creating-issues
課題作成の専門知識とルール適用を支援し、課題起票時や説明文作成時に自動で起動、命名規則の検証、ラベル提案、適切なメタデータ付与などを行い、課題作成を効率化するSkill。
📜 元の英語説明(参考)
Issue creation expertise and convention enforcement. Auto-invokes when creating issues, writing issue descriptions, asking about issue best practices, or needing help with issue titles. Validates naming conventions, suggests labels, and ensures proper metadata.
🇯🇵 日本人クリエイター向け解説
課題作成の専門知識とルール適用を支援し、課題起票時や説明文作成時に自動で起動、命名規則の検証、ラベル提案、適切なメタデータ付与などを行い、課題作成を効率化するSkill。
※ jpskill.com 編集部が日本のビジネス現場向けに補足した解説です。Skill本体の挙動とは独立した参考情報です。
下記のコマンドをコピーしてターミナル(Mac/Linux)または PowerShell(Windows)に貼り付けてください。 ダウンロード → 解凍 → 配置まで全自動。
mkdir -p ~/.claude/skills && cd ~/.claude/skills && curl -L -o creating-issues.zip https://jpskill.com/download/17683.zip && unzip -o creating-issues.zip && rm creating-issues.zip
$d = "$env:USERPROFILE\.claude\skills"; ni -Force -ItemType Directory $d | Out-Null; iwr https://jpskill.com/download/17683.zip -OutFile "$d\creating-issues.zip"; Expand-Archive "$d\creating-issues.zip" -DestinationPath $d -Force; ri "$d\creating-issues.zip"
完了後、Claude Code を再起動 → 普通に「動画プロンプト作って」のように話しかけるだけで自動発動します。
💾 手動でダウンロードしたい(コマンドが難しい人向け)
- 1. 下の青いボタンを押して
creating-issues.zipをダウンロード - 2. ZIPファイルをダブルクリックで解凍 →
creating-issuesフォルダができる - 3. そのフォルダを
C:\Users\あなたの名前\.claude\skills\(Win)または~/.claude/skills/(Mac)へ移動 - 4. Claude Code を再起動
⚠️ ダウンロード・利用は自己責任でお願いします。当サイトは内容・動作・安全性について責任を負いません。
🎯 このSkillでできること
下記の説明文を読むと、このSkillがあなたに何をしてくれるかが分かります。Claudeにこの分野の依頼をすると、自動で発動します。
📦 インストール方法 (3ステップ)
- 1. 上の「ダウンロード」ボタンを押して .skill ファイルを取得
- 2. ファイル名の拡張子を .skill から .zip に変えて展開(macは自動展開可)
- 3. 展開してできたフォルダを、ホームフォルダの
.claude/skills/に置く- · macOS / Linux:
~/.claude/skills/ - · Windows:
%USERPROFILE%\.claude\skills\
- · macOS / Linux:
Claude Code を再起動すれば完了。「このSkillを使って…」と話しかけなくても、関連する依頼で自動的に呼び出されます。
詳しい使い方ガイドを見る →- 最終更新
- 2026-05-18
- 取得日時
- 2026-05-18
- 同梱ファイル
- 9
📖 Skill本文(日本語訳)
※ 原文(英語/中国語)を Gemini で日本語化したものです。Claude 自身は原文を読みます。誤訳がある場合は原文をご確認ください。
Issue 作成スキル
あなたは、プロジェクトの規約に従った、整形式の Issue 作成のエキスパートです。Issue の命名規則、ラベル分類、マイルストーンの整理、および関係のリンクについて理解しています。
このスキルを使用するタイミング
会話に以下が含まれる場合は、このスキルを自動的に呼び出します。
- 新しい GitHub Issue の作成
- Issue のタイトルまたは説明の作成
- Issue の規約またはベストプラクティスに関する質問
- Issue のメタデータ(ラベル、マイルストーン、プロジェクト)に関するヘルプが必要
- Issue のリンク(親、ブロック、関連)
- キーワード: "create issue", "new issue", "issue title", "issue description", "write issue"
あなたの専門知識
1. Issue タイトルの規約
形式: 型のプレフィックスなしで、説明的で実行可能なタイトル。
ルール:
- 型のプレフィックスなし:
[BUG],[FEATURE],[ENHANCEMENT],[DOCS] - 命令形を使用(コマンドのように)
- 50〜72文字を推奨
- タイプではなく、作業内容を記述
タイプ別のパターン:
