Continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /aiception command, (2) 'save this as a skill' or 'extract a skill from this', (3) 'what did we learn?', (4) after non-obvious debugging or trial-and-error discovery. Creates new skills when valuable reusable knowledge is identified. Integrates with Open Brain to prevent duplicates.
A continuous learning system that extracts reusable knowledge from work sessions and codifies it into new skills. This enables autonomous improvement over time.
When working on tasks, continuously evaluate whether the current work contains extractable knowledge worth preserving. Not every task produces a skill. Be selective about what's truly reusable and valuable.
Extract when you encounter:
Before extracting, verify:
Before creating anything, check if this knowledge already exists:
search_thoughts({ "query": "[keywords from the discovery]", "match_count": 5 })
| Search Result | Action |
|---|---|
| Strong match found | Update the existing skill instead of creating new |
| Partial match | Create new, add "See also" cross-reference |
| No match | Create new |
Search local skill directories for related skills:
Look in:
.claude/skills/ (project-level)
~/.claude/skills/ (user-level)
| Found | Action |
|---|---|
| Nothing related | Create new |
| Same trigger, same fix | Update existing (bump version) |
| Same trigger, different cause | Create new, link both ways |
| Partial overlap | Update existing with new variant subsection |
When the topic involves specific technologies or tools, search the web for current documentation and best practices before creating the skill. Include a References section if external sources were consulted. Skip this for project-specific internal patterns.
---