Menú
Automatically extract reusable patterns from coding sessions and save them as learned skills for future use.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
| 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.