blader/claudeception
Overview
This skill implements a continuous learning system that extracts reusable knowledge from work sessions and codifies it into new Claude Code skills. It watches for non-obvious debugging, workarounds, project-specific patterns, and workflow optimizations, then creates focused, verifiable skills to speed future work. The goal is autonomous improvement: capture only high-value, tested knowledge and surface it when relevant.
How this skill works
During or after tasks the skill inspects conversation history, error patterns, and problem/solution traces to identify candidate knowledge. It applies quality gates (reusability, specificity, verification) then structures new skills with clear triggers, step-by-step solutions, verification steps, and references. It can be invoked explicitly via commands or automatically after non-trivial discoveries.
When to use it
- After non-obvious debugging that took significant investigation
- When you discover a repeatable workaround or integration technique
- When you encounter misleading errors whose root cause/fix is non-obvious
- When project-specific conventions or configurations are uncovered
- At session end with
/continuous-learningto review and extract learnings
Best practices
- Be selective: extract only reusable, non-trivial, and verified knowledge
- Document exact trigger conditions (error messages, symptoms, contexts)
- Search official docs and recent best practices when the topic is technology-specific
- Prefer concise, action-oriented descriptions that enable semantic matching
- Update or merge with existing skills rather than duplicating content
Example use cases
- Capture a fix for a cryptic build error that required a specific config change
- Create a skill describing how to integrate a library with a local monorepo
- Save a verified sequence of diagnostic steps that reveal a misleading runtime error
- Extract a workflow optimization that shortens repetitive deployment steps
- Produce a skill advising where to check logs when server-side errors appear silent
FAQ
I apply quality gates: the knowledge must be reusable, non-trivial, specific, and verified. If it fails one of these, I skip extraction or add it to a candidate list.
Do you perform web research before creating a skill?
Yes when the topic involves external tools, frameworks, or evolving best practices. I search official docs and recent resources to verify and cite recommendations; I skip web research for strictly project-specific discoveries.
4 skills
This skill continuously extracts reusable knowledge from work sessions and creates Claude Code skills to improve future tasks.
This skill helps you resolve Prisma connection pool exhaustion in serverless environments by guiding pooling, limits, and singleton patterns to prevent P2024
This skill helps you debug Next.js server-side errors in getServerSideProps and getStaticProps by guiding you to terminal logs and robust handling.
This skill helps you extract reusable knowledge from work sessions and codify it into Claude Code skills for continuous learning.
