From ecc
Automatically extract reusable patterns from Heiba Claude Code sessions and save them as learned skills for future use.
npx claudepluginhub darklegend5/heiba-claude-codeThis skill uses the workspace's default tool permissions.
Automatically evaluates Heiba Claude Code sessions on end to extract reusable patterns that can be saved as learned skills.
Audits UI buttons and touchpoints by tracing state changes in handlers to find canceling side effects, race conditions, and inconsistent final states after refactors or for user-reported bugs.
Provides ClickHouse patterns for MergeTree schemas, query optimization, aggregations, window functions, joins, and data ingestion for high-performance analytics.
Orchestrates multi-agent coding tasks via Claude DevFleet: plans projects into mission DAGs, dispatches parallel agents to isolated git worktrees, monitors progress, and retrieves structured reports.
Automatically evaluates Heiba Claude Code sessions on end to extract reusable patterns that can be saved as learned skills.
~/.claude/skills/learned/This v1 skill is still supported, but continuous-learning-v2 is the preferred path for new installs. Keep v1 when you explicitly want the simpler Stop-hook extraction flow or need compatibility with older learned-skill workflows.
This skill runs as a Stop hook at the end of each session:
~/.claude/skills/learned/Edit config.json to customize:
{
"min_session_length": 10,
"extraction_threshold": "medium",
"auto_approve": false,
"learned_skills_path": "~/.claude/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 ~/.claude/settings.json:
{
"hooks": {
"Stop": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "~/.claude/skills/continuous-learning/evaluate-session.sh"
}]
}]
}
}
/learn command - Manual pattern extraction mid-sessionHomunculus v2 takes a more sophisticated approach:
| Feature | Our Approach | Homunculus v2 |
|---|---|---|
| Observation | Stop hook (end of session) | PreToolUse/PostToolUse hooks (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 |
Key insight from homunculus:
"v1 relied on skills to observe. Skills are probabilistic—they fire ~50-80% of the time. v2 uses hooks for observation (100% reliable) and instincts as the atomic unit of learned behavior."
See: docs/continuous-learning-v2-spec.md for full spec.