complexity-class-oracle
Classify problems into complexity classes with supporting evidence and proof strategies
Profile →npx skills add a5c-ai/babysitter --skill complexity-class-oracle --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Complexity Class Oracle ## Purpose Provides expert guidance on classifying computational problems into complexity classes and understanding class relationships. ## Capabilities - Determine membership in P, NP, co-NP, PSPACE, EXPTIME - Identify complete problems for each class - Query known complexity results database - Suggest proof strategies for classification - Generate complexity landscape diagrams - Explain class inclusions and separations ## Usage Guidelines 1. **Problem Characterization**: Formalize the computational problem 2. **Class Investigation**: Check membership in relevant classes 3. **Evidence Collection**: Gather evidence for classification 4. **Strategy Selection**: Choose proof strategy for membership 5. **Documentation**: Generate classification report ## Tools/Libraries - Complexity Zoo database - Diagram generation - LaTeX documentation
- Purpose
- Capabilities
- Usage Guidelines
- Tools/Libraries
What does the complexity-class-oracle skill do?
Classify problems into complexity classes with supporting evidence and proof strategies
How do I install it?
Run `npx skills add a5c-ai/babysitter --skill complexity-class-oracle --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From a5c-ai/babysitter, a repository with 1,642 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.