

The skill supports manual context fetch, allowing you to retrieve and customize agent context explicitly for memory-aware prompts in advanced multi-thread conversation setups.

Does this approach support context summarization for LLM agents?▼

Yes, context summarization is supported alongside memory injection and cross-thread search, enabling you to manage and condense the information fed to the LLM for smarter agent responses.