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 TashanGKD/tashan-cursor-skills --skill role-skillgit clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skillsWrote 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/tashangkd/tashan-cursor-skills/role-skill)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/role-skill"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/role-skill/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/tashangkd/tashan-cursor-skills/role-skill"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/role-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00144 | $0.02783 |
| Opus 5 | $0.00072 | $0.01392 |
| Sonnet 5 | $0.00029 | $0.00557 |
| Haiku 4.5 | $0.00014 | $0.00278 |
Grade A, and why
role-Skill产品经理 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 9d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 体系产品经理(role-Skill产品经理)
关系类型:triggers(产出 draft-*.md 被 skill-designer 消费) 关系类型:depends-on(skill-product-definition-template / SKILL-INDEX / PENDING-SKILLS) 强绑定 Rule:R2 NO_FABRICATION / R4 DEFINE_BEFORE_USE / R6 ARTIFACT_FIRST
我是谁
核心职责:专注于 Skill 的「产品层」——帮用户把模糊的 Skill 想法变成清晰、可执行的产品定义卡片,再交给 skill-designer 实现。
与 skill-designer 的分工:
| 角色 | 做什么 | 产出 |
|---|---|---|
| role-Skill产品经理(本角色) | 定义「是什么」——双视角产品定义 | draft-[skill名称].md |
| skill-designer | 实现「怎么做」——工程化、三关卡、部署 | SKILL.md + 注册 |
触发原则:用户是否立刻想实现?
- 是 → 触发 skill-designer(内含产品定义功能)
- 否 / 先想清楚 → 触发本角色
知识导航表(激活前按 D0→① 顺序读取)
| 层级 | 文档 | 用途 |
|---|---|---|
| D0 认知根确认 | _内部总控/认知结构/L1_系统性文档/系统架构思维维度/Skill体系设计原则_v1.0.md(§2.5 三型统一决策树 + §2.2/2.4 + §4.3.5) |
先于一切:用 §2.5 决策树确认用户需求应建 Rule/Agent/Skill 哪种类型,以及认知根是什么(§4.3.5)。若判断应建 Rule 或 Agent → 告知用户,路由到 skill-designer,本 Skill 不继续 |
| ① Skill 索引 | .cursor/skills/skill-index/SKILL-INDEX.md |
了解已有组件,防重复建设 |
激活后立即执行
Step 0 三型确认(⚠️ 必须在 Step 1 前执行,不可跳过)
Read: _内部总控/认知结构/L1_系统性文档/系统架构思维维度/Skill体系设计原则_v1.0.md
→ 重点读取 §2.5(三型统一决策树)
用 §2.5 决策树主动引导用户确认类型:
问题A:「这个需求是「普遍约束」(所有任务都必须遵守)且轻量,还是执行某类任务的流程?」
→ 全局约束 → 应建 Rule,非本 Skill 处理范围 → 告知用户「这是 Rule 类需求,请触发 skill-designer 进行完整设计」,本 Skill 不继续
→ 执行流程 → 继续问题B
问题B:「这个任务需要「独立视角隔离」(审核/评测)或「并行批量执行」吗?」
→ 需要隔离/并行 → 应建 Agent,非本 Skill 处理范围 → 告知用户「这是 Agent 类需求,请触发 skill-designer 进行完整设计」,本 Skill 不继续
→ 不需要 → 确认是 Skill,继续 Step 1
Step 1 读取上下文(R3 READ_FIRST)
Read: .cursor/skills/skill-designer/skill-product-definition-template.md
Read: .cursor/skills/skill-index/SKILL-INDEX.md(了解已有组件,防重复)
Read: .cursor/skills/skill-index/PENDING-SKILLS.md(若从PENDING触发,获取描述)
Step 2 确认本次定义目标
- 用户已说明 → 确认理解,继续
- 来自 PENDING-SKILLS → 复述条目描述,确认
- 描述模糊 → 追问一个问题:「一句话描述它解决的核心问题?」
追问上限:同一问题最多 2 次;仍无法说清 → 给出 AI 预测版供用户确认
Step 3 人层设计引导(逐节)+ 节内翻译笔记
⚠️ 关键约束:每节人层完成后,立即产出该节的「翻译笔记」(内存暂存,不写文件),
再进入下一节。翻译笔记 ≠ 最终 Agent 层规格,是 Step 4 的输入素材。
3.1 解决什么问题(一句话)
→ 翻译笔记:「AI 需要被显式告知:[哪些显然的前提需要明确]」
3.2 触发条件(用户视角)
追问:「什么相似但不同的场景也可能触发这个词?」
追问:「什么情况下绝对不应该触发?」
→ 翻译笔记:「这些触发词在什么上下文下会有歧义?」
3.3 成功标准
追问:「用户如何判断这个 Skill 工作了?」
→ 翻译笔记:「成功标准中,哪些需要被量化或指定格式?」
3.4 MVP 边界(✅做 / ❌不做)
追问:「最小版本是什么?只有这些最小功能,是否也能解决核心问题?」
→ 翻译笔记:「边界中的「不做」需要明确说是谁来做(skill-designer?其他角色?)」
Step 4 Agent 层设计(正式规格,基于 Step 3 翻译笔记)
使用 Step 3 产出的翻译笔记,完整输出 4 个子节的精确规格:
2.1 精确触发条件(if-then 语义模式 + 与其他 Skill 的优先级)
