breadcrumb

Classifies and records discovered tools, patterns, and gotchas into Claude's persistent discovery files.

12|2|Updated Jun 8, 2026

Search Tags:#workflow #documentation #discovery #claude #memory #breadcrumb #knowledge-base

Ready to run

npx skills add https://github.com/Loringtonian/second-brain-template --skill breadcrumb-loringtonian

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: breadcrumb
Source: https://github.com/Loringtonian/second-brain-template/tree/main/.claude/skills/breadcrumb
Command: npx skills add https://github.com/Loringtonian/second-brain-template --skill breadcrumb-loringtonian

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill captures newly discovered capabilities, tools, patterns, and gotchas so future Claude instances can find them without rediscovering the same information.

Core Features & Use Cases

Discovery classification: Determines whether a breadcrumb belongs in CLAUDE.md, MEMORY.md, a specific Skill's SKILL.md, or a deeper reference document.
Compact persistence: Adds short, reusable notes in the right discovery layer instead of duplicating full documentation.
Workflow memory: Records verified tools, flags, and implementation patterns so future sessions can apply them consistently.
Use case: After confirming that a CLI flag or workaround is reliable, use this Skill to register it where the next Claude instance will actually see it.

Quick Start

Use the breadcrumb skill to record this verified capability in the most appropriate discovery layer for future Claude instances.

Frequently Asked Questions about breadcrumb

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

FAQPage Schema

How do I persist discovered tools and patterns for future Claude sessions?▼

To persist discovered tools and patterns for future Claude sessions, you register them as compact notes in the correct discovery layer, such as CLAUDE.md or MEMORY.md. This ensures future instances find the verified capabilities without rediscovering them.

What is the best way to save workflow memory and debugging gotchas in Claude?▼

The best way to save workflow memory and debugging gotchas is classifying the discovery and adding a short, reusable note to the appropriate persistent layer. This prevents duplicating full documentation while keeping the knowledge visible across sessions.

How do I record verified CLI flags so the next Claude instance can find them?▼

You record verified CLI flags by capturing them as a breadcrumb in the most appropriate discovery layer. This guarantees the next Claude instance will see the verified workaround and apply it consistently.

When should I write workflow discoveries to CLAUDE.md versus MEMORY.md?▼

You should write workflow discoveries to CLAUDE.md versus MEMORY.md based on layer classification. The skill determines whether a breadcrumb belongs in CLAUDE.md, MEMORY.md, a specific Skill's SKILL.md, or a deeper reference document to ensure careful placement.

Can I use this approach to avoid duplicating existing documentation entries?▼

Yes, you can use this approach to avoid duplicating existing documentation entries. The skill requires compact note formatting and careful placement to ensure newly registered capabilities do not duplicate existing records in the knowledge base.