This skill should be used when the user asks about "session learning", "learn from session", "improve future sessions", "session reflection", "session metrics", "session analysis", "/session-reflect", "req learning", "learning updates", "rollback learning", or wants to understand how Claude Code can get smarter over time by learning from sessions.
View on GitHubHarmAalbers/claude-requirements-framework
requirements-framework
plugins/requirements-framework/skills/session-learning/SKILL.md
January 25, 2026
Select agents to install to:
npx add-skill https://github.com/HarmAalbers/claude-requirements-framework/blob/main/plugins/requirements-framework/skills/session-learning/SKILL.md -a claude-code --skill session-learningInstallation paths:
.claude/skills/session-learning/# Session Learning Guide
The session learning system helps Claude Code improve over time by analyzing your sessions and suggesting updates to memories, skills, and commands.
## Quick Start
### Enable Session Learning
Add to your `.claude/requirements.yaml` or `.claude/requirements.local.yaml`:
```yaml
hooks:
session_learning:
enabled: true
prompt_on_stop: true # Prompts for review when ending session
```
### Review a Session
```bash
/session-reflect # Full analysis with recommendations
/session-reflect quick # Quick summary statistics
/session-reflect analyze-only # Analysis without applying changes
```
### Manage Learning
```bash
req learning stats # Show learning statistics
req learning list # List recent updates
req learning rollback 3 # Undo update #3
req learning disable # Disable learning for this project
```
## How It Works
### 1. Data Collection
During your session, the framework collects metrics:
- **Tool usage**: Which tools you use, how often, which files
- **Requirement flow**: What gets blocked, how long to satisfy
- **Errors**: What errors occur and how they're resolved
- **Skills/Agents**: Which skills and agents you run
Metrics are stored in `.git/requirements/sessions/<session_id>.json`.
### 2. Pattern Analysis
When you run `/session-reflect`, the session-analyzer agent looks for:
- **Workflow patterns**: Common sequences, TDD cycles, etc.
- **Friction points**: High time-to-satisfy, repeated blocks
- **Knowledge gaps**: Repeated lookups, error patterns
- **Automation opportunities**: Manual steps that could be automated
### 3. Recommendations
Based on analysis, the system suggests:
- **Memory updates**: Add project conventions to Serena memories
- **Skill updates**: Improve trigger patterns
- **Command updates**: Add frequently used arguments
Each recommendation has a confidence score (0-1).
### 4. User Approval
You review and select which recommendations to apply. All changes are:
-