From logvalet
Draft a context-aware Backlog issue comment: progress update, inquiry, resolution notice, or escalation — the LLM generates a draft based on the issue's full context and comment history. TRIGGER when: user says "コメント下書き", "draft comment", "コメントを書いて", "返信を作って", "コメントを作成", "comment draft", "コメント草稿", "コメントを下書きして", "issue comment を書いて", "バックログにコメント", "進捗報告コメント", "確認依頼コメント", "解決通知コメント", "コメントで報告したい", "返信案を作って", "エスカレーションコメント", "write a comment", "reply to this issue", "コメントの文面を考えて". DO NOT TRIGGER when: user wants to create a new issue (use issue-create) or wants to update issue fields like status/assignee (use logvalet CLI directly). Workflow: Automatically fetches context via /logvalet:context before drafting.
npx claudepluginhub youyo/claude-plugins --plugin logvaletThis skill uses the workspace's default tool permissions.
`lv issue context` を材料に、LLM がコンテキストに沿ったコメント下書きを生成する。
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
lv issue context を材料に、LLM がコンテキストに沿ったコメント下書きを生成する。
For full logvalet CLI documentation, see the
logvaletskill.
Use logvalet-draft when you need to:
If the user provides a Backlog issue key (e.g., PROJ-123, a URL like *.backlog.com/view/PROJ-123), extract and use it directly.
If no key is provided, ask for it.
Ask the user (if not already clear) what kind of comment they want to write:
This helps the LLM calibrate tone and content.
lv issue context ISSUE_KEY -f json
This returns:
Using the issue context, generate a comment that:
## コメント下書き — ISSUE_KEY
> コンテキスト: 最終更新 N日前、担当者: UserName、ステータス: X
---
<下書き内容>
---
このコメントを投稿しますか？[はい/編集/キャンセル]
If the user wants to edit, revise and re-present.
After user confirmation, write the draft to a temp file and post:
lv issue comment add ISSUE_KEY --content-file /tmp/draft_ISSUE_KEY.md --dry-run
lv issue comment add ISSUE_KEY --content-file /tmp/draft_ISSUE_KEY.md
Always run --dry-run first before posting.
issue context provides comment history — use it to match the thread's existing tone and avoid repeating information already stated/tmp/draft_ISSUE_KEY.md) rather than passing via --content--dry-run before posting