一键在 Manus 中运行任何 Skill

plan-advisor

星标7

分支1

更新时间2026年3月7日 10:34

General-purpose plan advisor that assesses any plan file, launches a sub-agent to evaluate it, and auto-answers questions during planning and implementation workflows. Answers are displayed transparently showing both Q and A. Follows senior/lead engineer quality standards across front-end, back-end, and product decisions. Manual activation only via phrases like 'use plan-advisor' or 'activate plan-advisor'. State persisted in project memory directory.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

quaylabshq

quaylabshq/skill-graph

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Plan Advisor

Navigable reference graph for the plan-advisor skill. Assesses plans, evaluates them via sub-agent, and auto-answers workflow questions at senior/lead engineer quality.

Activation

Topic	Reference
Activation concepts	references/activation/overview.md
Trigger detection	references/activation/invocation-detection.md
State persistence	references/activation/state-management.md

Assessment

Topic	Reference
Assessment process	references/assessment/overview.md
Plan discovery & parsing	references/assessment/plan-reading.md
Sub-agent evaluation	references/assessment/sub-agent-evaluation.md

Answering

Topic	Reference
Answer framework	references/answering/overview.md
Quality standards	references/answering/quality-standards.md
Domain expertise	references/answering/domain-expertise.md

Workflows

Topic	Reference
Workflow summary	references/workflows/overview.md
Activation sequence	references/workflows/activation-workflow.md
Question answering	references/workflows/question-answering-workflow.md

Extensions

Topic	Reference
Future capabilities	references/extensions.md

同仓库更多 Skills

同仓库

implementation-plan

quaylabshq/skill-graph

Structured implementation planning skill that enhances Claude's plan mode with mandatory questioning, research, problem decomposition, goal-driven criteria-first planning, and multi-agent verification before any implementation begins. Use when the user asks to plan a task, create an implementation plan, think through an approach, or when Claude enters plan mode. Plans are goal-driven: for code tasks, every step follows TDD (tests specified before implementation); for non-code tasks, every step has observable acceptance criteria defined before the approach. Plans are held to Google/NASA- grade quality standards and must pass independent verification by 3+ specialized sub-agents (requirements traceability, technical rigor, security & threat analysis) before presentation. Handles any domain — software engineering, design, business, research, content — by adapting its questioning depth, research strategy, and plan detail to the task's complexity and type. Always explores the codebase for code tasks; uses web rese

2026-03-207

chat-ui

quaylabshq/skill-graph

Chat UI building blocks for React/Next.js from ui.inference.sh. Components: ChatContainer, ChatMessages, ChatInput, MessageBubble, MessageContent, MessageReasoning, MessageStatusIndicator, Markdown. Capabilities: chat interfaces, message lists, input handling, streaming, file uploads, drag-and-drop, auto-scroll, reasoning/thinking blocks, markdown rendering with code highlighting. Use for: building custom chat UIs, messaging interfaces, AI agent frontends, conversational apps. Triggers: chat ui, chat component, message list, chat input, shadcn chat, react chat, chat interface, messaging ui, conversation ui, chat building blocks, inference.sh chat, agent chat ui, streaming chat

2026-03-077

design-md

quaylabshq/skill-graph

Analyze Stitch projects via MCP Server and synthesize semantic design systems into DESIGN.md files. Use when creating a DESIGN.md to capture an existing Stitch project's visual language — colors, typography, component styles, layout principles — in descriptive, designer-friendly prose with exact hex values. Requires access to Stitch MCP Server. Produces a single DESIGN.md that serves as the source of truth for prompting Stitch to generate new screens aligned with the existing design language.

2026-03-077

vercel-react-best-practices

quaylabshq/skill-graph

React and Next.js performance optimization guide with 58 rules across 8 priority categories. Use when writing new React components, implementing data fetching, reviewing code for performance, refactoring React/Next.js code, or optimizing bundle size and load times. Covers async waterfalls, bundle size, server-side performance, client-side data fetching, re-render optimization, rendering performance, JavaScript performance, and advanced patterns.

2026-03-077

web-design-guidelines

quaylabshq/skill-graph

Review React/Next.js UI code for compliance with web interface design guidelines. Triggers on requests like "review my UI", "check accessibility", "audit design", "review UX", "check my site against best practices", "review this component", or "audit web interface". Works with JSX, TSX, HTML, and CSS files.

2026-03-077

skill-graph-creator

quaylabshq/skill-graph

Guide for creating skill graphs — interlinked, modular skill architectures that decompose knowledge into navigable reference networks. Use when users want to create a new skill graph (or upgrade an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Always produces graph-structured output with lean index files, interlinked references, and explicit extension points.

2026-03-077

name

plan-advisor

description

Plan Advisor

Navigable reference graph for the plan-advisor skill. Assesses plans, evaluates them via sub-agent, and auto-answers workflow questions at senior/lead engineer quality.

Activation

Topic	Reference
Activation concepts	references/activation/overview.md
Trigger detection	references/activation/invocation-detection.md
State persistence	references/activation/state-management.md

Assessment

Topic	Reference
Assessment process	references/assessment/overview.md
Plan discovery & parsing	references/assessment/plan-reading.md
Sub-agent evaluation	references/assessment/sub-agent-evaluation.md

Answering

Topic	Reference
Answer framework	references/answering/overview.md
Quality standards	references/answering/quality-standards.md
Domain expertise	references/answering/domain-expertise.md

Workflows

Topic	Reference
Workflow summary	references/workflows/overview.md
Activation sequence	references/workflows/activation-workflow.md
Question answering	references/workflows/question-answering-workflow.md

Extensions

Topic	Reference
Future capabilities	references/extensions.md