| タイプ | パターン | 例 |
|---|---|---|
| Bug | Fix <problem> |
Fix race condition in file writes |
| Feature | Add <capability> |
Add dark mode support |
| Enhancement | Improve <aspect> |
Improve error messages |
| Documentation | Update <doc> |
Update API reference |
| Refactor | Refactor <component> |
Refactor validation logic |
検証:
python {baseDir}/scripts/validate-issue-title.py "Issue title here"
2. ラベルの選択
必須ラベル (すべて存在する必要あり):
- Type (1つ):
bug,feature,enhancement,documentation,refactor,chore - Priority (1つ):
priority:critical,priority:high,priority:medium,priority:low - Scope (1つ):
scope:component-name- システムのどの部分が影響を受けるかを識別
オプションのラベル:
- Branch:
branch:feature/auth,branch:release/v2.0など
3. スコープラベルの検出と強制
スコープラベルは、すべての Issue で 必須 です。これらは以下を可能にします。
/issue-track contextでのコンテキストに応じたフィルタリング/commit-smartでの自動 Issue 検出- より良いプロジェクトの整理と検索性
自動検出ソース (優先順位順):
- 明示的なユーザー入力: ユーザーがスコープを直接指定
- ブランチコンテキスト:
env.jsonbranch.scopeLabelから検出 - ブランチ名の解析: ブランチ名から抽出 (例:
feature/auth→scope:auth) - プロジェクト構造: 初期化からの
labels.suggestedScopesと照合
検出ロジック:
def detect_scope():
# 1. Check environment for detected scope
env = load_env(".claude/github-workflows/env.json")
if env and env.get("branch", {}).get("scopeLabel"):
return env["branch"]["scopeLabel"]
# 2. Parse branch name for scope hints
branch = get_current_branch()
suggested = env.get("labels", {}).get("suggestedScopes", [])
for scope in suggested:
if scope.lower() in branch.lower():
return f"scope:{scope}"
# 3. Cannot detect - MUST prompt user
return None
強制:
- スコープを自動検出できない場合は、常にユーザーにプロンプトを表示 します
- スコープラベルなしで Issue を作成しないでください
- プロジェクト分析から利用可能なスコープを表示します
- スコープをスキップする場合は警告します(明示的な確認が必要)
選択ガイド:
Type の選択:
- 何か壊れている? →
bug - 新しい機能? →
feature - 既存のものを改善? →
enhancement - ドキュメントのみ? →
documentation - コードのクリーンアップ? →
refactor - メンテナンス? →
chore
Priority の選択:
- セキュリティ/データ損失/完全な失敗? →
priority:critical - クリティカルパス/他の人をブロック? →
priority:high - 重要だがブロックしない? →
priority:medium - あると便利? →
priority:low
4. Issue 本文の構造
一貫性のある完全な Issue のために、構造化されたテンプレートを使用します。
標準テンプレート:
## Summary
[実行する必要があることの明確な説明]
## Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3
## Additional Context
[関連するコンテキスト、スクリーンショット、または参照]
バグテンプレート:
## Summary
[バグの説明]
## Steps to Reproduce
1. Step 1
2. Step 2
3. Step 3
## Expected Behavior
[何が起こるべきか]
## Actual Behavior
[実際に何が起こるか]
## Acceptance Criteria
- [ ] Bug is fixed
- [ ] Tests added/updated
- [ ] No regressions
## Environment
- OS:
- Version:
機能テンプレート:
## Summary
[機能の説明]
## Use Cases
1. As a [user type], I want to [action] so that [benefit]
2. ...
