Flutter Agent Skills
Official Flutter team Agent Skills for AI coding agents building Flutter apps, fixing layout issues, adding widget and integration tests, creating widget previews, applying layered architecture, routing, localization, JSON serialization, and HTTP workflows.
Open the source and read safety notes before installing.
Safety notes
- Flutter skills can modify application code, tests, pubspec dependencies, routing, localization files, serialization code, architecture boundaries, and app entry points.
- Integration-test workflows may enable Flutter Driver extensions, add keys to widgets, launch apps through MCP tools, interact with running UI, and create driver scripts.
- Do not run device, emulator, browser, Firebase Test Lab, or network-backed integration tests against production services without explicit approval and test credentials.
- Architecture and routing changes can alter navigation, state management, API access, caching, offline behavior, and user-visible app flows.
- Use project-local conventions and Flutter version constraints before applying generated examples.
Privacy notes
- Flutter projects may contain API URLs, Firebase project IDs, mobile bundle IDs, analytics keys, user fixtures, screenshots, test traces, device logs, crash output, and integration-test artifacts.
- MCP app exploration can expose widget trees, screen text, test data, typed inputs, navigation paths, and screenshots from the running app.
- HTTP, JSON, localization, and repository-layer work may touch private API schemas, user data models, translations, product copy, and backend payloads.
- Keep credentials, private endpoints, screenshots with user data, device logs, Firebase tokens, and proprietary UI flows out of public prompts, issues, PRs, and examples.
Prerequisites
- Flutter SDK and Dart tooling installed for the target project.
- An AI coding assistant or skill host compatible with Agent Skills, preferably using the standard `.agents/skills` install target.
- Project-specific Flutter targets, devices, emulators, browsers, test commands, and package constraints available before modifying app code.
- For MCP-assisted testing or UI exploration, access to the Dart/Flutter MCP server or equivalent app interaction tools.
Schema details
- Install type
- package
- Reading time
- 8 min
- Difficulty score
- 76
- Troubleshooting
- Yes
- Breaking changes
- No
- Scope
- Source repo
- Skill type
- capability-pack
- Skill level
- expert
- Verification
- validated
- Verified at
- 2026-06-18
| Platform | Support | Install path |
|---|---|---|
| claude-code | Native | .claude/skills/<skill-name>/SKILL.md |
| codex | Native | .agents/skills/<skill-name>/SKILL.md |
| windsurf | Native | .windsurf/skills/<skill-name>/SKILL.md |
| gemini | Native | .gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md |
| cursor | Adapter | .cursor/rules/<skill-name>.mdc |
| cli | Manual | AGENTS.md or tool-specific context file |
Full copyable content
npx skills add flutter/skills --skill '*' --agent universal --yes
# Update installed skills
npx skills updateAbout this resource
Flutter Agent Skills
flutter/skills is the official Flutter team Agent Skills repository. It gives
AI coding agents repeatable, Flutter-specific workflows for common app work:
layout errors, widget previews, widget tests, integration tests, responsive
layouts, layered architecture, routing, localization, JSON serialization, and
HTTP requests.
The README explicitly frames skills as complementary to MCP: MCP gives the agent specialized tools, while a skill teaches the agent how to use tools for a specific task. That makes this pack useful for Claude Code, Codex, Gemini CLI, and any skill-aware coding assistant working inside Flutter apps.
Knowledge Freshness
The repository is maintained by the Flutter team and the representative skills include metadata showing recent 2026 updates. Flutter SDK behavior, Dart language features, package APIs, integration testing, widget preview systems, MCP tooling, and recommended architecture patterns can change.
Use these skills to guide workflow and best practices, then verify exact commands, package versions, SDK constraints, device targets, and test behavior against the target Flutter project and current Flutter documentation.
Retrieval Sources
This listing is grounded in:
- The
flutter/skillsrepository README. - The public skills.sh listing for Flutter skills.
- Representative
SKILL.mdfiles for layout debugging, integration tests, and architecture best practices. - The repository license text.
- Current GitHub repository metadata from the official Flutter organization.
Core Workflow
Install all Flutter skills into the standard universal skill location:
npx skills add flutter/skills --skill '*' --agent universal --yes
Update installed skills:
npx skills update
The README recommends using the universal .agents/skills target so most
agents can discover the installed skills.
