speckit-plan
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseSpec Kit Plan Skill
Spec Kit Plan Skill
When to Use
使用场景
- The feature spec is ready and you need a technical implementation plan.
- 功能规格说明书已准备就绪,需要制定技术实施计划时。
Inputs
输入项
specs/<feature>/spec.md- Repo context and templates
.specify/ - User-provided constraints or tech preferences (if any)
If the spec is missing, ask the user to run speckit-specify first.
specs/<feature>/spec.md- 代码仓库上下文以及模板
.specify/ - 用户提供的约束条件或技术偏好(如有)
如果缺少规格说明书,请先让用户运行speckit-specify命令。
Workflow
工作流
-
Setup: Runfrom repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'''m Groot' (or double-quote if possible: "I'm Groot").
.specify/scripts/bash/setup-plan.sh --json -
Load context: Read FEATURE_SPEC and. Load IMPL_PLAN template (already copied).
.specify/memory/constitution.md -
Execute plan workflow: Follow the structure in IMPL_PLAN template to:
- Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")
- Fill Constitution Check section from constitution
- Evaluate gates (ERROR if violations unjustified)
- Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION)
- Phase 1: Generate data-model.md, contracts/, quickstart.md
- Phase 1: Update agent context by running the agent script
- Re-evaluate Constitution Check post-design
-
Stop and report: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.
-
环境准备:从代码仓库根目录运行,并解析JSON获取FEATURE_SPEC、IMPL_PLAN、SPECS_DIR、BRANCH参数。对于参数中的单引号(例如"I'm Groot"),请使用转义语法:比如'I'''m Groot'(或尽可能使用双引号:"I'm Groot")。
.specify/scripts/bash/setup-plan.sh --json -
加载上下文:读取FEATURE_SPEC和文件,加载已复制的IMPL_PLAN模板。
.specify/memory/constitution.md -
执行规划工作流:按照IMPL_PLAN模板的结构执行以下操作:
- 填写技术上下文(将未知内容标记为"NEEDS CLARIFICATION")
- 依据constitution.md填写合规性检查部分
- 评估准入条件(若违规且无合理解释则触发ERROR)
- 阶段0:生成research.md文件(解决所有NEEDS CLARIFICATION项)
- 阶段1:生成data-model.md、contracts/目录下文件以及quickstart.md
- 阶段1:运行agent脚本更新Agent上下文
- 设计完成后重新评估合规性检查
-
停止并报告:命令在完成阶段2规划后结束。报告分支信息、IMPL_PLAN路径以及生成的产物。
Phases
阶段详情
Phase 0: Outline & Research
阶段0:大纲与调研
-
Extract unknowns from Technical Context above:
- For each NEEDS CLARIFICATION → research task
- For each dependency → best practices task
- For each integration → patterns task
-
Generate and dispatch research agents:text
For each unknown in Technical Context: Task: "Research {unknown} for {feature context}" For each technology choice: Task: "Find best practices for {tech} in {domain}" -
Consolidate findings inusing format:
research.md- Decision: [what was chosen]
- Rationale: [why chosen]
- Alternatives considered: [what else evaluated]
Output: research.md with all NEEDS CLARIFICATION resolved
-
从技术上下文中提取未知项:
- 每个NEEDS CLARIFICATION项对应一个调研任务
- 每个依赖项对应一个最佳实践调研任务
- 每个集成项对应一个模式调研任务
-
生成并分派调研Agent:text
For each unknown in Technical Context: Task: "Research {unknown} for {feature context}" For each technology choice: Task: "Find best practices for {tech} in {domain}" -
将调研结果整理到文件中,格式如下:
research.md- 决策:[所选方案]
- 理由:[选择该方案的原因]
- 备选方案:[评估过的其他方案]
输出:已解决所有NEEDS CLARIFICATION项的research.md文件
Phase 1: Design & Contracts
阶段1:设计与合约
Prerequisites: complete
research.md-
Extract entities from feature spec →:
data-model.md- Entity name, fields, relationships
- Validation rules from requirements
- State transitions if applicable
-
Generate API contracts from functional requirements:
- For each user action → endpoint
- Use standard REST/GraphQL patterns
- Output OpenAPI/GraphQL schema to
/contracts/
-
Agent context update:
- Run
.specify/scripts/bash/update-agent-context.sh <agent_type> - Use the current runtime agent type (e.g., claude, codex, copilot, gemini). Leave empty to update all existing agent files.
- Update the appropriate agent-specific context file
- Add only new technology from current plan
- Preserve manual additions between markers
- Run
Output: data-model.md, /contracts/*, quickstart.md, agent-specific file
前置条件:文件已完成
research.md-
从功能规格说明书中提取实体,生成文件:
data-model.md- 实体名称、字段、关系
- 需求中的验证规则
- 适用的状态转换逻辑
-
根据功能需求生成API合约:
- 每个用户操作对应一个接口
- 使用标准REST/GraphQL模式
- 将OpenAPI/GraphQL schema输出到目录
/contracts/
-
Agent上下文更新:
- 运行
.specify/scripts/bash/update-agent-context.sh <agent_type> - 使用当前运行时的Agent类型(例如claude、codex、copilot、gemini)。留空则更新所有现有Agent文件。
- 更新对应的Agent专属上下文文件
- 仅添加当前计划中的新技术内容
- 保留标记之间的手动添加内容
- 运行
输出:data-model.md、/contracts/下所有文件、quickstart.md、Agent专属文件
Key rules
核心规则
- Use absolute paths
- ERROR on gate failures or unresolved clarifications
- 使用绝对路径
- 若准入条件不通过或存在未解决的待澄清项,触发ERROR
Outputs
输出产物
- (filled implementation plan)
specs/<feature>/plan.md specs/<feature>/research.mdspecs/<feature>/data-model.md- (API schemas)
specs/<feature>/contracts/ specs/<feature>/quickstart.md- Updated agent context file (runtime-specific)
- (已填写完成的实施计划)
specs/<feature>/plan.md specs/<feature>/research.mdspecs/<feature>/data-model.md- (API schema文件)
specs/<feature>/contracts/ specs/<feature>/quickstart.md- 更新后的Agent上下文文件(与运行时相关)
Next Steps
后续步骤
After planning:
- Generate tasks with speckit-tasks.
- Create a checklist with speckit-checklist when a quality gate is needed.
完成规划后:
- 使用speckit-tasks生成任务列表。
- 当需要质量准入检查时,使用speckit-checklist创建检查清单。