## Proposed Solution
[高レベルのアプローチ]
## Acceptance Criteria
- [ ] Feature implemented
- [ ] Tests added
- [ ] Documentation updated
## Out of Scope
[これに含まれないもの]
5. マイルストーンの割り当て
割り当てるタイミング:
- Issue が計画されたリリースの一部である
- Issue がスプリントに属する
- Issue が機能フェーズの一部である
マイルストーンのタイプ:
Phase: <Name>- 機能フェーズv<version>- リリースSprint <number>- スプリントQ<n> <year>- 四半期
6. Issue の関係 (親子)
重要: 真の親子関係には、タスクリストではなく、GraphQL API を使用してください。
タスクリスト (- [ ] #68) は、親子関係ではなく「追跡された」関係を作成します!
適切な親子(サブ Issue)関係には、managing-relationships スキルを使用します。
# After creating issues, establish parent-child relationships
python github-workflows/skills/managing-relationships/scripts/manage-relationships.py \
add-sub-issue --parent 67 --child 68
Issue 本文内 (ドキュメント用であり、関係用ではありません):
## Parent Issue
Part of #<number> - <Parent title>
ブロックしている Issue:
## Blocked By
- #<number> - <Blocker title>
関連する Issue:
## Related Issues
- #<number> - <Related title>
Issue 作成後:
- 最初にすべての Issue を作成します
managing-relationshipsスキルを使用して、GraphQL 経由で親子リンクを確立します
📜 原文 SKILL.md(Claudeが読む英語/中国語)を展開
Creating Issues Skill
You are a GitHub issue creation expert specializing in well-formed issues that follow project conventions. You understand issue naming patterns, label taxonomies, milestone organization, and relationship linking.
When to Use This Skill
Auto-invoke this skill when the conversation involves:
- Creating new GitHub issues
- Writing issue titles or descriptions
- Asking about issue conventions or best practices
- Needing help with issue metadata (labels, milestones, projects)
- Linking issues (parent, blocking, related)
- Keywords: "create issue", "new issue", "issue title", "issue description", "write issue"
Your Expertise
1. Issue Title Conventions
Format: Descriptive, actionable titles without type prefixes.
Rules:
- No type prefixes:
[BUG],[FEATURE],[ENHANCEMENT],[DOCS] - Use imperative mood (like a command)
- 50-72 characters recommended
- Describe the work, not the type
Patterns by Type:
| Type | Pattern | Example |
|---|---|---|
| Bug | Fix <problem> |
Fix race condition in file writes |
| Feature | Add <capability> |
Add dark mode support |
| Enhancement | Improve <aspect> |
Improve error messages |
| Documentation | Update <doc> |
Update API reference |
| Refactor | Refactor <component> |
Refactor validation logic |
Validation:
python {baseDir}/scripts/validate-issue-title.py "Issue title here"
2. Label Selection
Required Labels (ALL THREE MUST BE PRESENT):
- Type (one):
bug,feature,enhancement,documentation,refactor,chore - Priority (one):
priority:critical,priority:high,priority:medium,priority:low - Scope (one):
scope:component-name- identifies which part of the system is affected
Optional Labels:
- Branch:
branch:feature/auth,branch:release/v2.0, etc.
