Compound Learnings

by parcadei

Compound Learnings is an AI Engineering skill for Claude Code, published by parcadei in Continuous-Claude-v3.

3.9K stars296 forkson parcadei/Continuous-Claude-v3Added 2026/08/16Repository updated 2026/01/26

View source on GitHub Download repo ZIP

agentsclaude-codeclaude-code-cliclaude-code-hooksclaude-code-mcpclaude-code-skillsclaude-code-subagentsclaude-skillsmcp

Install in seconds

Install Compound Learnings

Copy Compound Learnings into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/compound-learnings ~/.claude/skills/compound-learnings

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/parcadei/Continuous-Claude-v3.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/compound-learnings/SKILL.md in parcadei/Continuous-Claude-v3
Installs to: ~/.claude/skills/compound-learnings
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Compound Learnings does

Compound Learnings analyzes session learning files to extract recurring patterns, then proposes and creates permanent capabilities such as rules, skills, hooks, and agent updates. Use it when asked to improve setup, compound learnings, or turn session patterns into reusable artifacts.

Compound Learnings is cataloged under AI Engineering on DirSkills. Compound Learnings comes from a repository tagged agents, claude-code, claude-code-cli, claude-code-hooks and claude-code-mcp.

Documentation

README

Excerpt

Compound Learnings

Transform ephemeral session learnings into permanent, compounding capabilities.

When to Use

"What should I learn from recent sessions?"
"Improve my setup based on recent work"
"Turn learnings into skills/rules"
"What patterns should become permanent?"
"Compound my learnings"

Process

Step 1: Gather Learnings

# List learnings (most recent first)
ls -t $CLAUDE_PROJECT_DIR/.claude/cache/learnings/*.md | head -20

# Count total
ls $CLAUDE_PROJECT_DIR/.claude/cache/learnings/*.md | wc -l

Read the most recent 5-10 files (or specify a date range).

Step 2: Extract Patterns (Structured)

For each learnings file, extract entries from these specific sections:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Compound Learnings

What else does parcadei publish alongside Compound Learnings?
Compound Learnings is one of 25 skills that DirSkills catalogs from parcadei/Continuous-Claude-v3, the repository it ships in. Its siblings there include AST-Grep Find, Agent Context Isolation and Agent Orchestration. Each one is a separate skill with its own page in this directory, installs the same way Compound Learnings does, and is maintained by parcadei in that same repository. The rest of the collection is listed on the parcadei/Continuous-Claude-v3 page.
How does Compound Learnings compare to other AI Engineering skills?
Compound Learnings ranks #560 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Compound Learnings against them. Open each page to compare what they document and how they install.