MCP 助手
- 作者仓库星标 0
- 作者更新于 实时读取
- 作者仓库 skills-registry
- 领域
- AI 智能
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @tomevault-io · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- macOS
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: flutter-mcp-cli-runtime-validation
description: Run Flutter MCP runtime validation from CLI in two steps (launch app, then run validate-runtime)…
category: AI 智能
runtime: 无特殊运行时
---
# flutter-mcp-cli-runtime-validation 输出预览
## PART A: 任务判断
- 适用问题:提示词、Agent 工作流、模型评估或自动化推理。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Two-Step Flow / What validate-runtime Must Prove / Output Handling”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于提示词、Agent 工作流、模型评估或自动化推理,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Two-Step Flow / What validate-runtime Must Prove / Output Handling”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 先确认触发方式
原文没有稳定的斜杠命令要求。安装验证后通常全局生效,直接在对话里点名这个 Skill 并描述任务即可。
给清楚输入和边界
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、执行终端命令。
小样例验证后再放大
先用一个小任务确认它会围绕“Two-Step Flow / What validate-runtime Must Prove / Output Handling”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
复核后再交付
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: flutter-mcp-cli-runtime-validation
description: Run Flutter MCP runtime validation from CLI in two steps (launch app, then run validate-runtime)…
category: AI 智能
source: tomevault-io/skills-registry
---
# flutter-mcp-cli-runtime-validation
## 什么时候使用
- 把 AI / Agent方向的常用动作沉淀成 Agent 可调用的技能 适合处理AI Agent、提示词、模型评估与自动化推理,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查…
- 面向提示词、Agent 工作流、模型评估或自动化推理,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Two-Step Flow / What validate-runtime Must Prove / Output Handling」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令;主要在本地完成;通常不需要额外 API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 证据边界与执行链路
作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "flutter-mcp-cli-runtime-validation" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Two-Step Flow / What validate-runtime Must Prove / Output Handling
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Flutter MCP CLI Runtime Validation
Use this skill when you need agent-style runtime validation through flutter-mcp-toolkit with minimal operator steps.
Two-Step Flow
- Launch the Flutter app in debug mode.
- Run one CLI command:
dart run mcp_server_dart/bin/flutter_mcp_toolkit.dart --save-images --output-dir .flutter_mcp/runtime_validation validate-runtime \
--target ws://127.0.0.1:8181/<token>/ws \
--timeout-ms 10000 \
--post-reload-delay-ms 500 \
--after-reload
Optional skill install in the same command:
dart run mcp_server_dart/bin/flutter_mcp_toolkit.dart validate-runtime \
--target ws://127.0.0.1:8181/<token>/ws \
--install-skill
Permission behavior for this flow:
validate-runtimestays read/write only for visual capture and defaults toauto_request_once.doctorremains read-only.- On macOS, Screen Recording permission belongs to the host process running
flutter-mcp-toolkit. - On web,
flutter_layeris the only supported truth path and no OS permission prompt is expected. - If the first
capture_ui_snapshotattempt uses hostdesktop_windowand fails (common on macOS when the window is not foregrounded, or for iOS Simulator),validate-runtimeautomatically retries once withflutter_layer. - You may pass the VM URI as global
--vm-service-uriinstead ofvalidate-runtime --targetwhen only one URI is needed.
What validate-runtime Must Prove
- Doctor preflight passes critical checks.
- Required toolkit extensions exist:
ext.mcp.toolkit.app_errorsext.mcp.toolkit.view_detailsext.mcp.toolkit.view_screenshotsext.mcp.toolkit.inspect_widget_at_point
- Screenshot capture works.
- View details (layout metadata) are available.
- App errors are retrievable.
- If
--after-reloadis enabled, post-reload screenshot also works.
Output Handling
- Use
data.summaryas pass/fail status for automation. - Use
data.summary.captureFallbackUsedto see whether theflutter_layerretry succeeded after a faileddesktop_windowattempt. - Use
data.stepsfor per-step evidence and retries. - Use
data.doctor.checksto explain setup blockers. - Use
data.summary.screenshotFilesfor saved screenshot paths when--save-imagesis enabled. - When
--save-imagesis enabled, read screenshot file URLs from step data. - For visual debugging reports, also run:
exec --name capture_ui_snapshot --args '{"errorsCount":4,"compress":true,"includeViewDetails":true,"includeErrors":true}'exec --name inspect_widget_at_point --args '{"x":<int>,"y":<int>}'
Failure Rules
- If toolkit extensions are missing, stop and report instrumentation gap with exact fix:
- add
mcp_toolkitto app dependencies - ensure
MCPToolkitBinding.instance.bootstrapFlutter(...)or equivalent manual initialization runs beforerunApp - hot restart or rerun the app
- add
- If first explicit URI connect fails, retry is automatic for retryable connection errors.
- If screenshots are blank, verify app window is visible and retry.
- If macOS visual capture is denied, use:
dart run mcp_server_dart/bin/flutter_mcp_toolkit.dart permissions statusdart run mcp_server_dart/bin/flutter_mcp_toolkit.dart permissions requestdart run mcp_server_dart/bin/flutter_mcp_toolkit.dart permissions open-settings
- If app cannot be instrumented, do not claim screenshot/layout/error inspection success.
Visual QA + Source Mapping Rules
- Always compare before/after screenshot evidence around changes.
- For each reported visual issue, provide coordinate +
inspect_widget_at_pointoutput. - Map defects to source using
get_app_errorstop stack frame (file,line,column) when available. - Do not use
debug_dump_*unless explicitly requested.
Challenge Cases (Always Call Out Explicitly)
- No running debug app:
doctorcritical failure onvm_target_reachable; request app launch before continuing. - Wrong target URI/token: treat as connection mismatch and retry with exact
app.debugPort.wsUri. - Toolkit added but still missing extensions: hot reload is often insufficient, require hot restart/full rerun.
- Non-modifiable app (cannot add toolkit): report inspection as unavailable instead of guessing.
Source: Arenukvern/mcp_flutter — distributed by TomeVault.
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核