Menu
Automatically extract reusable patterns from coding sessions and save them as learned skills for future use.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | continuous-learning |
| description | Automatically extract reusable patterns from coding sessions and save them as learned skills for future use. |
Automatically evaluates coding sessions on end to extract reusable patterns that can be saved as learned skills.
This skill runs as a sessionEnd hook at the end of each session:
~/.copilot/skills/learned/{
"min_session_length": 10,
"extraction_threshold": "medium",
"auto_approve": false,
"learned_skills_path": "~/.copilot/skills/learned/",
"patterns_to_detect": [
"error_resolution",
"user_corrections",
"workarounds",
"debugging_techniques",
"project_specific"
],
"ignore_patterns": [
"simple_typos",
"one_time_fixes",
"external_api_issues"
]
}
| Pattern | Description |
|---|---|
error_resolution | How specific errors were resolved |
user_corrections | Patterns from user corrections |
workarounds | Solutions to framework/library quirks |
debugging_techniques | Effective debugging approaches |
project_specific | Project-specific conventions |
Add to your .github/hooks/default.json:
{
"version": 1,
"hooks": {
"sessionEnd": [{
"type": "command",
"bash": "scripts/hooks/evaluate-session.sh"
}]
}
}
| Feature | v1 (This Skill) | v2 (Instinct-Based) |
|---|---|---|
| Observation | sessionEnd hook (end of session) | preToolUse/postToolUse (continuous) |
| Analysis | Main context | Background analysis |
| Granularity | Full skills | Atomic "instincts" |
| Confidence | None | 0.3–0.9 weighted |
| Evolution | Direct to skill | Instincts cluster into skills/commands/agents |
See continuous-learning-v2 for the instinct-based approach.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
Pattern for progressively refining context retrieval to solve the subagent context problem in multi-agent workflows.
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
Universal coding standards, best practices, and patterns for C#, ASP.NET Core, and Entity Framework Core development.
Formal evaluation framework for coding sessions implementing eval-driven development (EDD) principles.
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.