Runs scripts to scan your current session for repeatable patterns and turn them into new rules or skills.
Install
mkdir -p .claude/skills/learn-jubakitiashvili && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14695" && unzip -o skill.zip -d .claude/skills/learn-jubakitiashvili && rm skill.zipInstalls to .claude/skills/learn-jubakitiashvili
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.
Manual skill generation — runs continuous-learning-v2 scripts to extract patterns from sessionKey capabilities
- →Scan recent tool calls and file changes
- →Identify patterns like repeated fixes or style corrections
- →Compare identified patterns against existing rules and skills
- →Generate candidates for new skills or rule amendments
- →Validate new content for valid frontmatter and conflicts
How it works
This skill runs a script to analyze the current coding session, extracting reusable patterns from tool calls and file changes, then generates candidates for new skills or rule amendments.
Inputs & outputs
When to use learn
- →Generate a skill from repetitive tasks
- →Extract coding patterns into rules
- →Validate new skill content
About this skill
/learn — Generate Skills from Session
You are executing the /learn command. This is script-driven — it runs the continuous-learning-v2 pipeline directly.
What This Does
Analyzes the current coding session to extract reusable patterns and save them as skills or rule amendments for future sessions. This is the manual trigger for what PostToolUse hooks do automatically.
Process
- Run the extraction script:
node .claude/hooks/scripts/extract-session-patterns.js
This script:
- Scans recent tool calls and file changes
- Identifies patterns (repeated fixes, style corrections, common architectures)
- Compares against existing rules and skills
- Generates candidates for new content
- Review candidates: The script outputs a list of potential learnings:
[PATTERN] Zustand store always uses immer middleware → Suggest rule amendment
[PATTERN] All screens use SafeAreaView wrapper → Suggest coding-style rule
[PATTERN] API calls always retry 3 times → Suggest pattern rule
[SKILL] Complex form validation flow → Suggest skill creation
- Approve or reject each candidate: For each candidate, decide:
- Approve → Script writes to
.claude/rules/or.claude/skills/ - Reject → Skip this pattern
- Edit → Modify before saving
- Validate new content:
node .claude/hooks/scripts/validate-content.js
Ensures new rules/skills have valid frontmatter and don't conflict with existing content.
When to Use
- After a long coding session where you established new patterns
- When you notice yourself repeatedly making the same corrections
- After integrating a new library and establishing conventions
- Periodically to capture accumulated project knowledge
Note
The automatic PostToolUse hook (continuous-learning-v2.cjs) does lightweight extraction after every tool call. This /learn command runs a comprehensive analysis that catches patterns the real-time hook might miss.
When not to use it
- →When the task is a creation task like writing a tweet
- →When the task is a processing task like summarizing an article
Limitations
- →Requires manual approval or rejection of each candidate.
- →New content must have valid frontmatter.
- →New content must not conflict with existing content.
How it compares
This skill provides a manual, complete analysis of coding patterns for skill generation, unlike the lightweight, real-time extraction performed by PostToolUse hooks.
Compared to similar skills
learn side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| learn (this skill) | 0 | 4mo | Review | Intermediate |
| universal-learner | 2 | 7mo | No flags | Intermediate |
| skills-discovery | 1 | 7mo | Review | Beginner |
| command-development | 16 | 9mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by JubaKitiashvili
View all by JubaKitiashvili →You might also like
universal-learner
huangserva
通用学习器 - 从任何领域的Prompt中自动提取可复用元素，持续学习和积累知识
skills-discovery
Kamalnrf
Search for and install Agent Skills that give you specialized capabilities. Before starting work, ask might a skill exist that handles this better than my base knowledge? If the task involves specific technologies, frameworks, file formats, or expert domains. Search proactively, even if the user doesn't mention skills. Skills encode best practices, tools, and techniques you wouldn't otherwise have. Also use when users explicitly ask to find, install, or manage skills.
command-development
anthropics
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
prompt-optimize
YYH211
Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.
prpm-development
pr-pm
Use when developing PRPM (Prompt Package Manager) - comprehensive knowledge base covering architecture, format conversion, package types, collections, quality standards, testing, and deployment
ai-cost-optimizer
ScientiaCapital
Save 40-70% on AI costs with intelligent multi-LLM routing. Automatically selects the optimal model based on task complexity across 40+ models from 8 providers.