Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/linshidream/skill-hubnpx agentmods add skills/linshidream/skill-hub/product-lifecycleWrote 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/linshidream/skill-hub/product-lifecycle)<a href="https://agentmods.dev/skills/linshidream/skill-hub/product-lifecycle"><img src="https://agentmods.dev/badge/skills/linshidream/skill-hub/product-lifecycle/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/linshidream/skill-hub/product-lifecycle"><img src="https://agentmods.dev/badge/skills/linshidream/skill-hub/product-lifecycle.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 | $0.00092 | $0.02701 |
| Opus 5.5 | $0.00037 | $0.01080 |
| Sonnet 5.5 | $0.00018 | $0.00540 |
| Haiku 4.5 | $0.00009 | $0.00270 |
Grade A, and why
product-lifecycle 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 1mo 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Lifecycle
目标
product-lifecycle 把已接到的客户需求转成两类交接物：
- 客户能签字确认的演示物。
dev-spec能消费的需求签字记录.md。
它只负责 product 侧，不产出开发 spec，不写技术方案，不拆 implementation steps。规格化工作交给 dev 侧的 dev-spec。
本 skill 是 protocol，不是控制器：它定义状态机、操作契约和恢复规则，具体执行由当前 agent 按可用工具完成。
使用场景
启动：
- "接了个活：{客户/项目名}，需求是 {人话描述}"
- "启动产品流程"
- "做一个演示原型给客户看"
恢复：
- "继续产品流程"
- "接着上次的原型"
- 读取
.product-flow-state.json，从中断 node 继续
冻结：
- "客户确认了，冻结"
- "签字，进入开发"
状态机
N0 接活 Intake
-> N1 澄清 Elicitation
-> N2 生成 Generate
-> N3 自检 Self-check
-> 自检 fail：回 N2，列问题项重改
-> 自检 pass：路径回写 state，进 N4
-> N4 评审 Review
-> 有反馈且未到轮次上限：回 N2
-> 客户确认：进 N5
-> N5 签字冻结 Sign-off
-> N6 交付 Handoff
状态写入 engagement 工作区根的 .product-flow-state.json，最小 schema 见仓库级 schemas/product-flow-state.schema.json。
Node 的 canonical 写法使用 N0:intake 这类稳定编号。读到旧状态或临时状态时，可兼容以下别名并在写回时规范化：
| Canonical | 兼容别名 |
|---|---|
N0:intake |
intake |
N1:elicitation |
eliciting |
N2:generate |
generating |
N3:self-check |
self_checking、self-checking |
N4:review |
awaiting-review、revising、旧 N3:review |
N5:sign-off |
frozen、旧 N4:sign-off |
N6:handoff |
handoff、旧 N5:handoff |
v0.1.1 引入
N3:self-check自检 gate（设计策展层第 4 层，质量不靠客户兜底）后，原 N3/N4/N5 整体后移一位为 N4/N5/N6。读到旧状态时按别名映射到新 canonical，写回时规范化为新编号。
节点规则
| 节点 | 目标 | 产出/状态 |
|---|---|---|
N0:intake |
记录已接到的活、客户目标、业务场景 | state 初始化 |
N1:elicitation |
轻量澄清，只补到足够生成演示物 | 需求边界、关键流程、用户角色 |
N2:generate |
调用 ui-prototype-gen 生成演示物 |
演示原型/ |
N3:self-check |
过 ui-prototype-gen 的设计自检清单（8 项 gate），质量不靠客户兜底 |
self_check 记录（pass/fail + 问题项） |
N4:review |
客户评审，有限轮次修改 | round 增长，记录反馈 |
N5:sign-off |
冻结版本，提示用户可自行 commit/tag | frozen=true，sign_off.status=approved |
N6:handoff |
输出 需求签字记录.md + DESIGN.md（由 design-tokens.instance.json 生成），供 dev-spec 消费 |
requirements_doc_path、design_md_path |
澄清边界
N1 是轻量澄清，不做重规格化。只问影响演示物生成和客户签字的内容：
- 目标用户和业务目标。
- 核心页面/流程。
- 必须展示的字段、状态和操作。
- 明确不做的功能边界。
- 客户签字时要看到什么才算“对，就是这个”。
- 品牌资产清单（可选，有则收）：客户 logo、品牌主色/辅助色、指定字体、业务专属图标或插画倾向——供策展层第 ③ 层
brand_overrides落品牌色、生成原型时注入定制资产。无品牌资产时跳过，用 preset 默认。风格锁护栏见ui-prototype-gen/templates/curation/风格锁.md。
What ships with it
5 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.
- 1mo ago First seen · 203 lines · 92 tokens per session scan A 699873e66c61
product-lifecycle is a skill published in the GitHub repository linshidream/skill-hub (20 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 2,701 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.