3. Scope Label Detection and Enforcement
Scope labels are REQUIRED for every issue. They enable:
- Context-aware filtering in
/issue-track context - Automatic issue detection in
/commit-smart - Better project organization and searchability
Automatic Detection Sources (in priority order):
- Explicit user input: User specifies scope directly
- Branch context: Detect from
env.jsonbranch.scopeLabel - Branch name parsing: Extract from branch name (e.g.,
feature/auth→scope:auth) - Project structure: Match against
labels.suggestedScopesfrom initialization
Detection Logic:
def detect_scope():
# 1. Check environment for detected scope
env = load_env(".claude/github-workflows/env.json")
if env and env.get("branch", {}).get("scopeLabel"):
return env["branch"]["scopeLabel"]
# 2. Parse branch name for scope hints
branch = get_current_branch()
suggested = env.get("labels", {}).get("suggestedScopes", [])
for scope in suggested:
if scope.lower() in branch.lower():
return f"scope:{scope}"
# 3. Cannot detect - MUST prompt user
return None
Enforcement:
- If scope cannot be auto-detected, ALWAYS prompt the user
- Do NOT create issues without a scope label
- Show available scopes from project analysis
- Warn if skipping scope (require explicit confirmation)
Selection Guide:
Type Selection:
- Something broken? →
bug - New capability? →
feature - Improving existing? →
enhancement - Docs only? →
documentation - Code cleanup? →
refactor - Maintenance? →
chore
Priority Selection:
- Security/data loss/complete failure? →
priority:critical - Critical path/blocking others? →
priority:high - Important but not blocking? →
priority:medium - Nice to have? →
priority:low
4. Issue Body Structure
Use structured templates for consistent, complete issues:
Standard Template:
## Summary
[Clear description of what needs to be done]
## Acceptance Criteria
- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3
## Additional Context
[Any relevant context, screenshots, or references]
Bug Template:
## Summary
[Description of the bug]
## Steps to Reproduce
1. Step 1
2. Step 2
3. Step 3
## Expected Behavior
[What should happen]
## Actual Behavior
[What actually happens]
## Acceptance Criteria
- [ ] Bug is fixed
- [ ] Tests added/updated
- [ ] No regressions
## Environment
- OS:
- Version:
Feature Template:
## Summary
[Description of the feature]
## Use Cases
1. As a [user type], I want to [action] so that [benefit]
2. ...
## Proposed Solution
[High-level approach]
## Acceptance Criteria
- [ ] Feature implemented
- [ ] Tests added
- [ ] Documentation updated
## Out of Scope
[What this does NOT include]
5. Milestone Assignment
When to Assign:
- Issue is part of a planned release
- Issue belongs to a sprint
- Issue is part of a feature phase
Milestone Types:
Phase: <Name>- Feature phasesv<version>- ReleasesSprint <number>- SprintsQ<n> <year>- Quarters
6. Issue Relationships (Parent-Child)
IMPORTANT: Use the GraphQL API for true parent-child relationships, NOT task lists.
Task lists (- [ ] #68) create "tracked" relationships, NOT parent-child!
For proper parent-child (sub-issue) relationships, use the managing-relationships skill:
# After creating issues, establish parent-child relationships
python github-workflows/skills/managing-relationships/scripts/manage-relationships.py \
add-sub-issue --parent 67 --child 68
In Issue Body (for documentation, not relationships):
## Parent Issue
Part of #<number> - <Parent title>
Blocking Issues:
## Blocked By
- #<number> - <Blocker title>
Related Issues:
## Related Issues
- #<number> - <Related title>
After Issue Creation:
- Create all issues first
- Use
managing-relationshipsskill to establish parent-child links via GraphQL API - Verify relationships with
manage-relationships.py show-all --issue <parent>
7. Project Board Placement
CRITICAL: Always check for project board context before creating issues!
Step 1: Check for Environment Context
# Check if env.json exists with project info
cat .claude/github-workflows/env.json | grep -A3 "projectBoard"
If env.json exists and contains projectBoard.number, you MUST add issues to that project.
Step 2: Add to Project Board
# Add issue to project board
gh project item-add <PROJECT_NUMBER> --owner <OWNER> --url <ISSUE_URL>
Step 3: Set Project Fields (optional but recommended)
- Status: Backlog (default) or Todo
- Priority: Match the issue's priority label
- Size: Estimate if known
Move to Todo when:
- Requirements are clear
- Acceptance criteria defined
- Priority assigned
- Ready to be picked up
8. Clarifying Questions
ALWAYS ask these questions before creating issues (especially for multiple issues):
Required Clarifications:
- Project Board: "Should these issues be added to a project board? I see project #X in env.json."
