Specific rules for Starknet React projects, focusing on blockchain integration.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Skipping chain ID validation | Wallet connected to wrong network silently corrupts transactions | Always validate chainId matches expected Starknet network |
| Hardcoding contract addresses | Breaking changes when deploying to different environments | Use environment variables or config files for all contract addresses |
| Missing transaction state handling | Users see blank UI during pending/rejected states | Implement loading, confirmed, and rejected state for all transactions |
| Direct ABI calls without TypeScript types | Runtime errors from wrong argument types | Use TypeScript types generated from ABI for all contract calls |
| Ignoring wallet connection errors | Silent failures create confusing UX | Always handle ConnectionError, UserRejectedRequestError, and RejectedRequestError |
Before starting:
cat .claude/context/memory/learnings.md
After completing: Record any new patterns or exceptions discovered.
ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
The English summary is being prepared. Showing the original description.
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
The English summary is being prepared. Showing the original description.
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
The English summary is being prepared. Showing the original description.
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
The English summary is being prepared. Showing the original description.
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
The English summary is being prepared. Showing the original description.
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
The English summary is being prepared. Showing the original description.