菜单
GitHub issue creation skill. Analyzes the entire codebase impact based on user request, then creates a structured issue with AI-verified/human-judgment-needed/caution sections. /issue "issue description" Trigger: "/issue", "이슈 만들어", "issue 만들자", "깃헙 이슈"
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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/team-attention/hoyeon --skill issue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。
基于 SOC 职业分类
正在显示 SKILL.md
| name | issue |
| description | GitHub issue creation skill. Analyzes the entire codebase impact based on user request, then creates a structured issue with AI-verified/human-judgment-needed/caution sections. /issue "issue description" Trigger: "/issue", "이슈 만들어", "issue 만들자", "깃헙 이슈" |
| allowed_tools | ["Read","Grep","Glob","Bash","Agent","AskUserQuestion"] |
| validate_prompt | Must complete with one of: 1. GitHub issue created (URL returned) 2. User cancelled after preview Must NOT: create issue without user confirmation, skip impact analysis. |
Investigate the codebase based on the user's request and create a GitHub issue with clearly defined confidence boundaries.
The text the user typed after /issue is the original request. Preserve it verbatim.
Examples:
/issue Duplicate Shorts URL fetches in YouTube subscription feed/issue Add notification settings tab to Settings page/issue Scheduler occasionally runs twiceIf the input is too vague (e.g., "there's a bug"), ask ONE clarifying question. Otherwise, start investigating immediately.
Perform a full impact analysis based on the user's request. Use Agent to investigate in parallel.
Launch agents in parallel where possible:
Classify all findings into three confidence levels:
Objective facts confirmed through code exploration. No need for human re-verification.
Decision points that AI cannot make on your behalf.
Risks and caveats AI may have missed.
After investigation, show the user a preview of the issue body.
## Request
> {original text the user typed after /issue, verbatim}
## Impact Analysis
### Related Code
- `file:line` — description
- ...
### Scope of Impact
- List of affected modules/features
---
## ✅ AI Verified
> Facts confirmed through code exploration. No further verification needed.
- [ ] Confirmed fact 1
- [ ] Confirmed fact 2
## 🤔 Decision Required
> Decision points requiring human judgment.
- [ ] Decision point 1 — Option A vs B, considerations
- [ ] Decision point 2
## ⚠️ Human Verify
> Risks AI may have missed. Needs human review before and/or after implementation.
- [ ] Verification point 1 — why this needs checking
- [ ] Verification point 2
After showing the preview, confirm with AskUserQuestion:
AskUserQuestion(
question: "Should I create a GitHub issue with this content?",
header: "Issue Preview",
options: [
{ label: "Create", description: "Create the issue as-is" },
{ label: "Edit then create", description: "I want to make changes first" },
{ label: "Cancel", description: "Do not create the issue" }
]
)
Create the issue with gh issue create.
gh issue create --title "Issue title" --body "$(cat <<'EOF'
Issue body
EOF
)"
feat:, fix:, refactor:, chore:, etc. (based on content)Based on the issue content, add matching labels via the --label flag using the table below.
Multiple labels allowed. If no match, create without labels.
| Issue type | Label |
|---|---|
| Bug, error, broken behavior | bug |
| New feature, addition, improvement | enhancement |
| Documentation related | documentation |
| Question, investigation, needs clarification | question |
After creation, return the issue URL to the user.
gh issue create executed and URL returned (or user cancelled)