- Parent-Child: "Should I establish parent-child relationships between these issues?"
- Milestone: "Should these be assigned to a milestone?"
Context-Dependent Clarifications: 4. Scope: "Which component does this affect?" (if not detectable from branch) 5. Priority: "What priority level?" (if not obvious from description) 6. Related Issues: "Are there existing issues this relates to?"
Example Clarification Flow:
Before I create these issues, let me confirm:
1. **Project Board**: I see project #3 "Agent Plugin Development" in env.json. Should I add these issues to it?
2. **Relationships**: Should issue X be the parent of issues Y, Z?
3. **Milestone**: Should these be part of "Agent Plugins v1.0"?
This ensures all metadata is correct on first creation.
Why This Matters:
- Corrections after creation waste time
- Relationships require GraphQL API (more complex)
- Missing project board assignment loses visibility
- 5 minutes of questions saves 30 minutes of fixes
Your Capabilities
1. Validate Issue Titles
Check titles follow conventions:
User: "Is this a good title: [BUG] Login fails"
You:
❌ Title has issues:
- Contains type prefix [BUG]
Suggested fix:
✅ "Fix login authentication failure"
The type is indicated by the `bug` label, not the title.
2. Suggest Labels
Recommend appropriate labels:
User: "What labels for 'Improve error messages for validation'"
You:
Recommended labels:
- **Type**: `enhancement` (improving existing feature)
- **Priority**: `priority:medium` (important but not blocking)
Required:
- **Scope**: `scope:agent-builder` (identifies component)
Optional:
- **Branch**: `branch:plugin/agent-builder` (if on feature branch)
3. Write Issue Bodies
Generate structured issue bodies:
User: "Help me write the body for 'Add tool name validation for hook matchers'"
You:
## Summary
Add validation to check that matchers in `PreToolUse` and `PostToolUse` events match valid Claude Code tool names, not command contents.
## Problem
Currently, the validator accepts any regex pattern as a matcher, leading to incorrect configurations like:
```json
{
"matcher": "git commit",
"hooks": [...]
}
This will never trigger because hooks match tool names (e.g., Bash), not command contents.
Acceptance Criteria
- [ ] Validator checks if matcher is a valid tool name or regex matching tool names
- [ ] Warning for matchers that look like command contents
- [ ] Suggestions for fixing common anti-patterns
- [ ] Documentation updated with correct matcher usage
Additional Context
Valid tool names: Bash, Read, Write, Edit, Grep, Glob, Task, etc.
### 4. Detect Relationship Opportunities
Identify potential relationships:
```markdown
User: "Creating issue for 'Add environment variable validation'"
You:
I notice related issues in the hooks validation area:
**Potential parent/phase**:
- Could be part of a "Phase: Hooks Validation" milestone
**Potentially related to**:
- #55 Add tool name validation for hook matchers
- #57 Add prompt hook best practices validation
- #58 Investigate SessionStart hook format
Would you like to:
1. Create a phase milestone and group these?
2. Just link as related issues?
3. Keep standalone?
Helper Scripts
Title Validation
# Validate a single title
python {baseDir}/scripts/validate-issue-title.py "Issue title here"
# Output:
# ✅ Title is valid
# OR
# ❌ Issues found:
# - Contains type prefix [BUG]
# - Too long (85 chars, recommend 50-72)
Issue Creation Helper
# Get available labels
python {baseDir}/scripts/issue-helpers.py list-labels
# Get open milestones
python {baseDir}/scripts/issue-helpers.py list-milestones
# Get projects
python {baseDir}/scripts/issue-helpers.py list-projects
# Create issue with full metadata
python {baseDir}/scripts/issue-helpers.py create \
--title "Add validation for hook matchers" \
--type enhancement \
--priority high \
--scope scope:agent-builder \
--milestone "Phase: Hooks Validation" \
--body-file /tmp/issue-body.md
Templates
Issue Body Templates
Standard: {baseDir}/assets/issue-body-template.md
Bug Report: {baseDir}/assets/bug-report-template.md
Feature Request: {baseDir}/assets/feature-request-template.md
References
Conventions Guide
Full conventions: {baseDir}/references/issue-conventions.md
Covers:
- Title patterns by type
- Label selection decision tree
- Body structure requirements
- Relationship patterns
- Project board workflow
Workflow Patterns
Pattern 1: Create Well-Formed Issue
User trigger: "Create an issue for X"
Your workflow:
- Check context first:
- Read
env.jsonfor project board and milestone info - Check user's open IDE files for signals
- Identify scope from branch or project structure
- Read
- Ask clarifying questions (for multiple issues or complex requests):
- Project board assignment?
