菜单
Triage Linear inbox issues with AI classification. Triggers on "pm triage", "triage inbox", "classify issues", "process inbox", "处理反馈".
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/wuyuxiangX/yux-claude-hub --skill yux-pm-triage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。
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".
正在显示 SKILL.md
基于 SOC 职业分类
| name | yux-pm-triage |
| description | Triage Linear inbox issues with AI classification. Triggers on "pm triage", "triage inbox", "classify issues", "process inbox", "处理反馈". |
| allowed-tools | Read, Write, Glob, Grep, Bash(git:*), Bash(gh:*), mcp__linear__* |
Process inbox issues: classify type, set priority/effort, structure descriptions, and move to Backlog.
Prerequisite: .claude/linear-config.json must exist. If missing, show:
"Please run /yux-linear-init first."
Read .claude/linear-config.json
mcp__linear__list_issue_labels(team: "<team.id>")
Parse labels into categories:
mcp__linear__list_issues(
project: "<project.id>",
state: "Triage",
limit: 20,
orderBy: "createdAt"
)
If empty, report clean inbox and stop.
Display inbox summary table (ID, title, created date) and ask user to process all or select specific items.
For each selected issue, analyze these factors:
Type Detection (keyword-based):
If multiple types match, prefer: Bug > Feature > Improvement > Chore.
Priority Assessment:
Effort Estimation (T-shirt sizing):
For each issue, display:
Ask user to apply, reject, or edit before proceeding.
On confirmation, update the issue in Linear:
mcp__linear__update_issue(
id: "<issue_id>",
description: "<structured_description>",
priority: <priority_number>,
labels: ["<type_label_id>", "<func_label_id>"],
project: "<project.id>",
state: "Backlog"
)
After all items are processed, display summary:
=== Triage Complete ===
Processed: 5 issues
By Type: Bug: 2 | Feature: 2 | Improvement: 1
By Priority: High: 1 | Medium: 3 | Low: 1
Moved to Backlog:
WYX-120 [Bug/High] Login crash on iOS
WYX-121 [Feature/Med] Dark mode support
WYX-122 [Bug/Med] Typo in settings