KS
Killer-Skills

roadmap-guide — Categories.community

v1.0.0
GitHub

About this Skill

Perfect for Documentation Agents needing structured roadmap creation and version management. discord bot

MMorit00 MMorit00
[0]
[0]
Updated: 12/26/2025

Quality Score

Top 5%
49
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add MMorit00/fund-portfolio-bot/roadmap-guide

Agent Capability Analysis

The roadmap-guide MCP Server by MMorit00 is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion.

Ideal Agent Persona

Perfect for Documentation Agents needing structured roadmap creation and version management.

Core Value

Empowers agents to create concise and informative roadmaps using Markdown, enforcing simplicity and eliminating redundant information, with features like prohibiting excessive code examples and redundant data.

Capabilities Granted for roadmap-guide MCP Server

Updating version statuses in docs/roadmap.md
Recording architectural decisions and rationale
Marking deprecated features and data source restrictions

! Prerequisites & Limits

  • Requires adherence to core principles of information density over detail
  • Limited to Markdown format
Project
SKILL.md
2.6 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Roadmap 编写指南

核心原则:roadmap 是导航图,不是教科书。信息密度 > 详细程度。

When to use

必须应用此规范的场景:

  • docs/roadmap.md 添加新版本/功能
  • 更新已有版本的状态
  • 记录架构决策的理由
  • 标记禁止事项和数据源限制

1. 简洁性原则(CRITICAL)

❌ 禁止冗余

删除这些内容:

  1. 示例代码(除非必需理解问题)

    markdown
    1❌ 错误: 2**实现方案:** 3```python 4# 20 行完整代码示例 5async def chat_with_loop(self, query: str) -> str: 6 for i in range(15): 7 ...

    ✅ 正确: 实现方案: chat_with_loop() 方法,最多 15 轮 ReAct 循环

  2. 重复信息(已在其他文档详述)

    markdown
    1❌ 错误:详细解释 T+1/T+2 确认规则 2✅ 正确:确认规则见 `docs/settlement-rules.md`
  3. 过长段落

    markdown
    1❌ 错误:超过 3 行的描述段落 2✅ 正确:每段 ≤ 3 行,优先使用列表/表格

2. 版本条目结构

每个版本条目遵循固定结构:

markdown
1## vX.Y.Z 版本标题(状态标记) 2 3### 核心目标 4一句话说明此版本解决什么问题。 5 6### 实现范围 7- [x] 已完成项 8- [ ] 待完成项 9 10### 不做 11- ❌ 明确排除的功能(防止范围蔓延)

状态标记

  • 已完成
  • 🚧 进行中
  • 🔮 规划中

3. 对比表格

版本间对比使用表格,清晰展示差异:

markdown
1| 维度 | v0.5.0 | v0.5.1 | 2|------|--------|--------| 3| 调用轮数 | 固定 1-2 轮 | 动态 N 轮 | 4| 决策模式 | 一次性决定 | 边做边决策 |

4. 禁止事项 & 限制

使用统一格式记录:

markdown
1## 禁止事项 2- ❌ AI 执行交易操作(只给建议) 3- ❌ 修改数据库 Schema 4 5## 已知限制 6**限制名称**(记录日期): 7- 问题描述(1-2 行) 8- 未来方案(可选)

5. ASCII 图表

架构/数据流优先使用 ASCII 图:

markdown
1导入阶段: 2 CSV → 算法 → BillFacts → AI 判断 → 回填 ActionLog 3 4分析阶段: 5 用户提问 → AI → Tools → 分析 → 建议

6. 触发机制

自动触发: 当检测到以下操作时,自动应用此 skill

  • 文件路径包含 roadmap.md
  • 提交信息包含 "roadmap" / "版本" / "规划"
  • 用户明确要求更新 roadmap

提醒文案:

正在编辑 roadmap.md
请遵循简洁性原则:
- 每段 ≤ 3 行
- 代码示例 ≤ 5 行或删除
- 无重复信息
- 优先使用列表/表格

Related Skills

Looking for an alternative to roadmap-guide or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication