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 issue-triagegit 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/issue-triage)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/issue-triage"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/issue-triage/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/issue-triage"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/issue-triage.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 | $0.00070 | $0.01693 |
| Opus 5 | $0.00035 | $0.00847 |
| Sonnet 5 | $0.00014 | $0.00339 |
| Haiku 4.5 | $0.00007 | $0.00169 |
Grade A, and why
issue-triage 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用户收到了一个 GitHub Issue(bug 报告、疑问、feature request),需要 AI 协助分析问题、判断是否要做、起草回复。AI 全程主导推进,用户只在关键节点做判断。
核心原则
- 先诊断后开口 — 没看完代码不下结论,没找到根因不定性
- 对用户诚实 — 是 bug 就认,是架构限制就说清楚,不甩锅也不画饼
- 量化成本 — "成本高"不是结论,要说清楚高在哪:改几个文件、涉及哪些模块、有没有测试条件
- 给替代方案 — 不做不等于不管,要告诉用户现在怎么绕过
工作流程
第 1 步:获取 Issue 内容
目标: 拿到 issue 的完整信息。
方法:
- 用户提供 issue 链接或仓库地址
- 通过
gh issue view或 WebFetch 获取 issue 详情 - 提取关键信息:用户环境、复现步骤、期望行为、实际行为、用户的猜测
输出: 向用户简要转述 issue 内容,确认理解无误。
禁止: 只看标题就开始分析。必须读完 issue 全文。
第 2 步:代码诊断
目标: 在代码中找到根因。
方法:
- 从 issue 描述中提取关键词(功能名、错误信息、页面名等)
- 在代码中定位相关链路:从前端入口 → IPC 调用 → 后端处理 → 底层实现
- 画出完整调用链,标注每个环节的文件和行号
- 确认根因:代码哪里出了问题,或者代码为什么不支持用户的场景
输出: 向用户展示:
- 完整调用链(文件 + 行号)
- 根因的一句话总结
- 必要时附关键代码片段
禁止:
- 没读代码就猜原因
- 只看一个文件就下结论(要追完整条链路)
第 3 步:定性
目标: 判断这个 issue 属于哪种类型。
| 类型 | 判断标准 | 应对策略 |
|---|---|---|
| Bug | 在产品设计范围内,行为不符合预期 | 排期修复 |
| 架构限制 | 用户场景超出产品的设计前提 | 解释现状,评估是否值得扩展 |
| Feature Request | 产品本身没问题,用户想要新能力 | 评估成本和优先级 |
| 使用问题 | 用户操作方式不对,但产品可以做得更友好 | 回复指引,考虑优化体验 |
关键判断: 区分"该做但做错了"(bug)和"没打算做"(架构限制/feature)。
输出: 向用户说明定性结论和理由,等用户确认后再往下走。
第 4 步:决策(做还是不做)
目标: 基于根因和定性,给出做/不做的建议。
评估四个维度
- 改动范围 — 改几行 / 改一个模块 / 新增一个模块
- 影响面 — 只动一个文件 / 要改多个文件的调用链 / 要重构
- 测试条件 — 有没有环境能复现和验证(没环境 = 高风险)
- 用户绕过成本 — 用户自己能不能用其他方式解决
决策矩阵
| 改动范围 | 有测试条件 | 用户可绕过 | 建议 |
|---|---|---|---|
| 小(几行) | 有 | — | 直接修 |
| 中(一个模块) | 有 | — | 排期做 |
| 大(新模块/重构) | 有 | 否 | 评估后排期 |
| 大(新模块/重构) | 没有 | 是 | 记下需求,暂不做 |
| 任意 | 没有 | 是 | 告知绕过方案,需求记下 |
输出: 向用户说明建议和理由。如果建议不做,要量化成本(改几个文件、涉及哪些模块、为什么没法测)。
等用户确认决策后,再进入回复环节。
第 5 步:起草回复
目标: 写一条专业、得体、有信息量的 issue 回复。
回复结构(三层)
- 解释场景定位 — 这个功能是为什么场景设计的,让用户理解"为什么当前不支持"
- 给出实际影响 — 对用户来说,没有这个功能影响大不大,有没有替代方案
- 说明后续计划 — 如果做,给方向;如果不做,诚实说明成本和原因
语气原则
- 感谢反馈 — 用户花时间提 issue 值得尊重
- 不甩锅 — 不说"你用错了",说"这个场景我们还没覆盖到"
- 给具体建议 — 不只说"不行",要告诉用户现在怎么办
- 量化成本 — 让用户理解不是不想做,是客观上成本高
回复模板
Hi @{用户名},感谢反馈!
**1. 功能定位**
{这个功能是为什么场景设计的,为什么当前不支持用户的场景}
**2. 对你的实际影响**
{用户现在能不能绕过,怎么绕过,核心功能是否受影响}
**3. 关于{用户期望的能力}**
{成本说明 + 后续计划}
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 · 159 lines · 70 tokens per session scan A 36b7f9d1feab
issue-triage is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,693 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
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
browse-flows
Browse Power Automate environments and flows interactively. Use when the user wants to browse, list, or explore their flows and environments.
operating-cadence
Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…
status
Display current FIRE project status and validate integrity of intents, work items, and runs.