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 product-evolution-plannergit 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/product-evolution-planner)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/product-evolution-planner"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/product-evolution-planner/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/product-evolution-planner"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/product-evolution-planner.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 | $0.00149 | $0.02682 |
| Opus 5 | $0.00075 | $0.01341 |
| Sonnet 5 | $0.00030 | $0.00536 |
| Haiku 4.5 | $0.00015 | $0.00268 |
Grade A, and why
product-evolution-planner 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 8d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
主动式产品演进规划(product-evolution-planner)
核心定位:AI 不等待指令,主动对照原则思考「这个产品应该往哪里演进」。 强绑定 Rule:R2 NO_FABRICATION / R3 READ_FIRST / R1 EVIDENCE_FIRST / R6 ARTIFACT_FIRST
与其他 Skill 的区别:
- role-产品经理:执行具体的产品设计任务(闭环递进法、动线设计)
知识导航表(执行前必须理解的概念根)
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| D0 认知根(必读) | _内部总控/认知结构/L1_系统性文档/产品理论维度/AI时代产品问题全景框架.md |
§五 产品构建五大原则;§六 五条判断原则;§七 马斯洛新瓶颈;§八 闭环递进法(产品演进的理论依据) |
| D3 规范参考 | — | 本 Skill 是战略诊断,不修改任何文档,无需规范参考 |
| D4 运行时数据 | 各项目 产品定义.md + 开发计划.md |
当前产品现状(被诊断的对象) |
核心概念速查: ① 原则驱动 = 以L1产品理论为标准评估,不是凭感觉或竞品对标来建议改进 ② 战略诊断 ≠ 产品设计:本 Skill 只产出建议报告,不创建或修改产品文档 ③ 缺口 = 当前产品与产品原则之间的差距(证据必须引用具体章节)
- architecture-gap-mapper:对比两个已有系统/方案的差距
- product-evolution-planner:对照设计原则,主动诊断当前产品,生成战略级改进建议
激活后立即执行(顺序不可跳过)
Step 1 读取原则文档(R3 READ_FIRST:必须先读完再分析)
用 explore 子智能体并行读取以下文档:
【必读,不存在则中止】
- _内部总控/产品定义/AI时代产品问题全景框架.md
⚠️ 该文档约1400行,必须读取以下核心章节(不允许只读摘要):
- 第三章:各马斯洛层的新瓶颈(一到五层)
- 第五章:Human-Readable + Agent-Operable 双层设计原则
- 第六章:五条判断原则(马斯洛定位/AI放大/需求质量/Taste/研发壁垒)
- 当前项目的 产品经理/产品定义.md
【可选,不存在则跳过,不报错】
- _内部总控/产品定义/体系架构原则.md(未来会建立)
- 当前项目的 技术架构师/技术架构.md
若「必读」文档不存在:
→ 若产品原则文档不存在:中止并提示「_内部总控/产品定义/ 目录下未找到框架文档」
→ 若产品定义不存在:提示「当前项目没有产品定义,建议先运行 role-产品经理 完成定义,再做演进分析」
Step 2 从每条原则出发,对照当前产品做原则检验
对照 AI时代产品问题全景框架 的核心原则(R1 EVIDENCE_FIRST:每条必须引用原则文档具体论断):
【原则一:马斯洛新瓶颈检验】
→ 这个产品服务的是哪一层的需求?
→ 它解决的是「AI时代的新瓶颈」,还是「旧瓶颈」(已被AI直接解决或即将解决的)?
→ 判据:AI越强,这个需求是更强烈还是消失?
【原则二:AI放大检验】
→ AI能力再强10倍,这个产品的需求变大了还是消失了?
→ 若消失:本质是在填AI能力空缺,不是长期方向
【原则三:Human-Readable + Agent-Operable 双层设计检验】
→ 人层:产品是否极简可读、体验先于功能?
→ 智能体层:所有功能是否有对应的API/接口,AI可以完整操作?
→ 有没有「只为人设计、AI无法操作」或「只有API、人不知道怎么用」的情况?
【原则四:闭环完整性检验】
→ 主干用户动线是否有明确的入口和出口?
→ 有没有「用户走到一半找不到下一步」的断点?
→ 有没有功能「没有反馈分支」(不论用户做什么,系统反应一样)?
【原则五:研发壁垒检验】
→ 6-12个月内,竞品是否可以完整复制这个产品?
→ 背后有没有持续生产新知识的研究方向?
→ 数据飞轮是否存在(越用越强)?
【技术架构原则检验(若文档存在)】
→ 读取体系架构原则.md,逐条对照当前技术架构
每项检验必须同时给出:
- 当前产品的具体证据(引用产品定义中的具体描述)
- 通过/部分通过/未通过的判断
- 未通过时:具体体现在哪里
Step 3 生成原则缺口清单
对每个「未通过」或「部分通过」的检验,生成一条缺口描述:
格式:
[优先级] 缺口:[一句话描述]
原则依据:[引用框架文档的具体论断]
当前产品的体现:[引用产品定义的具体描述]
改进方向:[建议的方向,不是具体实现]
类型:产品功能类 / 技术架构类
Step 4 优先级排序
P0:违反核心原则(会让产品往错方向持续投入)
→ 对应:解决旧瓶颈 / AI越强需求消失 / 数据飞轮反转
P1:明显改进机会(现有框架内可做,改了明显更好)
→ 对应:闭环有断点 / 双层设计缺失某一层 / 研发壁垒薄弱
P2:中长期演进方向(需要新资源或新研究,当前不紧急)
Step 5 输出「产品演进建议报告」(R6 ARTIFACT_FIRST:必须写文件)
写入:产品经理/产品演进建议_YYYYMMDD.md
格式见下方「报告格式」
Step 6 路由询问
「📊 产品演进分析完成。共发现 N 条改进建议(P0: N,P1: N,P2: N)。
是否现在执行某项?
- 产品功能类建议 → 加载 role-产品经理 继续设计
- 技术架构类建议 → 加载 role-技术架构师 继续设计
- [选择第几条执行] [先看报告,稍后决定]」
若用户选择执行某条:
→ 将该条建议的完整内容(原则依据 + 当前问题 + 改进方向)作为上下文
→ 加载对应角色 Skill,将建议内容传入作为「本次任务背景」
What ships with it
2 files 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.
- 8d ago First seen · 206 lines · 149 tokens per session scan A 50c87f78380e
product-evolution-planner is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 149 tokens to every session and 2,682 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
team
Coordinate parallel work across multiple Cursor sessions via shared .omc/team/ state.
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-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…
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-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…