session-learner

anexpn's avatarfrom anexpn

Extract and persist learnings from the current session. This skill should be used when the user wants Claude to analyze the conversation and capture insights, patterns, preferences, or knowledge discovered during work. Triggers on requests like "learn from this session", "what did we learn", or "capture insights".

⭐0stars🔀0forks📁View on GitHub🕐Updated Dec 1, 2025
[Memory and Context Management]

When & Why to Use This Skill

The Session Learner skill empowers Claude to systematically analyze interactions and preserve valuable insights, including user preferences, technical patterns, and project-specific knowledge. By persisting these learnings to configuration files like CLAUDE.md or project documentation, it creates a self-improving feedback loop that enhances agent accuracy, reduces repetitive instructions, and ensures long-term personalization across sessions.

Use Cases

  • User Preference Persistence: Automatically capture and store your specific coding style, communication tone, and tool preferences in a global configuration to ensure Claude stays aligned with your workflow in every new session.
  • Project Knowledge Extraction: Identify and document project-specific architectural decisions, naming conventions, and technical patterns discovered during development, saving them directly to the project's CLAUDE.md for future reference.
  • Agent Failure Analysis: Detect patterns where Claude previously misunderstood instructions or made technical errors, and record 'lessons learned' to prevent the agent from repeating the same mistakes.
  • Workflow Discovery: Analyze successful multi-step manual procedures performed during a conversation and transform them into structured, reusable skills or SOPs.
  • Conflict Resolution & Knowledge Updates: Review existing project documentation against new session insights to identify contradictions, allowing you to merge, replace, or update outdated information seamlessly.
namesession-learner
descriptionExtract and persist learnings from the current session. This skill should be used when the user wants Claude to analyze the conversation and capture insights, patterns, preferences, or knowledge discovered during work. Triggers on requests like "learn from this session", "what did we learn", or "capture insights".

Session Learner

Analyze the current session to extract learnings and persist them to appropriate locations.

Workflow

Step 1: Analyze Session

Review the entire conversation to identify learnings in these categories:

  1. User Preferences - Working style, communication preferences, tool preferences
  2. Agent Failure Patterns - Mistakes Claude made, misunderstandings, approaches that didn't work
  3. Project Technical Patterns - Code patterns, architecture decisions, project-specific conventions
  4. Reusable Workflows - Multi-step procedures that could become skills
  5. Reference Knowledge - Architectural decisions, domain knowledge, API behaviors

Step 2: Categorize by Destination

Map each learning to its appropriate destination:

Learning Type Destination Rationale
User preferences ~/.claude/CLAUDE.md Applies across all projects
Agent failure patterns ~/.claude/CLAUDE.md Prevents repeating mistakes globally
Project technical patterns Project CLAUDE.md Project-specific guidance
Reusable workflows New skill Procedural knowledge for reuse
Reference knowledge Project docs/ folder Documentation for future reference

Step 3: Check for Conflicts

Before presenting findings, check if any learning contradicts existing content:

  1. Read the target file (user CLAUDE.md, project CLAUDE.md, or relevant docs)
  2. Identify any conflicts between new learnings and existing content
  3. Flag conflicts explicitly for user decision

Step 4: Present Findings

Present findings grouped by destination. For each group:

  1. State the destination file path
  2. List each learning with a brief description (1-2 sentences)
  3. If conflicts exist, show:
    • The existing content
    • The proposed new content
    • Ask user to choose: keep existing, replace with new, or merge

Format:

## Learnings for ~/.claude/CLAUDE.md

1. [Brief description of learning]
2. [Brief description of learning]

⚠️ CONFLICT: [description]
   Existing: [current content]
   Proposed: [new content]
   Keep existing / Replace / Merge?

## Learnings for [project]/CLAUDE.md

1. [Brief description of learning]

## Learnings for [project]/docs/

1. [Brief description] → docs/[filename].md

## Potential New Skill

1. [Workflow name]: [brief description]

Step 5: Apply Approved Learnings

After user approves (or modifies) findings:

  1. For CLAUDE.md files: Append to appropriate section, or create section if needed
  2. For docs/: Create or update the markdown file
  3. For new skills: Offer to create using the skill-creator skill

Guidelines

  • Keep learnings concise and actionable
  • Prefer specific examples over abstract principles
  • Do not duplicate information already in target files
  • When uncertain about destination, ask the user to choose
  • Learnings should be evergreen - no temporal references like "today we learned"