compound-learnings
Extract patterns from recent sessions and convert them into persistent capabilities—rules for heuristics, skills for workflows, and hooks for automation. The skill guides you through gathering learnings, consolidating similar patterns, detecting meta-themes, and proposing artifacts with appropriate signal thresholds before creation.
Compound Learnings transforms recurring patterns from your sessions into permanent rules, skills, and hooks.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-01-26
Compound Learnings transforms recurring patterns from your sessions into permanent rules, skills, and hooks. Extract patterns from recent sessions and convert them into persistent capabilities—rules for heuristics, skills for workflows, and hooks for automation. The skill guides you through gathering learnings, consolidating similar patterns, detecting meta-themes, and proposing artifacts with appropriate signal thresholds before creation.
Use it when
- compound-learnings analyzes your session history to identify which recurring techniques and workflows merit permanence.
- compound-learnings consolidates learnings from recent work into structured proposals for new artifacts.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
parcadei/Continuous-Claude-v3/compound-learnings · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I turn session learnings into permanent skills?
compound-learnings guides you through converting recurring patterns from your work sessions into durable capabilities. Start by gathering learnings from recent sessions, then consolidate similar patterns to identify what repeats. The skill helps you detect meta-themes across those patterns and propose the right artifact type—rules for heuristics, skills for workflows, or hooks for automation—each with appropriate signal thresholds before creation.
What patterns should become permanent in my setup?
compound-learnings analyzes your session history to identify which recurring techniques and workflows merit permanence. It examines what you've done repeatedly, extracts actionable insights, and helps you distinguish between one-off solutions and genuine patterns worth automating. The skill then suggests the optimal artifact type—whether a rule, skill, agent enhancement, or hook—to capture each pattern effectively.
How do I compound my learnings into reusable capabilities?
compound-learnings consolidates learnings from recent work into structured proposals for new artifacts. It extracts reusable techniques, detects meta-patterns across your sessions, and generates recommendations for rules, skills, agents, and hooks. Each proposal includes signal thresholds to help you decide when the pattern is strong enough to implement as a permanent capability in your setup.
Can compound-learnings identify meta-patterns in my work?
Yes. compound-learnings detects meta-patterns by analyzing learnings across multiple sessions and recognizing themes that span different contexts. It consolidates similar insights, identifies underlying principles, and determines which patterns are significant enough to become permanent. This meta-level analysis helps you see not just what you did, but why it worked and how to systematize it.
How does compound-learnings help me improve my setup?
compound-learnings improves your setup by transforming ephemeral session insights into compounding capabilities. It gathers learnings, extracts patterns, analyzes what should become automated, and proposes new rules, skills, agents, and hooks with appropriate thresholds. This systematic approach ensures your best practices stick permanently rather than being rediscovered in each session.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
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:
| Section Header | What to Extract |
|---|---|
## Patterns or Reusable techniques |
Direct candidates for rules |
(truncated - see the full file via the links below)
File tree — 1 file
.claude/skills/compound-learnings/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Transform recurring session patterns into permanent rules, skills, and hooks”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Skill Developer is a meta-skill for building new Claude Code skills from the ground up or converting existing scripts. It provides templates, step-by-step guidance for wrapping MCP pipelines, and configuration patterns to enable Claude's automatic skill discovery.
Wiring ensures your infrastructure components are reachable and actually execute when needed. It guides you through verifying entry points, tracing call paths from trigger to execution, testing end-to-end flows, and eliminating orphaned modules—preventing dead code and wasted effort.
Skill Developer is a comprehensive guide for creating and managing Claude Code skills with auto-activation. It covers skill structure, YAML frontmatter, trigger types, enforcement levels, hook mechanisms, and the 500-line rule. Use it when building new skills, modifying skill-rules.json, debugging activation issues, or implementing progressive disclosure patterns.
lab:autoresearch runs a self-improving loop that mutates plugin skills one change at a time, scores each against deterministic criteria, and commits improvements while reverting failures. Target the weakest skill or run a full sweep overnight with /loop.
self-learn captures patterns, failures, and decisions from substantial sessions, scores them for generality and confidence, then proposes targeted framework updates—from project-specific steering rules to cross-cutting framework changes. It's the mechanism that lets your framework evolve from real usage, surfacing diffs for approval before any changes apply.
Master the architecture of workflow-based skills through essential principles covering phased execution, tool alignment, progressive disclosure, and scalable patterns. This guide teaches you how to structure multi-step processes with numbered phases, entry/exit criteria, and appropriate freedom levels for each task type.
More skills skill-generator (MIT)