skills.rest
nhatnguyen1122
nhatnguyen1122COMMUNITY
Explore all skills by this author →
GitHub

context-loader

Searches and injects relevant memories into agent context before starting a task.

Updated Jun 29, 2026
Search Tags:#context#recall#search#agent#memory#session#mem0
One-click install
npx skills add https://github.com/nhatnguyen1122/Agent-Memory-Eval --skill context-loader-nhatnguyen1122
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: context-loader
Source: https://github.com/nhatnguyen1122/Agent-Memory-Eval/tree/main/mem0/integrations/pi-agent-plugin/skills/context-loader
Command: npx skills add https://github.com/nhatnguyen1122/Agent-Memory-Eval --skill context-loader-nhatnguyen1122

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When starting a new task or switching topics, an AI agent lacks awareness of past decisions, preferences, and lessons stored in long-term memory, forcing users to repeat context manually. ## Core Features & Use Cases - Parallel Memory Search: Runs 2-4 parallel queries against the mem0 memory store using different angles such as topic, people, and project references. - Deduplicated Context Block: Merges results by memory ID and outputs a compact block of up to 10 memories tagged by type (decisions, preferences, lessons). - Silent-on-Empty Behavior: Produces no output when no relevant memories exist, avoiding noise in the conversation. - Use Case: At the start of a session about a specific project, the Skill automatically loads prior architectural decisions and user preferences so the agent continues work with full background. ## Quick Start Ask the agent to load context for a topic, for example: load what we know about the billing service refactor before we continue.

Frequently Asked Questions about context-loader

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

FAQPage Schema
How do I load past memories into an AI agent's context?▼

Run parallel search queries against the mem0 memory store using different angles such as topic, people, and project names, then deduplicate results by memory ID. The Skill outputs a compact block of up to 10 relevant memories tagged by type.

How to search mem0 memories before starting a task?▼

Extract topics from the current message, then call the mem0_memory tool with action set to search across 2-4 query angles. Merge and deduplicate the results, keeping only the most relevant memories.

Does context-loader modify or delete stored memories?▼

No, the Skill is strictly read-only. It only performs search operations and never modifies or deletes memories in the store.

What happens when no relevant memories are found?▼

The Skill outputs nothing when searches return zero results. It stays silent rather than announcing empty context, keeping the conversation free of noise.

What are the limitations of memory-based context loading?▼

Results are capped at 10 memories, so very broad topics may lose older relevant entries. It also skips memories already visible in the current session and depends on search query quality for coverage.

Related Skills

Explore More Software Engineering Skills→
mem0aimem0ai
64.5k

remember

Stores user-provided text verbatim into Mem0 with automatic category classification.

Official
Basic
hiddink-aihiddink-ai
1

memory-save

Save session context with tasks, decisions, and code changes to claude-mem.

Official
Intermediate
swarm-ai-researchswarm-ai-research

Memory Flush

Promote recent Aeon logs into MEMORY.md, resolve contradictions, and decay stale details.

Official
Advanced
peterlianpipeterlianpi
1

Zolai RAG Builder

Create document embeddings and index them in a vector store for retrieval-augmented generation.

Community
Advanced