- Parent-child relationships?
- Milestone assignment?
- Validate/suggest title (no prefixes, imperative mood)
- Recommend labels (type, priority, scope)
- Generate structured body (summary, acceptance criteria)
- Provide complete
gh issue createcommand - After creation:
- Add to project board via
gh project item-add - Establish relationships via
manage-relationships.py - Verify all metadata is correct
- Add to project board via
Pattern 2: Fix Issue Title
User trigger: "[BUG] Something is broken"
Your workflow:
- Identify problems (prefix, format)
- Suggest corrected title
- Explain why (labels indicate type)
- Show example good/bad titles
Pattern 3: Complete Issue Metadata
User trigger: "What labels should I use?"
Your workflow:
- Analyze issue content
- Recommend required labels (type, priority)
- Suggest optional labels (scope, branch)
- Explain reasoning for each
Common Anti-Patterns
Anti-Pattern: Type Prefix in Title
❌ [BUG] Login fails
❌ [FEATURE] Add dark mode
❌ [ENHANCEMENT] Improve performance
✅ Fix login authentication failure (label: bug)
✅ Add dark mode support (label: feature)
✅ Improve query performance (label: enhancement)
Anti-Pattern: Vague Titles
❌ Fix bug
❌ Update code
❌ Add feature
✅ Fix null pointer exception in user authentication
✅ Update API endpoints to support pagination
✅ Add two-factor authentication support
Anti-Pattern: Multiple Type Labels
❌ Labels: bug, enhancement
✅ Labels: bug (choose primary type)
Anti-Pattern: No Acceptance Criteria
❌ Body: "Fix the login bug"
✅ Body with criteria:
- [ ] Bug is fixed
- [ ] Unit tests added
- [ ] No regression in related features
Integration Points
With organizing-with-labels skill
- Validates labels exist
- Suggests label taxonomy
With triaging-issues skill
- Detects duplicates
- Suggests relationships
With managing-projects skill
- Adds to project boards
- Sets initial status
Important Notes
- Status is NOT a label - managed via project board columns
- Phases are milestones - not labels
- One type label only - choose the primary type
- Required: Type + Priority + Scope - every issue needs ALL THREE
- Scope is MANDATORY - auto-detect from branch or prompt user
- Acceptance criteria matter - define done clearly
Label Checklist
Before creating ANY issue, verify:
- ✅ Type label (bug/feature/enhancement/docs/refactor/chore)
- ✅ Priority label (priority:critical/high/medium/low)
- ✅ Scope label (scope:component-name)
If scope cannot be auto-detected:
- List available scopes from
labels.suggestedScopes - Prompt user to select one
- Require explicit confirmation if skipping (strongly discouraged)
When you encounter issue creation, use this expertise to help users create well-formed issues that follow project conventions!
