执行实施规划工作流程，使用计划模板生成设计工件。触发词包括："speckit计划"。
执行实施规划工作流程，使用计划模板生成设计工件。触发词包括："speckit计划"。
/plugin marketplace add forztf/open-skilled-sdd/plugin install open-skilled-sdd@open-skilled-sdd-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
assets/key-rules.mdassets/phase0-research.mdassets/phase1-design.mdassets/plan-template.mdassets/setup-workflow.mdreferences/technical-context.mdscripts/bash/check-prerequisites.shscripts/bash/common.shscripts/bash/create-new-feature.shscripts/bash/setup-plan.shscripts/bash/update-agent-context.shscripts/execute-workflow.ps1scripts/powershell/check-prerequisites.ps1scripts/powershell/common.ps1scripts/powershell/create-new-feature.ps1scripts/powershell/setup-plan.ps1scripts/powershell/update-agent-context.ps1scripts/setup-plan.ps1scripts/update-agent-context.ps1$ARGUMENTS
在继续之前，您必须考虑用户输入（如果不为空）。
设置: 从仓库根目录运行 .specify/scripts/powershell/setup-plan.ps1 -Json 并解析 JSON 以获取 FEATURE_SPEC、IMPL_PLAN、SPECS_DIR、BRANCH。对于参数中的单引号，如 "I'm Groot"，请使用转义语法：例如 'I'''m Groot'（或者如果可能的话使用双引号："I'm Groot"）。
加载上下文: 读取 FEATURE_SPEC 和 .specify/memory/constitution.md。加载 IMPL_PLAN 模板（已复制）。
执行计划工作流程: 遵循 IMPL_PLAN 模板中的结构来：
停止并报告: 命令在阶段 2 规划后结束。报告分支、IMPL_PLAN 路径和生成的工件。
从上述技术上下文中提取未知项:
生成并分发研究代理:
对于技术上下文中的每个未知项:
任务: "研究 {未知项} 用于 {功能上下文}"
对于每个技术选择:
任务: "查找 {技术} 在 {领域} 中的最佳实践"
在 research.md 中整合发现结果，使用格式:
输出: 解决了所有"需要澄清"的 research.md
前提条件: research.md 完成
从功能规格中提取实体 → data-model.md:
从功能需求生成 API 契约:
/contracts/代理上下文更新:
.specify/scripts/powershell/update-agent-context.ps1 -AgentType claude输出: data-model.md、/contracts/*、quickstart.md、代理特定文件
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.