evo-memory

Maintain persistent research memory across ideation and experimentation cycles.

425|44|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/EvoScientist/EvoSkills --skill evo-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evo-memory
Source: https://github.com/EvoScientist/EvoSkills/tree/main/skills/evo-memory
Command: npx skills add https://github.com/EvoScientist/EvoSkills --skill evo-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

Keeps persistent research memory across ideation and experimentation cycles, enabling knowledge continuity, faster cycle starts, and better decision-making by recalling past directions, experiments, and outcomes.

Core Features & Use Cases

  • Two memory stores: Ideation Memory (M_I) for feasible and unsuccessful directions, and Experimentation Memory (M_E) for data-processing and model-training strategies.
  • Three evolution mechanisms: IDE (Idea Direction Evolution) after ideation, IVE (Idea Validation Evolution) after experiments, and ESE (Experiment Strategy Evolution) after successful pipelines.
  • Reading memory at cycle start to seed ideation and guide experiments; pruning and version tracking to maintain memory hygiene; generation of evolution reports to justify memory updates.
  • Memory integration points with other skills to improve search, planning, and execution across cycles.

Quick Start

Load M_I and M_E from the memory directory and initialize IDE, IVE, and ESE triggers for a new research cycle.

Frequently Asked Questions about evo-memory

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

FAQPage Schema
How do I maintain persistent research memory across ideation and experimentation cycles?

Persistent research memory is maintained by loading two stores, Ideation Memory and Experimentation Memory, at the start of each cycle to recall past directions, data-processing strategies, and outcomes for knowledge continuity.

What is the best way to prune outdated ideas during iterative research?

Pruning outdated ideas uses protocol-driven updates and version tracking within the Ideation Memory store to maintain memory hygiene, ensuring only feasible directions are retained for future ideation cycles.

How do evolution reports guide future research experiments?

Evolution reports justify memory updates after ideation and experiments by applying three evolution mechanisms, tracking which idea directions and experiment strategies succeeded or failed to guide future work.

Can I track successful model-training strategies across multiple research cycles?

Successful model-training strategies are tracked using the Experimentation Memory store and the Experiment Strategy Evolution mechanism, which records effective pipelines for cross-cycle knowledge reuse.

Does ideation memory work with experimentation memory for cross-cycle knowledge reuse?

Ideation Memory and Experimentation Memory work together through integration points, seeding ideation and guiding experiments based on past outcomes to achieve cross-cycle knowledge reuse.

When do I need to trigger idea validation evolution in my research pipeline?

Idea Validation Evolution is triggered after experiments are completed, updating the memory stores with validation outcomes to evolve research directions before the next ideation cycle begins.