Extracts and saves reusable knowledge and coding patterns from the current session.

Install

mkdir -p .claude/skills/learn-naj2r && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18178" && unzip -o skill.zip -d .claude/skills/learn-naj2r && rm skill.zip

Installs to .claude/skills/learn-naj2r

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Extract reusable knowledge from this session and save to persistent memory or new skills
88 charsno explicit “when” trigger
Beginner

Key capabilities

  • Identify and save user corrections from the session
  • Extract and store successful or failed coding patterns
  • Record data quirks and Stata/R translation issues
  • Document user workflow and communication style preferences
  • Save general learnings to MEMORY.md
  • Create new skill patterns in .claude/skills/

How it works

The skill reviews the current session for corrections, patterns, and preferences, then categorizes and writes this reusable knowledge to appropriate persistent memory locations or new skill files.

Inputs & outputs

You give it
The current session conversation, optionally with a specific topic focus
You get back
Updated memory files (MEMORY.md, .claude/rules/stata-r-conventions.md, backmatter chapter) or new skill files

When to use learn

  • Saving session learnings
  • Persisting coding patterns
  • Storing user preferences

About this skill

Learn

Extract reusable knowledge from the current session and persist it for future sessions.

Input: $ARGUMENTS — optional topic focus. If blank, review the full session.

What to Extract

Corrections ([LEARN] tags)

Look for any [LEARN:category] tags in the conversation where the user corrected Claude. Save as:

[LEARN:category] wrong assumption → correct behavior

Patterns

  • Coding patterns that worked well or failed
  • Data quirks that will recur (e.g., {{data source}} missing value format)
  • Stata/R translation gotchas encountered
  • File path conventions that are easy to get wrong

Preferences

  • User workflow preferences discovered during the session
  • Communication style preferences
  • Tool usage patterns

Where to Save

TypeLocation
General learningsMEMORY.md (update, don't duplicate)
Stata-specific.claude/rules/stata-r-conventions.md
Data-specificRelevant backmatter chapter (93 for problems)
New skill patternCreate new skill in .claude/skills/

Process

  1. Review the session for corrections, discoveries, and patterns
  2. Check existing memory — don't duplicate what's already stored
  3. Categorize each learning (correction, pattern, preference, skill)
  4. Write to appropriate location
  5. Report what was saved and where

Quality Gates

  • Don't save speculative conclusions from a single interaction
  • Don't save session-specific context (current task, temp state)
  • Do save stable patterns confirmed across multiple observations
  • Do save explicit user requests ("always do X", "never do Y")

When not to use it

  • When saving speculative conclusions from a single interaction
  • When saving session-specific context or temporary state
  • When the information is already stored in memory

Limitations

  • It does not save speculative conclusions from a single interaction
  • It does not save session-specific context or temporary state
  • It only saves stable patterns confirmed across multiple observations or explicit user requests

How it compares

This skill systematically extracts and categorizes specific types of reusable knowledge from a session for persistence, unlike manual note-taking which may lack structure or consistent storage.

Compared to similar skills

learn side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
learn (this skill)05moNo flagsBeginner
notion-knowledge-capture108moNo flagsIntermediate
history-insight06moReviewBeginner
log06moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

notion-knowledge-capture

makenotion

Transforms conversations and discussions into structured documentation pages in Notion. Captures insights, decisions, and knowledge from chat context, formats appropriately, and saves to wikis or databases with proper organization and linking for easy discovery.

10115

history-insight

team-attention

This skill should be used when user wants to access, capture, or reference Claude Code session history. Trigger when user says "capture session", "save session history", or references past/current conversation as a source - whether for saving, extracting, summarizing, or reviewing. This includes any mention of "what we discussed", "today's work", "session history", or when user treats the conversation itself as source material (e.g., "from our conversation").

02

log

dev-whitecrow

기록 스킬. 중요한 의사결정이나 순간을 Decision_Log나 History에 빠르게 기록합니다.

00

distill

dev-whitecrow

정제 스킬. Inbox의 날것의 생각(Raw Data)을 읽어 분석하고, 이를 The_Ark의 적절한 위치에 구조화하여 배치합니다. 온보딩 단계에 따라 다르게 작동합니다.

00

wiki-fileback

GYF0311

把对话中产生的洞察/决策/事实按主语写回 corpus,追加 timeline 或新建页面。触发词:记一下、存下来、笔记、把刚才那个放进去、fileback、存回知识库。

00

paper-connections-session-summary

IcyChlorine

Update durable workflow/docs and write a new Paper Connections session summary for the current worktree. Use near session close-out when the user asks to summarize lessons learned, create a new session summary, or says `总结沉淀`.

00

Search skills

Search the agent skills registry