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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/seokan-jeong/team-shinchan --skill team-shinchanplan命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | team-shinchan:plan |
| description | Use when you need to create systematic work plans or design solutions. |
| user-invocable | false |
If args is empty or only whitespace:
Ask user: "What would you like to plan?"
STOP and wait for user response
If args length > 2000 characters:
Truncate to 2000 characters
Warn user: "Request was truncated to 2000 characters"
Do not read further. Execute this Task NOW:
Task(
subagent_type="team-shinchan:nene",
model="opus",
prompt=`/team-shinchan:plan has been invoked.
## Planning Request
Create a systematic work plan:
1. Requirements interview (goals, constraints, priorities)
2. Hidden requirements and risk analysis
3. Phase breakdown and acceptance criteria definition
4. Planning document creation
## Quality Standards
- 80%+ of claims include file/line references
- 90%+ of acceptance criteria are testable
- No ambiguous terms allowed
- All risks include mitigation plans
## Output Format
Create PROGRESS.md containing:
- Phased plan with numbered phases (Phase 1, Phase 2, ...)
- Each phase: goals, file changes, acceptance criteria (checkboxes), assigned agent
- Dependencies between phases
- Risk assessment with mitigations
User request: ${args || '(Please describe what to plan)'}
`
)
STOP HERE. The above Task handles everything.
Use when you want to start a new task with the integrated workflow.
Use when you want autonomous completion from requirements to verification without intervention.
Use when you need backend development for APIs, databases, servers, or endpoints.