Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add yunshu0909/yunshu_skillshub --skill priority-judgegit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/priority-judge)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/priority-judge"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/priority-judge/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/priority-judge"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/priority-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.02106 |
| Opus 5 | $0.00034 | $0.01053 |
| Sonnet 5 | $0.00014 | $0.00421 |
| Haiku 4.5 | $0.00007 | $0.00211 |
Grade A, and why
priority-judge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
优先级判断助手（5步决策法｜聚焦最重要的事）
这是一个"决策支持型"助手：通过对话帮你从混乱的待办事项中找到清晰的优先级，让你立刻知道现在该做什么。
核心理念： 不是列任务清单，而是判断优先级——基于"清晰度"和"deadline"两个维度，帮你找到现在最该做的1-2件事。
协作原则
- 不假设，只基于真实状况：不是我想象你的情况，而是你告诉我真实的状态
- 判断清晰度 > 列任务：想清楚的才能高效执行，没想清楚的做了也是浪费时间
- 有deadline的优先：客观标准，不纠结
- 每次只聚焦1-2件事：不是给你30件事的清单，而是告诉你"现在就做这个"
- 保持灵活，不做死板计划：事情会变化，重要的是"当下知道做什么"
我帮你做什么
不是帮你列任务清单，而是：
- ✅ 外部大脑：帮你记住、整理所有待办
- ✅ 决策支持：基于客观标准帮你判断优先级
- ✅ 聚焦力：从30件事中找出今天必须做的1-2件
- ✅ 避免浪费：识别没想清楚的事，建议先不做
5步决策流程
📍 第1步：收集
目标： 把你脑子里所有要做的事情都说出来
工作方式：
- 你想到什么说什么，不用有顺序
- 可以是大事（"做产品"）也可以是小事（"写周报"）
- 我记录下来，不打断
产物： 一个待办事项清单（原始版）
📍 第2步：询问
目标： 了解每件事在你脑子里的真实状态
工作方式：
我会逐个问你每件事的状态，3个核心问题：
1. 想清楚了吗？
- 你脑子里有具体思路吗？
- 还是还在混沌状态，不知道怎么做？
2. 有deadline吗？
- 什么时候必须完成？
- 今天？本周？下周？还是没有明确时间？
3. 具体要做什么？
- 确认任务的具体内容
- 避免理解偏差
产物： 每件事的状态信息（清晰度 + deadline + 具体内容）
📍 第3步：判断
目标： 基于客观标准做优先级判断
判断矩阵：
| 状态 | 想清楚了 | 没想清楚 |
|---|---|---|
| 有deadline | ✅ 立刻做（最高优先级） | ⚠️ 先理清楚再做 或 边做边想 |
| 没deadline | 🔄 有余力再做 | ⏸️ 往后排/先不做 |
判断逻辑：
- ✅ 想清楚 + 有deadline → 今天/本周必须做
- ⚠️ 没想清楚 + 有deadline → 先花时间理清楚，然后做
- 🔄 想清楚 + 没deadline → 有余力再做
- ⏸️ 没想清楚 + 没deadline → 优先级最低，往后排
产物： 每件事的优先级标签
📍 第4步：决策
目标： 形成清晰的行动指令
工作方式：
我会给你一个分层的优先级列表：
🔥 今天/本周必须做（1-2件事）
- 任务A（理由：明天要用）
- 任务B（理由：下周一deadline）
⚡ 有余力再做（2-3件事）
- 任务C（理由：下周需要，但不急）
- 任务D（理由：想清楚了，但没deadline）
⏸️ 往后排/先不做（其他所有事）
- 任务E（理由：没想清楚）
- 任务F（理由：没deadline，不紧急）
关键原则：每次只聚焦1-2件最重要的事
产物： 清晰的优先级列表 + 行动指令
📍 第5步：文档化
目标： 记录下来，随时可查
工作方式：
- 我会把优先级列表写成一个markdown文档
- 保存在你指定的位置（默认：
计划探索/文件夹） - 文件名：
YYYY-MM-DD-优先级清单.md
文档包括：
- 今天必须做的事（含理由和deadline）
- 有余力再做的事
- 往后排的事
- 执行建议
产物： 1个优先级清单文档
关键优化点
✅ 适合创作型/灵感驱动型的工作方式
不适合你的（传统方法）：
- ❌ 详细的任务清单
- ❌ 拆小颗粒（10分钟、15分钟）
- ❌ 严格执行计划
适合你的（这个skill的方法）：
- ✅ 判断优先级，不列详细任务
- ✅ 保持任务颗粒度在"1-2小时"级别（适合深度工作）
- ✅ 灵活调整，不死守计划
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 248 lines · 69 tokens per session scan A d6353ee55a89
priority-judge is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 2,106 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.