Capability Scope
The repository currently lists these Flutter skills:
| Skill | Scope |
|---|---|
flutter-add-integration-test |
Configure integration tests and convert MCP UI actions into permanent tests |
flutter-add-widget-preview |
Add interactive previews for UI components and screen states |
flutter-add-widget-test |
Write component-level tests with WidgetTester |
flutter-apply-architecture-best-practices |
Structure apps with UI, logic, and data layers |
flutter-build-responsive-layout |
Build adaptive layouts with LayoutBuilder, MediaQuery, Expanded, and Flexible |
flutter-fix-layout-issues |
Diagnose overflows, unbounded constraints, ParentData errors, and layout failures |
flutter-implement-json-serialization |
Map JSON to Dart model classes with fromJson and toJson |
flutter-setup-declarative-routing |
Configure router-based navigation and deep links |
flutter-setup-localization |
Add localization dependencies, generated l10n, and translations |
flutter-use-http-package |
Make GET, POST, PUT, and DELETE requests with the http package |
Production Rules
Use these skills with project-specific Flutter discipline:
- Inspect the target Flutter version, Dart SDK constraint, app structure, package manager state, and test setup before editing.
- Prefer nearby project conventions for state management, routing, networking, localization, theming, and dependency injection.
- For layout errors, capture the primary Flutter exception before applying a generic constraint fix.
- For integration tests, add stable keys, use test entry points, and avoid hitting production APIs or accounts.
- For architecture changes, keep UI, ViewModel or logic, repositories, services, and models in clear layers rather than mixing data access into widgets.
- Run focused widget, integration, or
flutter testvalidation before broad refactors. - Redact screenshots, logs, API payloads, and test data before sharing output.
Use Cases
- Ask Codex to fix a
RenderFlex overflowedor unboundedListViewerror with a source-backed Flutter layout workflow. - Use Claude Code to turn an MCP-explored checkout flow into a permanent Flutter integration test.
- Have Gemini CLI add widget tests for a UI component using
WidgetTester. - Ask an agent to add localization scaffolding with
flutter_localizations,intl, generated ARB files, andl10n.yaml. - Use an assistant to refactor a feature into Flutter's recommended layered architecture without mixing UI and data logic.
Source Review
- The README describes Flutter Agent Skills as maintained by the Flutter team.
- The README states the skills provide tailored instructions for happy-path Flutter app development workflows.
- The README says skills complement MCP by teaching agents how to use tools for a task.
- The install command uses
npx skills add flutter/skills --skill '*' --agent universal --yes. - The available skills list covers integration tests, widget previews, widget tests, architecture, responsive layouts, layout fixes, JSON serialization, declarative routing, localization, and HTTP.
- The integration-test skill includes MCP-assisted UI exploration and conversion into permanent integration tests.
- The layout skill documents common Flutter constraint errors and repair workflows.
- The license file identifies the repository as BSD-3-Clause.
Duplicate Review
Checked current content/skills/, content/tools/, content/mcp/, open pull
requests, and repository-wide content for flutter/skills, Flutter Agent
Skills, Flutter skills, Flutter MCP integration tests, Flutter layout skills,
and representative skill names. No dedicated Flutter Agent Skills entry, exact
source URL duplicate, target file, or open duplicate PR was found.
Disclosure
Editorial listing. No paid placement or affiliate link is used. The upstream repository is maintained by the Flutter team and licensed under BSD-3-Clause.
Source citations
Add this badge to your README
How it compares
Flutter Agent Skills side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Flutter Agent Skills Official Flutter team Agent Skills for AI coding agents building Flutter apps, fixing layout issues, adding widget and integration tests, creating widget previews, applying layered architecture, routing, localization, JSON serialization, and HTTP workflows. Open dossier | Dart Agent Skills Official Dart team Agent Skills for AI coding agents working on Dart unit tests, CLI apps, coverage, runtime errors, mocks, package conflicts, static analysis, Native Assets, FFI, ffigen, and pattern matching. Open dossier | Vercel Agent Skills Vercel Labs' official Agent Skills collection for AI coding agents working on Vercel deployments, React and Next.js performance, React Native, web design guidelines, writing guidelines, composition patterns, view transitions, CLI token workflows, and Vercel optimization audits. Open dossier | Google Cloud Agent Skills Google Agent Skills catalog for AI agents working with Google Cloud, Gemini Enterprise Agent Platform, Gemini APIs, Skill Registry, Cloud Run, BigQuery, Firebase, GKE, Cloud SQL, AlloyDB, gcloud, auth, onboarding, and Well-Architected Framework guidance. Open dossier |
|---|---|---|---|---|
| Trust | ||||
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Category | skills | skills | skills | skills |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | Flutter Team | Dart Team | Vercel Labs | |
| Added | 2026-06-18 | 2026-06-18 | 2026-06-18 | 2026-06-18 |
| Platforms | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI |
| Source repo | — | — | — | — |
