一键导入
spec-sequential
Use after /dream-team:plan to write a sequential execution spec. No arguments needed — picks up conversation context from the brainstorming session.
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。
菜单
Use after /dream-team:plan to write a sequential execution spec. No arguments needed — picks up conversation context from the brainstorming session.
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。
基于 SOC 职业分类
Use when the user wants to execute an implementation plan. Reads a spec file, detects the execution mode (sequential, delegated, or team) from frontmatter, and runs the appropriate strategy. Pass the spec file path as an argument.
Use after /dream-team:plan to write a delegated execution spec (orchestrator + sub-agents). No arguments needed — picks up conversation context from the brainstorming session.
Use after /dream-team:plan to write a team execution spec (parallel Claude instances). No arguments needed — picks up conversation context from the brainstorming session.
Use when the user wants to build something new or plan a feature. Collaborative brainstorming that explores requirements, constraints, and approach through natural dialogue before any spec is written.
Use when encountering a bug, test failure, unexpected behavior, or when the user asks for help debugging. Hypothesis-driven — reproduce, investigate, fix, verify. Standalone — works outside the plan/spec/build workflow.
| name | spec-sequential |
| description | Use after /dream-team:plan to write a sequential execution spec. No arguments needed — picks up conversation context from the brainstorming session. |
| hooks | {"Stop":[{"hooks":[{"type":"command","command":"node ${CLAUDE_PLUGIN_ROOT}/hooks/validate_spec_exists.js --directory specs --extension .md"},{"type":"command","command":"node ${CLAUDE_PLUGIN_ROOT}/hooks/validate_spec_sections.js --directory specs"}]}]} |
Convert the brainstorming conversation into a formal spec file for sequential execution — single session, no sub-agents, tasks run one at a time.
Prerequisites: This skill assumes /dream-team:plan has already been run in this session. If the conversation has no brainstorming context (no discussed requirements, no confirmed approach, no validated task breakdown), stop and tell the user: "No brainstorming context found. Run /dream-team:plan <prompt> first to explore requirements and design."
${CLAUDE_PLUGIN_ROOT}/templates/spec-template.md and the spec writing guide at ${CLAUDE_PLUGIN_ROOT}/templates/spec-writing-guide.md. Follow the guide's filename format, ambiguity elimination, and git instructions.mode: sequential and spec-version: 1.playwright: true if the brainstorming decided to use Playwright MCP, otherwise playwright: false.frontend-design: true if the brainstorming discussed frontend/UI work and design direction, otherwise frontend-design: false.frontend-design: true, fill in the ## Design Direction section with the aesthetic style, stack, component libraries, and design notes from the brainstorming conversation. Auto-suggest component libraries based on the chosen stack if not explicitly discussed.## Cleanup section with any teardown commands needed (stop servers, remove temp files). Use "N/A" if nothing to clean up.specs/YYYY-MM-DD-<descriptive-kebab-case>.md using today's date.Assigned To, Agent Type, Background, or Parallel fields**Files** field listing exactly which files it creates or modifies, prefixed with creates: or modifies:. Review and validation tasks may omit this field.After saving and committing the spec, output:
Spec written (sequential mode)
File: specs/YYYY-MM-DD-<name>.md
Tasks: <number of tasks>
Complexity: <simple | medium | complex>
Execute with: /dream-team:build specs/YYYY-MM-DD-<name>.md