Back to Details

divine

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

skill:divine - Divine Toolkit Entry Point

skill:divine - Divine工具包入口

Version: 1.0.0

Version: 1.0.0

Purpose

用途

The divine skill is the master entry point for The Forge's entire toolkit. It discovers and catalogs all available skills, agents, and commands, then recommends the optimal tool or workflow for a given task. Use this skill when users need guidance on which Forge capabilities to employ, when exploring what's available, or when orchestrating multi-skill workflows.
Divine skill是The Forge整个工具包的主入口。它会发现并分类所有可用的技能、Agent和命令，然后为给定任务推荐最佳工具或工作流。当用户需要指导以确定应使用The Forge的哪些功能、探索可用功能，或编排多技能工作流时，请使用此skill。

File Structure

文件结构

skills/divine/
├── SKILL.md (this file)
└── examples.md
skills/divine/
├── SKILL.md (this file)
└── examples.md

Interface References

接口参考

  • Context: Loaded via ContextProvider Interface
  • Memory: Accessed via MemoryStore Interface
  • Schemas: Validated against context_metadata.schema.json and memory_entry.schema.json
  • Context：通过ContextProvider Interface加载
  • Memory：通过MemoryStore Interface访问
  • Schemas：根据context_metadata.schema.json和memory_entry.schema.json进行验证

Mandatory Workflow

强制工作流

IMPORTANT: Execute ALL steps in order. Do not skip any step.
重要提示：按顺序执行所有步骤，请勿跳过任何步骤。

Step 1: Initial Analysis

步骤1：初始分析

  • Gather user intent (what task or problem they want to solve)
  • Determine the scope: skill discovery, agent recommendation, command lookup, or full workflow orchestration
  • Identify whether the user needs a single tool or a multi-tool workflow
  • 收集用户意图（他们想要解决的任务或问题）
  • 确定范围：技能发现、Agent推荐、命令查询或完整工作流编排
  • 确定用户需要单一工具还是多工具工作流

Step 2: Load Memory

步骤2：加载内存

  • Use 
    memoryStore.getSkillMemory("divine", "{project-name}")
    to load existing project memory. See MemoryStore Interface.
  • Load previously recommended workflows and their outcomes
  • Retrieve user preference patterns for tool selection
  • 使用
    memoryStore.getSkillMemory("divine", "{project-name}")
    加载现有项目内存。请参阅MemoryStore Interface。
  • 加载之前推荐的工作流及其结果
  • 检索用户在工具选择方面的偏好模式

Step 3: Load Context

步骤3：加载上下文

  • Load engineering domain context via 
    contextProvider.getIndex("engineering")
    . See ContextProvider Interface.
  • Load the skill registry (all available SKILL.md files)
  • Load the agent registry (all agent .config.json files)
  • Load the command registry (all command .md files)
  • 通过
    contextProvider.getIndex("engineering")
    加载工程领域上下文。请参阅ContextProvider Interface。
  • 加载技能注册表（所有可用的SKILL.md文件）
  • 加载Agent注册表（所有agent .config.json文件）
  • 加载命令注册表（所有命令 .md文件）

Step 4: Discover Available Tools

步骤4：发现可用工具

  • Enumerate all skills, agents, and commands in The Forge
  • Classify each by category, domain, and capability
  • Build an indexed catalog with triggers, descriptions, and prerequisites
  • 枚举The Forge中的所有技能、Agent和命令
  • 按类别、领域和能力对每个工具进行分类
  • 构建包含触发条件、描述和先决条件的索引目录

Step 5: Match Task to Tools

步骤5：任务与工具匹配

  • Analyze the user's task against the catalog
  • Score each tool for relevance based on:
    • Domain alignment (language, framework, infrastructure)
    • Task type match (review, generate, plan, analyze, deploy)
    • Trigger keyword matches
    • Historical success from memory
  • Rank recommendations by confidence
  • 将用户任务与目录进行比对
  • 根据以下因素为每个工具的相关性评分：
    • 领域匹配度（语言、框架、基础设施）
    • 任务类型匹配度（审核、生成、规划、分析、部署）
    • 触发关键词匹配
    • 内存中的历史成功率
  • 按置信度对推荐结果排序

Step 6: Compose Workflow

步骤6：编排工作流

  • For simple tasks: recommend a single skill, agent, or command
  • For complex tasks: compose a multi-step workflow with:
    • Ordered skill invocations via 
      skillInvoker
    • Agent delegation assignments
    • Command sequences
    • Data flow between steps
  • Include estimated effort and prerequisites for each step
  • 对于简单任务：推荐单一技能、Agent或命令
  • 对于复杂任务：编排多步骤工作流，包括：
    • 通过
      skillInvoker
      按顺序调用技能
    • Agent委托分配
    • 命令序列
    • 步骤间的数据流转
  • 包含每个步骤的预估工作量和先决条件

Step 7: Generate Output

步骤7：生成输出

  • Save output to 
    /claudedocs/divine_{project}_{YYYY-MM-DD}.md
  • Follow naming conventions in 
    ../OUTPUT_CONVENTIONS.md
  • Present recommendations with rationale and confidence scores
  • 将输出保存至
    /claudedocs/divine_{project}_{YYYY-MM-DD}.md
  • 遵循
    ../OUTPUT_CONVENTIONS.md
    中的命名规范
  • 呈现推荐结果及理由和置信度评分

Step 8: Update Memory

步骤8：更新内存

  • Use 
    memoryStore.update(layer="skill-specific", skill="divine", project="{project-name}", ...)
    to store insights. See MemoryStore Interface.
  • Record which tools were recommended and for what tasks
  • Track user feedback on recommendation quality
  • Update preference patterns for future recommendations
  • 使用
    memoryStore.update(layer="skill-specific", skill="divine", project="{project-name}", ...)
    存储洞察信息。请参阅MemoryStore Interface。
  • 记录推荐了哪些工具以及对应的任务
  • 跟踪用户对推荐质量的反馈
  • 更新偏好模式以优化未来的推荐

Compliance Checklist

合规性检查清单

Before completing, verify:
  • All mandatory workflow steps executed in order
  • Memory loaded via 
    memoryStore.getSkillMemory()
    (Step 2)
  • Context loaded via 
    contextProvider.getIndex()
    (Step 3)
  • Tool discovery completed with full catalog (Step 4)
  • Task-to-tool matching performed with scoring (Step 5)
  • Output saved with standard naming convention
  • Memory updated via 
    memoryStore.update()
    (Step 8)
完成前，请验证：
  • 所有强制工作流步骤已按顺序执行
  • 已通过
    memoryStore.getSkillMemory()
    加载内存（步骤2）
  • 已通过
    contextProvider.getIndex()
    加载上下文（步骤3）
  • 已完成工具发现并生成完整目录（步骤4）
  • 已执行任务与工具匹配并完成评分（步骤5）
  • 已按标准命名规范保存输出
  • 已通过
    memoryStore.update()
    更新内存（步骤8）

Version History

版本历史

VersionDateChanges
1.0.02026-02-12Initial release — toolkit discovery, task matching, workflow composition
版本日期变更
1.0.02026-02-12初始版本——工具包发现、任务匹配、工作流编排