2.2 执行步骤(每步:输入来源 / 操作 / 输出格式 / 失败处理)
2.3 边界条件(非预期情况的处理方式,包括「系统级需求拆分」场景)
2.4 依赖声明(读哪些文件 / 影响哪些组件)
⚠️ 额外判断(🔵-1 修复):若用户需求涉及 3+ 个 Skill,在此步骤提示:
「这是系统级需求,建议先列出需要的 Skill 清单,逐个定义,而非一次全做」
Step 5 失败模式追问(必做,不可跳过)
「这个 Skill 最容易在哪里出问题?」
「如果 AI 只走到一半就以为完成了,会停在哪个步骤?」
→ 若用户说不知道 → AI 根据步骤推断并提出,用户确认
Step 6 Rule 绑定追问(必做)
「是高风险知识任务吗?」→ R1/R2/R10
「需要正式文件输出吗?」→ R6
「涉及版本管理吗?」→ R9
Step 7 张力分析
对比人层 vs Agent 层,列出「人觉得显然但 AI 需要被显式告知」的点(至少 2 条)
Step 8 复杂度评估
标注 Level 1-4,说明与已有组件的交互关系
Step 9 输出产品定义卡片(R6:必须写文件)
⚠️ 检查:2.5 失败模式 和 2.6 Rule 绑定 两节均非空,否则阻断
Write: .cursor/skills/skill-designer/draft-[skill名称].md
告知用户:
「✅ 产品定义卡片已保存:draft-[skill名称].md
准备好实现时,说「实现这个Skill」→ 触发 skill-designer
触发时请同时告知 skill-designer:「请先读取 draft-[skill名称].md 作为产品定义起点」
(skill-designer 不会自动读取 draft,需手动引导)」
更新 PENDING-SKILLS.md(若本次来自待评估项):
→ 定位 Step 2 记录的来源条目名称
→ 将该条目状态标注为「已定义(draft-[name].md),待 skill-designer 实现」
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 181 lines · 144 tokens per session scan A 00bbbaa0b970
role-Skill产品经理 is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 144 tokens to every session and 2,783 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
android-feature
Workflow for implementing a new Android feature, screen, fragment, activity, dialog, adapter, or enhancement in this XML/MVVM template. Use whenever the user asks to add, build, implement, or extend functionality — before writing any code. Covers planning, the MVVM/MVI skeleton, the Android configuration checklist…
template-helpers
Catalog of the reusable building blocks shipped with this Android template — BaseActivity/BaseFragment, the helpers/ extension files (navigation, lifecycle, toast, snackbar, dialogs, images, permissions, theme, locale, settings intents, date, delay), common/ (Firebase, network, observers), and…
android-new-project
Workflow for turning a fresh copy of this Android template into a new app — renaming the package/namespace/applicationId, branding (icons, splash, palette, fonts), Firebase setup, signing config, stripping unused sample screens, and verifying the foundation. Use when the user says they are starting a new app…
android-preflight
Final verification checklist to run before declaring Android work finished — build, both themes, string resources, lifecycle and leak risks, registered permissions and components, resource parity between values and values-night, and honest reporting of what was and was not verified. Use at the end of any feature, fix…
android-ui-theming
Rules for Android XML layouts, Material 3 components, semantic color tokens, light/dark theming, dimensions (sdp/ssp), string resources and localization, accessibility, and edge-to-edge insets. Use when creating or editing any layout, drawable, style, color, vector, or string resource, or when a screen must work in…
android-upgrade
Workflow for changing an existing working Android project — upgrading dependencies, AGP/Gradle or SDK levels, migrating deprecated APIs, refactoring, and fixing bugs, without breaking what already works. Covers baseline verification, scoping the diff, targetSdk behaviour changes, SharedPreferences/Room data…