mcp_flutter

Generic contract/schema boundary audit across authoring, discovery, validation, and execute—detecting split-brain between listings and invoke paths, gateway divergence, and permissive placeholders. Use when changing tool registration, RPC/plugin registries, dynamic tools, MCP or WebMCP surfaces, CLI exec aliases, OpenAPI or JSON Schema contracts, migrators/codegen, bridge argument encoding, or platform docs that describe API contracts.

Use this skill whenever inspecting, interacting with, or live-editing a running Flutter app via the Flutter MCP toolkit server (`mcpServers` key **`flutter-mcp-toolkit`**, or legacy **`flutter-inspector`**). Covers preflight, snapshot/tap/enter/scroll loop, hot-reload validation, and error envelope parsing.

Use this skill when the agent exposes app-specific surfaces by registering custom MCP tools and resources inside the Flutter app (mcp_toolkit dynamic registry — AgentCallEntry, bootstrapFlutter additionalEntries / addEntries). Covers tool vs resource vs evaluate-expression, Map-based handlers, schema strictness, discovery via fmt_list_client_tools_and_resources, fmt_client_tool, fmt_client_resource, and lifecycle pitfalls.

Entry point for inspecting or driving a running Flutter app from your AI assistant — routes to the right task skill (inspect / control / debug / custom app surfaces) and runs preflight.

Read state from a running Flutter app — semantic snapshot, view details, errors, screenshots, VM info. Use when you need to understand what the app is showing.

Migrate Flutter app code from removed MCPCallEntry to AgentCallEntry after the hard cut. Use when upgrading mcp_toolkit, fixing compile errors after a major bump, or running flutter-mcp-toolkit migrate agent-entries.

Maintains repo-local action contracts and harness repositories where product CLI and MCP adapters stay thin over core libraries. Use when adopting or improving steward.yaml actions, capability-level adoption evidence, cold-start proof loops, probes, benchmarks, CLI/MCP/core parity, adapter refactors, packages/core boundaries, or sibling harness layout; use repo-quality-system-lifecycle first for general app/library/tool stewardship baselines.

Maintain mcp_flutter releases, CHANGELOG, version pins, docs, and CI. Use when cutting a release, editing CHANGELOG.md, bumping VERSION, running release-please, sync-skills, check-contracts, or updating install/docs for npx skills and flutter-mcp-toolkit init.

Maintains flutter_test_app macOS showcase, native intentcall hooks (codegen, app_links invoke), and VM MCP validation. Use when editing macOS Runner, intentcall_codegen.sh, macOS dogfood, Screen Recording capture, or comparing macOS parity to web WebMCP.

Maintains flutter_test_app and intentcall web targets (Chrome, web codegen, WebMCP bootstrap, web-showcase, webmcp verify). Use when editing web/index.html, agent_manifest.json, intentcall_webmcp.generated.js, web platform sync, Chrome dogfood, or WebMCP modelContext.

Verify the flutter-mcp-toolkit install, run doctor preflight, troubleshoot connection issues. Use when the toolkit isn't responding or first-time setup.

Runs and records flutter_test_app dogfood iterations (tool_quality_rubric, run_dogfood_eval.sh, dogfood_web_eval.yaml). Use when scoring MCP/intentcall quality, appending iteration N, comparing regressions, or CI static/weekly eval gates.

Design, implement, and integrate generalized validation harnesses across a producer-consumer boundary after a local harness contract exists. Use when refactoring custom validation CLIs/MCPs for large polyrepos, extending Steward across sibling repos, or deploying a local tool to a consumer project for dogfooding and testing; use mcp-harness-repo-maintainer first for initial steward.yaml adoption and cold-start proof.

Run a Mixture of Experts (MoE) audit on any topic, plan, codebase, evidence archive, or process. Dynamically spawns specialized subagents with different critical lenses to cross-reference findings and detect flaws, overlap, retention issues, or drift. Use when designing architectures, analyzing complex code, verifying multi-step plans, classifying evidence artifacts, or looking for duplicated intent in a repo.

Plan and document handoffs, parent lane contracts, and parallel batch contracts between specialized AI agents (foreman, workers, reviewers). Use for multi-agent workflows, subagents, original goal preservation, native gates, claim ceilings, terminal states, baton passes, or guild-style agent coordination.

Designs public or private Agent Skill and plugin marketplaces for Cursor, Claude Code, Codex, Zed, Open Plugin, and npx skills—manifest layout, install matrix, and Skill Steward vs product boundaries. Use when setting up a marketplace, distributing skills/plugins to a team, private registry, .cursor-plugin, .codex-plugin, .plugin, .claude-plugin, or skills.sh publishing.

Chooses ecosystem-native release and changelog tooling (Changesets, Melos, release-plz) plus binary distribution (GitHub Release tarballs, install.sh) when the product is an executable. Use for release CI, install.sh, versioning, CHANGELOGs, shipping MCP/CLI without clone, or meta repos that only ship skills via npx skills—not domain app tutorials.

Master orchestration for repository governance, North Star impact, sub-Star boundaries, and repair-first or evidence-first drift checks. Guides an agent through the complete lifecycle of making architectural decisions, documenting them, writing FAQs, and cleaning up stale plans while adhering strictly to repo ethics and brand tone. Use whenever you need to make a structural change, write an ADR, update the doc lattice, or govern repository architecture.

Scaffold and formally review a new Agent Skill in this marketplace repo. Covers valid SKILL.md generation, directory layout, registry entries, and spec auditing. Use when adding a skill, validating frontmatter, or checking marketplace readiness before a PR.

Improves Agent Skills via validate → rule-based eval cases → plugin-eval → prompt evals → bounded edits with held-out gates. Use when tuning skill quality, routing, or adopting Chrome/Microsoft T-named quality gates—not for bulk validate-only or SkillOpt automation.

Drive a running Flutter app — tap, scroll, type, fill forms, hot-reload, navigate. Use when you need to interact with the UI.

Requires durable citations when authoring or researching Agent Skills—maintain references/sources.md per skill, link external research, and record provenance in PRs. Use when creating skills, updating SKILL.md, doing web research for skills, or auditing missing sources.

Run Flutter MCP runtime validation from CLI in two steps (launch app, then run validate-runtime), including toolkit-extension gating, screenshot/layout capture, app error collection, optional reload verification, and retry handling for transient first-connect failures.

Diagnose problems in a running Flutter app — read logs, evaluate Dart expressions, interpret error envelopes. Use when something broke.