skills.rest
krbylit
krbylitCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

lavra-knowledge

Append solved problems as JSONL entries to .lavra/memory/knowledge.jsonl.

1|Updated Jan 11, 2025
Search Tags:#automation#recall#memory#knowledge#jsonl#bead
One-click install
npx skills add https://github.com/krbylit/dotfiles --skill lavra-knowledge
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: lavra-knowledge
Source: https://github.com/krbylit/dotfiles/tree/main/cm-util/pkg-backups/lavra/0.7.0/skills/lavra-knowledge
Command: npx skills add https://github.com/krbylit/dotfiles --skill lavra-knowledge

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Capture solved problems as structured JSONL entries in .lavra/memory/knowledge.jsonl and log bead comments to build a searchable knowledge base that auto-recall can inject into future sessions.

Core Features & Use Cases

  • Append-only JSONL entries for every solved problem to enable fast recall.
  • Bead comments logging for traceability back to work items.
  • Auto-recall integration at session start to surface relevant knowledge.
  • Use of five prefixes: LEARNED, DECISION, FACT, PATTERN, INVESTIGATION.

Quick Start

After confirming a solution, run the lavra-knowledge capture to append a knowledge entry to .lavra/memory/knowledge.jsonl and log a bead comment.

Frequently Asked Questions about lavra-knowledge

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

FAQPage Schema
How do I capture solved problems into a searchable knowledge base for future recall?▼

You can capture solved problems by appending structured JSONL entries to a memory file. This records solutions with specific prefixes and bead comments for traceability, enabling fast recall across sessions.

What are the five knowledge prefixes used for structuring memory entries?▼

The five knowledge prefixes are LEARNED, DECISION, FACT, PATTERN, and INVESTIGATION. They categorize solved problems in the JSONL knowledge base to enable precise auto-recall filtering.

How does auto-recall integration work with JSONL knowledge storage?▼

Auto-recall integration surfaces relevant knowledge at session start by reading the stored JSONL memory entries. This injects previously captured solutions directly into your current working session.

Can I use bead comments for traceability back to specific work items?▼

Yes, bead comments log alongside JSONL memory entries to provide traceability back to work items. This optional bead-backed traceability links captured knowledge directly to its originating task.

Is append-only JSONL storage suitable for cross-session knowledge management?▼

Append-only JSONL storage is designed for cross-session knowledge management. It continuously accumulates solved problems without modifying past entries, ensuring a stable and searchable history.

When should I document a solution as a structured JSONL entry?▼

You should document a solution as a structured JSONL entry immediately after confirming it works. This captures the problem resolution while context is fresh for future auto-recall.

Related Skills

Explore More Software Engineering Skills→
kssuminkssumin

memory-distill

Distill episodic lessons from failures.jsonl and decisions.jsonl into permanent skills and rules.

Community
Advanced
Signet-AISignet-AI
237

recall

Query persistent memories using hybrid vector and keyword search.

Official
Intermediate
krbylitkrbylit

beads-knowledge

Document solved problems as categorized JSONL entries in .beads/memory/knowledge.jsonl.

Community
Advanced
dawsonblockdawsonblock

llm-wiki

Manageable workflows require manageable inputs. Manage your virtual machine inventory with ease by leveraging this powerful tool.

Community
Advanced