Some applications require a flexible chain of calls to LLMs and other tools based on user input. The Agent interface provides the flexibility for such applications. An agent has access to a suite of tools, and determines which ones to use depending on the user input. Agents can use multiple tools, and use the output…
Create a pull request for the aiclientsdart monorepo with proper conventional commit titles, structured descriptions, labels, and assignees. Use this skill whenever the user asks to create a PR, open a pull request, push changes for review, submit changes, or anything related to creating or opening a GitHub pull…
Release Dart packages in the aiclientsdart monorepo. Detects changes since last release, bumps semver, writes changelogs, publishes to pub.dev, creates git tags, and creates a combined GitHub release. Use for releasing packages, publishing, version bumping, or creating releases.
Extract validated review findings from merged PRs and update skill files (checklists, implementation patterns) to prevent recurring issues. Use whenever asked to learn from PR reviews, mine review comments, update review checklists, upskill from past feedback, or improve skills based on code review history — even if…
Instructions for davidmigloz/ai_clients_dart, covering ai clients dart, repository structure, development commands, dart monorepo setup and code quality.
Instructions for davidmigloz/ai_clients_dart, a project described as: A collection of Dart client libraries for popular AI APIs. Provides type-safe, well-documented, and idiomatic interfaces to OpenAI, Anthropic (Claude), Google AI (Gemini), Mistral, Ollama, and other providers. Ready for Dart and Flutter.