Journey - Persistent Learning Logs

VerifiedSafe

Create or read session learning logs that persist institutional memory across Claude Code sessions. Helps preserve decisions, patterns, and learnings beyond a single session. Useful after completing significant work or discovering important insights.

Sby Skills Guide Bot
DocumentationBeginner
6/2/2026
Claude Code
#session-logs#learning-logs#institutional-memory#claude-code

Recommended for

Automated summary

Creates or reads session learning logs that persist institutional memory across Claude Code sessions.

Strengths

  • Preserves context and rationale for future sessions.
  • Structured format with tags and cross-links.
  • Tracks codebase evolution and decisions over time.
  • Goes beyond git by explaining why changes were made.

Limitations

  • Requires manual input after each significant session.
  • Tied to Claude Code (not portable to other tools).
  • Does not automatically capture code changes.
When to use it

After completing significant work, discovering important patterns, making architectural decisions, or fixing non-trivial bugs.

When not to use it

For trivial changes or when a simple git commit suffices, as the writing overhead is not justified.

Security analysis

Safe
Quality score95/100

This skill only writes structured learning logs to a project's `.claude/journeys/` directory, uses safe file operations (Read, Write, Glob), and has no network access or destructive commands. No security concerns.

No concerns found

How this analysis is made

Examples

Create journey after fixing a bug
/journey Fixed critical authentication bug in login flow
List all existing journeys
/journey --list
Read a specific journey
/journey --read 2026-02-20-fixed-auth-bug.md

name: journey updated: 2026-02-20 description: Create session learning logs that persist institutional memory across Claude Code sessions. user-invocable: true allowed-tools: Read, Write, Glob, Bash

Journey Skill

Create or read session learning logs that persist institutional memory across Claude Code sessions.

When to Use

Use /journey when:

  • After completing significant work in a session
  • After discovering important patterns or learnings
  • After making architectural decisions
  • After fixing non-trivial bugs
  • When the session contains knowledge worth preserving

Commands

Create New Journey

/journey {title}

Creates a new journey file with a summary of the current session.

List Journeys

/journey --list

Shows all existing journeys.

Read Journey

/journey --read {filename}

Reads a specific journey file.

Show Recent

/journey --recent

Shows the 5 most recent journeys.

Journey File Format

Journeys are saved to .claude/journeys/ with naming: YYYY-MM-DD-{slug}.md

Template Structure

# Journey: {Title}

**Date:** YYYY-MM-DD
**Tags:** #tag1 #tag2 #tag3

## Summary

1-3 sentences describing what was accomplished and why it matters.

## What Was Done

1. **First major item**
   - Details
   - More details

2. **Second major item**
   - Details

## Key Learnings

- **Learning 1**: Explanation with context
- **Learning 2**: Explanation with context

## Files Changed

| File | Change |
|------|--------|
| `path/to/file.ts` | Brief description |

## Patterns Discovered

### Pattern Name
\`\`\`code
// Example code showing the pattern
\`\`\`

## Decisions Made

| Decision | Rationale |
|----------|-----------|
| Choice made | Why it was made |

## Connected To

- Related skills, files, or future work

Writing Guidelines

Summary

  • Be concise but specific
  • Mention the "why" not just the "what"
  • Future Claude sessions should understand the context

Key Learnings

  • Focus on insights that prevent future mistakes
  • Include code patterns when relevant
  • Explain the "gotcha" moments

Tags

Common tags:

  • #bugfix - Bug fixes
  • #feature - New features
  • #refactor - Code restructuring
  • #tooling - Build/dev tooling
  • #performance - Performance work
  • #meta - Claude Code/skills work
  • #architecture - Architectural decisions
  • #security - Security-related work

Purpose

Journeys create institutional memory that:

  1. Helps future sessions avoid repeating mistakes
  2. Documents decisions and their rationale
  3. Preserves patterns and best practices
  4. Tracks the evolution of the codebase

Unlike git commits (which track what changed), journeys track why and what was learned.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/journey-persistent-learning-logs-mm8o51zu/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/journey-persistent-learning-logs-mm8o51zu' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/journey-persistent-learning-logs-mm8o51zu/download' --output '.skill-downloads/journey-persistent-learning-logs-mm8o51zu/SKILL.md.part' && mv '.skill-downloads/journey-persistent-learning-logs-mm8o51zu/SKILL.md.part' '.skill-downloads/journey-persistent-learning-logs-mm8o51zu/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Write, Glob, Bash

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/journey-persistent-learning-logs-mm8o51zu/SKILL.md' && test -s '.skill-downloads/journey-persistent-learning-logs-mm8o51zu/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/journey' && cp -R '.skill-downloads/journey-persistent-learning-logs-mm8o51zu' '.claude/skills/journey'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/journey-persistent-learning-logs-mm8o51zu'

openskills read 'journey-persistent-learning-logs-mm8o51zu'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/journey-persistent-learning-logs-mm8o51zu/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills