Automatically extracts reusable patterns like error resolutions and workarounds from Claude Code sessions via Stop hook and saves as learned skills.
npx claudepluginhub saar120/skillgate-registry --plugin everything-claude-codeThis skill uses the workspace's default tool permissions.
Automatically evaluates Claude Code sessions on end to extract reusable patterns that can be saved as learned skills.
Writes articles, guides, blog posts, tutorials, and newsletters in a voice from examples or brand guidance. For polished long-form content with structure, pacing, and credibility.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Executes repo commands, inspects git state, debugs CI failures, and pushes narrow fixes with exact proof of execution and verification. Use for command runs, repo checks, or evidence-based changes.
Automatically evaluates Claude Code sessions on end to extract reusable patterns that can be saved as learned skills.
~/.claude/skills/learned/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.