| Safety notes | ✓Flutter skills can modify application code, tests, pubspec dependencies, routing, localization files, serialization code, architecture boundaries, and app entry points. Integration-test workflows may enable Flutter Driver extensions, add keys to widgets, launch apps through MCP tools, interact with running UI, and create driver scripts. Do not run device, emulator, browser, Firebase Test Lab, or network-backed integration tests against production services without explicit approval and test credentials. Architecture and routing changes can alter navigation, state management, API access, caching, offline behavior, and user-visible app flows. Use project-local conventions and Flutter version constraints before applying generated examples. | ✓Dart skills can modify source code, tests, pubspec dependencies, analysis options, generated mocks, coverage output, native hooks, FFI bindings, and package constraints. `dart fix --apply`, formatter runs, mock generation, build_runner, ffigen, and Native Assets hooks can create broad mechanical diffs; inspect changes before committing. Native Assets and FFI workflows may compile C/C++ code, run local toolchains, download precompiled binaries, and link dynamic or static libraries. Downloaded binaries should use cryptographic hash validation and offline fallbacks as the skill describes. Package conflict fixes can upgrade or downgrade dependencies and affect transitive package behavior across Dart and Flutter projects. | ✓The deploy-to-vercel and Vercel CLI token skills can guide agents toward git pushes, preview deployments, Vercel project linking, environment variable changes, and account-scoped CLI calls; keep human approval on those actions. The vercel-cli-with-tokens skill includes token-handling workflows. Prefer environment variables over command-line token flags and avoid echoing secrets into prompts, logs, screenshots, or public PRs. The vercel-optimize skill reads Vercel metrics, usage, project configuration, and code scan results; verify the linked project and team scope before collecting or acting on recommendations. The web-design-guidelines and writing-guidelines skills fetch current upstream rule documents at use time, so review fetched guidance before treating output as policy. React, Next.js, and React Native performance rules are strong defaults, but agents still need local tests, framework-version checks, and product-specific review before broad refactors. | ✓Google Cloud skills can create, update, delete, deploy, query, or configure cloud resources, datasets, IAM policies, service accounts, APIs, containers, jobs, and networking. The gcloud skill requires command validation and safety guardrails before invoking Google Cloud CLI commands; do not let agents improvise cloud commands from memory. Skill Registry guidance includes skill lifecycle management such as upload, update, and permanent delete operations; validate environment and approval before use. Cloud Run, GKE, BigQuery, Firebase, Cloud SQL, AlloyDB, and Gemini API workflows can create cost, expose endpoints, alter data, or change production behavior. The repository notes active development, so verify exact commands, product names, API availability, and launch-stage limits before production use. |
| Privacy notes | ✓Flutter projects may contain API URLs, Firebase project IDs, mobile bundle IDs, analytics keys, user fixtures, screenshots, test traces, device logs, crash output, and integration-test artifacts. MCP app exploration can expose widget trees, screen text, test data, typed inputs, navigation paths, and screenshots from the running app. HTTP, JSON, localization, and repository-layer work may touch private API schemas, user data models, translations, product copy, and backend payloads. Keep credentials, private endpoints, screenshots with user data, device logs, Firebase tokens, and proprietary UI flows out of public prompts, issues, PRs, and examples. | ✓Dart projects may contain private package names, API schemas, service URLs, test fixtures, generated mocks, coverage paths, stack traces, native library names, and build logs. Runtime-error workflows can expose stack traces, local paths, active app state, logs, and user-input data from the running program. FFI and Native Assets workflows may include proprietary C/C++ source, platform-specific build settings, binary hashes, and downloaded artifact URLs. Keep credentials, private package registries, source paths when sensitive, proprietary native code, test data, and generated coverage reports out of public prompts, issues, PRs, and examples. | ✓Deployment and optimization workflows may expose project names, team slugs, deployment URLs, routes, metrics, usage details, billing signals, source paths, build configuration, environment variable names, and CLI account context. Keep VERCEL_TOKEN, VERCEL_ORG_ID, VERCEL_PROJECT_ID, API keys, environment values, claim URLs, deployment logs, and private preview URLs out of public artifacts unless intentionally disclosed. Design, writing, React, and performance reviews can reveal proprietary UI, product copy, documentation strategy, source code, routes, and business priorities to the configured model provider. | ✓Google Cloud workflows may expose project IDs, service account emails, OAuth tokens, API keys, ADC credentials, Terraform state, dataset names, table schemas, query text, logs, traces, prompts, model outputs, embeddings, and customer data. BigQuery, Firebase, Cloud SQL, AlloyDB, GKE, and Agent Platform workflows may process regulated or proprietary data; review data residency, IAM, retention, audit logging, and sharing rules before use. Gemini API and Agent Platform skills can send prompts, files, images, audio, video, tool inputs, structured outputs, cached contexts, and batch datasets to Google services. Keep credentials, project IDs when sensitive, private queries, logs, trace payloads, Terraform state, customer data, and generated datasets out of public prompts, issues, PRs, and screenshots. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | — | — | — | — |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.