ai-sdk
Vercel AI SDK reference for building AI-powered applications. Use when implementing text/object generation (generateText, streamText, generateObject, streamObject), building chatbots with useChat/useCompletion...
Découvrez les skills Documentation, comparez leurs dépôts et consultez leurs instructions.
Vercel AI SDK reference for building AI-powered applications. Use when implementing text/object generation (generateText, streamText, generateObject, streamObject), building chatbots with useChat/useCompletion...
Complete workflow for verifying and committing Brane SDK changes. Run after implementing fixes/features to verify impact, test affected modules, and prepare for commit.
Systematic approach to debugging Brane SDK issues. Use when diagnosing transaction failures, RPC errors, encoding mismatches, or unexpected behavior.
Analyze change impact and discover affected tests. Use after making changes to understand what depends on the modified code, find relevant tests, and determine what to run.
Update Javadoc and public documentation after implementing features. Use when finishing implementation to ensure both internal (Javadoc) and external (website docs) documentation are accurate and complete.
Review Brane SDK code for correctness, Java 21 patterns, type safety, and architectural consistency. Use when reviewing PRs, checking code changes, or validating implementations against Brane standards.
Research EVM SDK patterns from viem (TypeScript) and alloy (Rust) when designing Brane features. Use when implementing new functionality, designing APIs, or solving problems that other SDKs have already address...
Has guidelines for creating Mermaid diagrams and fixing its syntax errors. Use this before creating or updating Mermaid diagrams.
Use when initiating new features, complex code changes, or technical research tasks that require structured planning and documentation before implementation.
Instructions for reviewing changes using subagents. Use after implementation and verification are complete
Guidelines for a writing style that's concise and direct. aka High density language, HD style Use for writing/editing prompts, artefact documents, TDD, PRD, discovery documents, research, AGENTS.md, and more.
Guidelines for Plan Mode - focus on planning before implementation
Gives guidelines on how to explain code with call graphs and pseudocode. Invoke this when creating code explanations. Common user requests: - "Explain {feature or function}" - "Show me how {feature} works" - "C...
Write solution options documents to evaluate and compare different technical approaches with trade-off analysis Common user requests: - "Evaluate options for [problem]" - "Compare [solution A] vs [solution B]"...
Refine an implementation
Get alternative perspectives on a plan
Guidelines for automated and manual verification of code changes. When to use: - After making code changes to ensure correctness As part of the implementation workflow
Use when executing implementation plans from planning phase to verified completion
tbd
Analyse and review a pull request
Distill learnings into improvements for the skills and AGENTS.md instructions
Guidelines for documenting work in a changelog artefact after implementing and verifying work
Refine a plan
Create hierarchical, bottom-up "layered summaries" by generating `AGENTS.md` files per directory in a subtree (e.g., `reth/crates/engine`). Deep directories summarize files and key APIs; parent directories roll...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.