メニュー
Sprint planning with capacity calculation and scope suggestion. Triggers on "pm plan", "plan sprint", "sprint planning", "capacity planning", "排期".
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/wuyuxiangX/yux-claude-hub --skill yux-pm-planコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Analyze a blog article's structure to plan optimal image placement, then generate and insert AI images. This is the blog-specific image workflow — it reads a markdown article, identifies where images should go, creates a plan, and generates images that fit each section. Use when the user wants images added to an existing article — e.g., "analyze article images", "suggest images for this post", "generate article images", "分析文章配图", "生成文章配图", "插入文章配图". Do NOT use for standalone image generation (use yux-nano-banana instead). After generating, use yux-blog-oss to upload images to CDN.
Generate images via OpenRouter API with user-selected models. Supports any OpenRouter image model (Gemini, Flux, etc.), prompt optimization, text-to-image, and image editing. Triggers on "generate image", "create image", "draw", "nano banana", "image generation", "生成图片", "画图", "图像生成", "信息卡片".
Commit changes with conventional commit messages and sync to Linear. Triggers on "linear commit", "commit and sync", "save progress", "提交代码".
SKILL.md を表示中
SOC 職業分類に基づく
| name | yux-pm-plan |
| description | Sprint planning with capacity calculation and scope suggestion. Triggers on "pm plan", "plan sprint", "sprint planning", "capacity planning", "排期". |
| allowed-tools | Read, Write, Glob, Grep, Bash(git:*), Bash(gh:*), mcp__linear__* |
Usage: /yux-pm-plan [next|current|cycle-name]
Prerequisite: .claude/linear-config.json must exist. If missing, show:
"Please run /yux-linear-init first."
Read .claude/linear-config.json. Extract team.id and project.id.
mcp__linear__list_cycles(teamId: "<team.id>", type: "next")
mcp__linear__list_cycles(teamId: "<team.id>", type: "current")
mcp__linear__list_issues(
project: "<project.id>",
state: "Backlog,Todo",
limit: 50,
orderBy: "priority"
)
If arg is current, focus on the current cycle for review/adjustment.
cycle_days = (cycle_end - cycle_start).business_days
buffer = 0.2
effective_days = cycle_days * (1 - buffer)
effort_map = {
"XS": 0.25, # 2 hours
"S": 0.5, # 4 hours
"M": 2, # 2 days
"L": 5, # 5 days
"XL": 10 # 10 days
}
Score each issue using the algorithm in ../../references/issue-scoring.md (base score + pm-plan additional bonuses). Sort all backlog issues by score descending.
Assign issues to three categories by filling capacity top-down:
Display the categorized plan with per-issue effort, total days used vs. capacity.
Example output:
=== Sprint Plan: Sprint 24 (Mar 17 - Mar 28) ===
Capacity: 8 effective days (10 business days, 20% buffer)
Must Complete (4.75 days / 60% cap):
WYX-101 [M] Fix auth token refresh score: 190
WYX-98 [S] Update error messages score: 150
WYX-105 [L] Search API endpoint score: 140
Should Complete (2.5 days):
WYX-110 [M] Dashboard filters score: 95
WYX-112 [S] Extension icon update score: 80
Stretch Goals:
WYX-115 [M] Analytics event tracking score: 60
On user confirmation, assign issues to the cycle:
For each issue in accepted scope:
mcp__linear__update_issue(
id: "<issue_id>",
cycle: "<cycle_id>",
assignee: "me"
)
If user requests edits before applying, adjust the scope and recalculate totals.
If the current cycle has incomplete issues, list them with remaining effort estimates. Use AskUserQuestion to offer: auto-carry all to next sprint, review individually, or move all back to backlog.
If the team has no cycles configured, offer time-boxed planning (default 2 weeks) using the same scoring and capacity logic but without cycle assignment in Linear.