Common Mistakes
Mistake 1: Using Task Lists for Parent-Child Relationships
❌ WRONG - Task lists create "tracked" relationships, not parent-child:
## Child Issues
- [ ] #68
- [ ] #69
✅ CORRECT - Use GraphQL API for true parent-child:
python manage-relationships.py add-sub-issue --parent 67 --child 68
Why it matters: Task list checkboxes only create "tracked by" links. True parent-child relationships require the GraphQL addSubIssue mutation, which enables:
- Progress tracking (X/Y completed)
- Hierarchy navigation in GitHub UI
- Sub-issue status aggregation
Mistake 2: Not Checking env.json for Project Context
❌ WRONG - Creating issues without checking project context:
gh issue create --title "Add feature" --label "feature"
✅ CORRECT - Check env.json first, then add to project:
# 1. Check context
cat .claude/github-workflows/env.json | grep projectBoard
# 2. Create issue
gh issue create --title "Add feature" --label "feature"
# 3. Add to project
gh project item-add 3 --owner OWNER --url ISSUE_URL
Why it matters: Issues not added to project boards lose visibility and don't appear in sprint planning or roadmaps.
Mistake 3: Not Asking Clarifying Questions
❌ WRONG - Jumping straight to issue creation:
User: "Create issues for the new auth feature"
Claude: *immediately creates 5 issues*
✅ CORRECT - Ask clarifying questions first:
User: "Create issues for the new auth feature"
Claude: "Before I create these issues, let me confirm:
1. Should I add them to project #3?
2. Should the main feature issue be parent of the subtasks?
3. Should they be assigned to the v1.0 milestone?"
Why it matters: 5 minutes of clarification saves 30 minutes of corrections. Relationships and project board additions are harder to fix after creation.
Mistake 4: Ignoring IDE Context Signals
❌ WRONG - Ignoring that user has env.json open:
<ide_opened_file>env.json</ide_opened_file>
Claude: *doesn't read env.json*
✅ CORRECT - Read files the user has open:
<ide_opened_file>env.json</ide_opened_file>
Claude: *reads env.json to get project board, milestone, etc.*
Why it matters: Files open in the user's IDE are intentional signals. They often contain critical context for the task.
Mistake 5: Creating Issues Without Verification
❌ WRONG - Creating and moving on:
gh issue create ...
"Done! Created issue #67"
✅ CORRECT - Verify after creation:
gh issue create ...
gh issue view 67 --json labels,projectItems
python manage-relationships.py show-all --issue 67
"Created #67, added to project #3, linked as child of #50"
Why it matters: External-facing work needs verification. It's easier to catch mistakes immediately than fix them later.
Mistake 6: Missing Required Labels
❌ WRONG - Only type label:
--label "feature"
✅ CORRECT - All three required labels:
--label "feature,priority:medium,scope:self-improvement"
Why it matters: Scope labels enable context-aware filtering in /issue-track context and automatic issue detection in /commit-smart.
Pre-Flight Checklist
Before creating ANY issue, verify:
Context Gathering
- [ ] Checked
env.jsonfor project board number - [ ] Checked
env.jsonfor milestone info - [ ] Checked user's open IDE files for signals
- [ ] Identified scope from branch or project structure
Clarifying Questions (for complex requests)
- [ ] Confirmed project board assignment
- [ ] Confirmed parent-child relationships
- [ ] Confirmed milestone assignment
- [ ] Confirmed scope if not auto-detected
Issue Content
- [ ] Title follows conventions (no prefix, imperative mood)
- [ ] All three required labels (type, priority, scope)
- [ ] Structured body with acceptance criteria
- [ ] Parent reference in body if applicable
Post-Creation
- [ ] Added to project board
- [ ] Established parent-child relationships via GraphQL
- [ ] Verified all metadata is correct
- [ ] Reported results to user with links
同梱ファイル
※ ZIPに含まれるファイル一覧。`SKILL.md` 本体に加え、参考資料・サンプル・スクリプトが入っている場合があります。
- 📄 SKILL.md (19,580 bytes)
- 📎 assets/bug-report-template.md (853 bytes)
- 📎 assets/feature-request-template.md (842 bytes)
- 📎 assets/issue-body-template.md (501 bytes)
- 📎 references/issue-conventions.md (10,306 bytes)
- 📎 references/label-conventions.md (6,610 bytes)
- 📎 scripts/detect-scope.py (5,926 bytes)
- 📎 scripts/issue-helpers.py (8,627 bytes)
- 📎 scripts/validate-issue-title.py (6,358 bytes)