gMCPLite — for Claude Code gMCPLite, gsDesignSkills, community, for Claude Code, ide skills, graphicalMCP, matrix2graph(), graphMCP, joinGraphs(), subgraph()

v1.0.0
GitHub

关于此技能

适用场景： Ideal for AI agents that need graphical mcp with gmcplite (legacy). 本地化技能摘要： gMCPLite helps AI agents handle repository-specific developer workflows with documented implementation details.

功能特性

Graphical MCP with gMCPLite (Legacy)
For new projects, prefer the graphicalMCP package which has a cleaner API.
Full function docs: references/llms.txt (built from local man pages)
Workflow patterns: references/code patterns.md
matrix2graph() - Create graphMCP object from transition matrix

# 核心主题

for Claude Code graphicalMCP matrix2graph() graphMCP joinGraphs() subgraph()
keaven keaven
[0]
[0]
更新于: 4/4/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
48
Canonical Locale
en
Detected Body Locale
en

适用场景： Ideal for AI agents that need graphical mcp with gmcplite (legacy). 本地化技能摘要： gMCPLite helps AI agents handle repository-specific developer workflows with documented implementation details.

核心价值

推荐说明： gMCPLite helps agents graphical mcp with gmcplite (legacy). gMCPLite helps AI agents handle repository-specific developer workflows with documented implementation details.

适用 Agent 类型

适用场景： Ideal for AI agents that need graphical mcp with gmcplite (legacy).

↓ 赋予的主要能力 · gMCPLite

适用任务： Applying Graphical MCP with gMCPLite (Legacy)
适用任务： Applying For new projects, prefer the graphicalMCP package which has a cleaner API
适用任务： Applying Full function docs: references/llms.txt (built from local man pages)

! 使用限制与门槛

  • 限制说明： Requires repository-specific context from the skill documentation
  • 限制说明： Works best when the underlying tools and dependencies are already configured

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作，再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”，而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核，以及是否已经进入工作流落地阶段。

安装路径

先进入安装与验证

如果这项技能值得继续，下一步应该先确认安装命令、CLI 写入路径与环境验证。
可信复核

回到可信合集再做一次复核

如果你还在比较不同技能或供应方，先回到可信合集做二次判断，而不是继续放大仓库噪音。
工作流

如果要进团队流转，转到工作流集合

当你的目标已经不是单个技能，而是团队协作、审批和交接，就应该转到工作流合集继续决策。
实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致，便于搜索引擎理解页面内容。

? FAQ

gMCPLite 是什么？

适用场景： Ideal for AI agents that need graphical mcp with gmcplite (legacy). 本地化技能摘要： gMCPLite helps AI agents handle repository-specific developer workflows with documented implementation details.

如何安装 gMCPLite？

运行命令：npx killer-skills add keaven/gsDesignSkills/gMCPLite。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

gMCPLite 适用于哪些场景？

典型场景包括：适用任务： Applying Graphical MCP with gMCPLite (Legacy)、适用任务： Applying For new projects, prefer the graphicalMCP package which has a cleaner API、适用任务： Applying Full function docs: references/llms.txt (built from local man pages)。

gMCPLite 支持哪些 IDE 或 Agent？

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

gMCPLite 有哪些限制？

限制说明： Requires repository-specific context from the skill documentation；限制说明： Works best when the underlying tools and dependencies are already configured。

↓ 安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行：npx killer-skills add keaven/gsDesignSkills/gMCPLite。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    gMCPLite 已启用，可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考，但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论，再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

gMCPLite

安装 gMCPLite，这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Graphical MCP with gMCPLite (Legacy)

For new projects, prefer the graphicalMCP package which has a cleaner API.

API reference

  • Full function docs: references/llms.txt (built from local man pages)
  • Workflow patterns: references/code_patterns.md

Key functions

Graph creation

  • matrix2graph() - Create graphMCP object from transition matrix
  • graphMCP class - Core graph representation (hypotheses, weights, transitions)
  • joinGraphs() - Combine multiple graphs
  • subgraph() - Extract subgraph

Testing

  • gMCP() - Graphical MCP testing procedure
  • gMCP.extended() - Extended testing with parametric tests
  • graphTest() - Test hypotheses on a graph

Visualization

  • hGraph() - Create multiplicity graph visualization (ggplot2-based)
  • placeNodes() - Compute node positions for graph layout

Test functions

  • bonferroni.test() - Bonferroni test
  • bonferroni.trimmed.simes.test() - Bonferroni-trimmed Simes test
  • parametric.test() - Parametric test using correlation
  • simes.test() - Simes test
  • simes.on.subsets.test() - Simes test on subsets

Utilities

  • generateWeights() - Generate weights for intersection hypotheses
  • generatePvals() - Generate p-values for simulation
  • simConfint() - Simultaneous confidence intervals
  • rejectNode() - Reject a hypothesis and update graph
  • exampleGraphs() - Pre-built example graphs
  • checkCorrelation() - Validate correlation matrix

Workflow patterns

For detailed code templates, read references/code_patterns.md.

Topics covered:

  • Creating multiplicity graphs with hGraph() (basic and custom)
  • Customizing hGraph layout (positions, colors, legends, sizing, radianStart)
  • Creating graphMCP objects with matrix2graph()
  • Bonferroni, Simes, and parametric testing with gMCP()
  • Extended testing with gMCP.extended() and custom test functions
  • Generating intersection weights with generateWeights()
  • Updating graphs after rejection with rejectNode()
  • Simultaneous confidence intervals with simConfint()
  • Built-in example graphs (BonferroniHolm, fixedSequence, fallback, etc.)
  • Integration with gsDesign sequential p-values (sequentialPValue())
  • Complex oncology trial template (6 hypotheses: OS/PFS/ORR x Subgroup/All)
  • Combining and subsetting graphs (joinGraphs(), subgraph())

Important design considerations

  • For new projects, prefer graphicalMCP: It has a cleaner S3 API (graph_create, graph_test_shortcut, graph_test_closure) and is actively maintained
  • hGraph() remains widely used: Even with graphicalMCP for testing, hGraph() from gMCPLite is commonly used for visualization in publications and presentations
  • Sequential p-values workflow: Use gsDesign::sequentialPValue() to convert nominal p-values from group sequential analyses into sequential p-values, then pass to gMCP() for multiplicity control
  • upscale = TRUE: Required for parametric tests (Bretz et al. 2011) to rescale subgraph weights to sum to 1
  • correlation with NA: gMCPLite supports partially specified correlation matrices (NA for unknown entries)
  • Time travel for alpha: When a hypothesis is rejected at a later analysis, previously tested hypotheses can be re-tested at updated alpha levels — this controls Type I error but requires careful bound re-derivation
  • gMCP() returns gMCPResult: Access @rejected (logical), @adjPValues (adjusted p-values), and @graphs (sequence of updated graphs)

相关技能

寻找 gMCPLite 的替代方案 (Alternative) 或可搭配使用的同类 community Skill？探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

★ 333.8k
⑂ 0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

React 框架

★ 138.4k
⑂ 0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

★ 98.6k
⑂ 0
开发者工具