tools/sage-claude-plugin/skills/stack-flutter-firebase/SKILL.md
Integration patterns for Flutter + Firebase + Riverpod — auth, Firestore, Cloud Functions, project structure
npx skillsauth add xoai/sage stack-flutter-firebaseInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Layer 3 — Stack Composition
Integration patterns for the most common Flutter fullstack combination: Flutter + Firebase (Auth, Firestore, Cloud Functions, Storage) + Riverpod.
Firebase documentation explains each service in isolation. Riverpod docs explain state management in isolation. Neither explains: how Firebase Auth state feeds into Riverpod providers, how Firestore streams compose with Riverpod's reactive model, how to structure a project where Firebase is the backend and Riverpod manages the entire state tree.
These seams are where this pack provides value.
| Type | Files | Coverage | |------|-------|----------| | Integration | 4 | Firebase Auth + Riverpod, Firestore + Riverpod, Cloud Functions patterns, project structure | | Anti-patterns | 3 | Direct Firebase in widgets, unstructured Firestore, no security rules | | Constitution | 1 | 4 stack integration principles |
development
Branch-per-initiative git discipline for all delivery workflows. Defines branch naming by workflow, the propose-confirm creation protocol, dirty-tree and detached-HEAD handling, the always user-gated merge protocol, worktree support for parallel sessions, and abandonment cleanup. Activates only in git repositories — silently inactive everywhere else. Use when starting /build, /fix, /architect, or /build-x at Standard+ scope, when resuming an initiative, when offering a merge at a completion checkpoint, or when the user wants a second concurrent initiative.
development
Drives task-by-task execution from an approved plan with quality gates between each task. Reads the plan, finds the next incomplete task, dispatches implementation, validates, updates progress, and continues. Use after a plan is approved and the user says "go", "start building", "execute the plan", or "implement the feature".
testing
Preserves and restores context across agent sessions using plan file checkboxes as source of truth. Use when starting a new session, resuming previous work, ending a session, or when the user says "continue from last time", "what was I doing", or "save progress".
tools
Captures agent mistakes, corrections, and discovered gotchas so they are not repeated. Use when: (1) a command or operation fails unexpectedly, (2) the user corrects the agent, (3) the agent discovers non-obvious behavior through debugging, (4) an API or tool behaves differently than expected, (5) a better approach is found for a recurring task. Also searches past learnings before starting tasks to avoid known pitfalls. Activate alongside the sage-memory skill — they share the same MCP backend but serve different purposes (sage-memory = codebase knowledge, sage-self-learning = agent mistakes and gotchas).