Agent skill
continuous-learning-v2
Instinct-based pattern learning with confidence scoring and auto-evolution
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/continuous-learning-v2-erp-core-dev-eagles-claude-config
SKILL.md
Continuous Learning v2
Overview
Captures atomic behavioral patterns (instincts) from session activity via hooks. Each instinct has a confidence score (0.3-0.9) that increases with repetition and decays when contradicted.
Commands
-
- View learned patterns with confidence scores
-
- Export instincts as JSON for team sharing
-
- Import instincts from teammate
-
- Cluster related instincts into reusable skills/commands
How It Works
Capture Pipeline
Instinct Format
Confidence Scoring
| Score | Meaning | Action |
|---|---|---|
| 0.3-0.4 | Weak signal | Observe only |
| 0.5-0.6 | Emerging pattern | Suggest in context |
| 0.7-0.8 | Strong pattern | Auto-apply |
| 0.9+ | Established behavior | Promote to skill |
Evolution Pipeline
When 3+ related instincts reach 0.7+ confidence:
- Cluster by category/domain
- Generate skill draft from instinct descriptions
- Present for human review
- If approved, create skill .md file in skills/ directory
Stack Context
- .NET 8: Watch for CosmosDB patterns, GDPR anonymization, French HR terms
- React 18: Watch for Redux Toolkit patterns, Ant Design usage, French labels
- Azure: Watch for AKS deployment patterns, Key Vault usage
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?