vibeeval/continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
npx skills add https://github.com/vibeeval/vibecosystem --skill continuous-learning-v2An advanced learning system that turns your Claude Code sessions into reusable knowledge through atomic "instincts" - small learned behaviors with confidence scoring.
| Feature | v1 | v2 |
|---------|----|----|
| Observation | Stop hook (session end) | PreToolUse/PostToolUse (100% reliable) |
| Analysis | Main context | Background agent (Haiku) |
| Granularity | Full skills | Atomic "instincts" |
| Confidence | None | 0.3-0.9 weighted |
| Evolution | Direct to skill | Instincts → cluster → skill/command/agent |
| Sharing | None | Export/import instincts |
An instinct is a small learned behavior:
---
id: prefer-functional-style
trigger: "when writing new functions"
confidence: 0.7
domain: "code-style"
source: "session-observation"
---
# Prefer Functional Style
## Action
Use functional patterns over classes when appropriate.
## Evidence
- Observed 5 instances of functional pattern preference
- User corrected class-based approach to functional on 2025-01-15
Properties:
Session Activity
│
│ Hooks capture prompts + tool use (100% reliable)
▼
┌─────────────────────────────────────────┐
│ observations.jsonl │
│ (prompts, tool calls, outcomes) │
└─────────────────────────────────────────┘
│
│ Observer agent reads (background, Haiku)
▼
┌─────────────────────────────────────────┐
│ PATTERN DETECTION │
│ • User corrections → instinct │
│ • Error resolutions → instinct │
│ • Repeated workflows → instinct │
└─────────────────────────────────────────┘
│
│ Creates/updates
▼
┌─────────────────────────────────────────┐
│ instincts/personal/ │
│ • prefer-functional.md (0.7) │
│ • always-test-first.md (0.9) │
│ • use-zod-validation.md (0.6) │
└─────────────────────────────────────────┘
│
│ /evolve clusters
▼
┌─────────────────────────────────────────┐
│ evolved/ │
│ • commands/new-feature.md │
│ • skills/testing-workflow.md │
│ • agents/refactor-specialist.md │
└─────────────────────────────────────────┘
Add to your ~/.claude/settings.json.
If installed as a plugin (recommended):
{
"hooks": {
"PreToolUse": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/skills/continuous-learning-v2/hooks/observe.sh pre"
}]
}],
"PostToolUse": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/skills/continuous-learning-v2/hooks/observe.sh post"
}]
}]
}
}
If installed manually to ~/.claude/skills:
{
"hooks": {
"PreToolUse": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh pre"
}]
}],
"PostToolUse": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "~/.claude/skills/continuous-learning-v2/hooks/observe.sh post"
}]
}]
}
}
The Python CLI will create these automatically, but you can also create them manually:
mkdir -p ~/.claude/homunculus/{instincts/{personal,inherited},evolved/{agents,skills,commands}}
touch ~/.claude/homunculus/observations.jsonl
/instinct-status # Show learned instincts with confidence scores
/evolve # Cluster related instincts into skills/commands
/instinct-export # Export instincts for sharing
/instinct-import # Import instincts from others
| Command | Description |
|---------|-------------|
| /instinct-status | Show all learned instincts with confidence |
| /evolve | Cluster related instincts into skills/commands |
| /instinct-export | Export instincts for sharing |
| /instinct-import <file> | Import instincts from others |
Edit config.json:
{
"version": "2.0",
"observation": {
"enabled": true,
"store_path": "~/.claude/homunculus/observations.jsonl",
"max_file_size_mb": 10,
"archive_after_days": 7
},
"instincts": {
"personal_path": "~/.claude/homunculus/instincts/personal/",
"inherited_path": "~/.claude/homunculus/instincts/inherited/",
"min_confidence": 0.3,
"auto_approve_threshold": 0.7,
"confidence_decay_rate": 0.05
},
"observer": {
"enabled": true,
"model": "haiku",
"run_interval_minutes": 5,
"patterns_to_detect": [
"user_corrections",
"error_resolutions",
"repeated_workflows",
"tool_preferences"
]
},
"evolution": {
"cluster_threshold": 3,
"evolved_path": "~/.claude/homunculus/evolved/"
}
}
~/.claude/homunculus/
├── identity.json # Your profile, technical level
├── observations.jsonl # Current session observations
├── observations.archive/ # Processed observations
├── instincts/
│ ├── personal/ # Auto-learned instincts
│ └── inherited/ # Imported from others
└── evolved/
├── agents/ # Generated specialist agents
├── skills/ # Generated skills
└── commands/ # Generated commands
When you use the Skill Creator GitHub App, it now generates both:
Instincts from repo analysis have source: "repo-analysis" and include the source repository URL.
Confidence evolves over time:
| Score | Meaning | Behavior |
|-------|---------|----------|
| 0.3 | Tentative | Suggested but not enforced |
| 0.5 | Moderate | Applied when relevant |
| 0.7 | Strong | Auto-approved for application |
| 0.9 | Near-certain | Core behavior |
Confidence increases when:
Confidence decreases when:
> "v1 relied on skills to observe. Skills are probabilistic—they fire ~50-80% of the time based on Claude's judgment."
Hooks fire 100% of the time, deterministically. This means:
v2 is fully compatible with v1:
~/.claude/skills/learned/ skills still work*Instinct-based learning: teaching Claude your patterns, one observation at a time.*
Take vibeeval/continuous-learning-v2 from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.