compile-observations

Extract significant long-term memories from JSONL tool observation buffers.

5|1|Updated Feb 10, 2026
One-click install
npx skills add https://github.com/ehfazrezwan/neuralscape --skill compile-observations
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: compile-observations
Source: https://github.com/ehfazrezwan/neuralscape/tree/main/neuralscape-plugin/skills/compile-observations
Command: npx skills add https://github.com/ehfazrezwan/neuralscape --skill compile-observations

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Raw tool observation logs captured during AI coding sessions are unstructured and discarded after sessions end, leading to the permanent loss of valuable technical insights, decisions, and project context that could improve future work.

Core Features & Use Cases

  • Processes JSONL observation buffers from Claude Code sessions to group related tool actions into coherent work units.
  • Applies a strict quality rubric to filter out low-value noise, retaining only significant insights like technical decisions, bugfixes, recurring patterns, and project conventions.
  • Submits approved memories directly to the Neuralscape memory system via MCP tools for persistent, searchable storage across sessions and projects.
  • Use Case: If you debugged a dependency version conflict and pinned the correct library version during a session, this skill will capture that as a durable memory instead of letting the insight disappear when the session ends.

Quick Start

Invoke the compile-observations skill with the path to your session's JSONL observation buffer to automatically extract and save all significant memories from your recent tool usage.

Frequently Asked Questions about compile-observations

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

FAQPage Schema
How do I extract long-term memories from AI coding session logs?

To extract long-term memories from AI coding session logs, you can process raw JSONL tool observation buffers to filter and retain significant insights like technical decisions, bugfixes, and recurring patterns. This prevents valuable project context from being discarded when sessions end.

How do I save technical decisions and bugfixes from Claude Code sessions permanently?

You can save technical decisions and bugfixes from Claude Code sessions by compiling raw JSONL observation logs into persistent AI memories. Approved insights are submitted directly to the Neuralscape memory system via MCP tools for searchable storage across projects.

Does compile-observations automatically filter out low-value noise from observation buffers?

Yes, compile-observations applies a strict quality rubric to filter out low-value noise from observation buffers. It groups related tool actions into coherent work units and retains only high-value insights like technical decisions, discoveries, and project conventions.

How do I trigger post-session memory compilation for coding assistant tool observations?

Post-session memory compilation for coding assistant tool observations can be triggered by session start, user prompt submission, or manual invocation via the neuralscape:capture command. You invoke the skill with the path to your session's JSONL observation buffer.

What type of technical insights are retained during JSONL session log memory compilation?

During JSONL session log memory compilation, the process retains significant long-term memories such as technical decisions, discoveries, bugfixes, recurring patterns, and project conventions. Low-value noise is filtered out using a defined quality rubric.

Can I use Neuralscape MCP tools to store coding assistant memories across different projects?

Yes, you can use Neuralscape MCP tools to store coding assistant memories across different projects. The skill submits approved memories directly to the Neuralscape memory system, enabling persistent and searchable storage that improves future work across sessions.