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-shinchan-implement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。
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.
基于 SOC 职业分类
正在显示 SKILL.md
| name | team-shinchan:implement |
| description | Use when you need quick code implementation for features, bug fixes, or utilities. |
| user-invocable | false |
If args is empty or only whitespace:
Ask user: "What would you like me to implement?"
STOP and wait for user response
If args length > 2000 characters:
Truncate to 2000 characters
Warn user: "Request was truncated to 2000 characters"
Read ${CLAUDE_PLUGIN_ROOT}/agents/_shared/domain-router.json to determine the target agent.
Detection logic (apply in order):
.tsx → frontend)Routing decision:
subagent_type="team-shinchan:aichan"subagent_type="team-shinchan:buriburi"subagent_type="team-shinchan:masao"subagent_type="team-shinchan:bo" (fallback)Before dispatching, run the START → In Progress transition per
agents/_shared/linear-sync.md: detect a Linear issue in args/branch, confirm it
with get_issue, and if real move it to In Progress. No-op if no Linear issue / Linear
MCP unavailable — never block the work.
Do not read further. Execute this Task NOW:
Task(
subagent_type="{detected_agent from Step 2}",
model="sonnet",
prompt=`/team-shinchan:implement has been invoked.
## Implementation Request
Handle coding tasks including:
| Area | Capabilities |
|------|-------------|
| Feature Implementation | New features, functions, classes |
| Bug Fixes | Debugging, error correction |
| Code Modification | Refactoring, updates, changes |
| Utilities | Helper functions, utilities |
| Tests | Unit tests, integration tests |
## Implementation Requirements
- Read existing code first to understand patterns
- Follow project conventions
- Write clean, maintainable code
- Handle errors gracefully
- Keep functions small and focused
- Add comments only for complex logic
## Post-Implementation Verification
After writing code:
1. Run existing tests if available (detect test framework from package.json/config)
2. If tests fail, fix the issues before reporting completion
3. If no tests exist, verify the code compiles/loads without errors
## Output Format
After implementation:
- Summary of changes made
- Files modified with line references
- Test results (pass/fail/skipped)
- Any follow-up recommendations
User request: ${args || '(Please describe what to implement)'}
`
)
After the Task returns successfully, run the FINISH → In Review transition per
agents/_shared/linear-sync.md for the same issue (no-op if not Linear-based), then STOP.
STOP HERE. The above Task handles everything.