product-management by vasilyu1983/ai-agents-public
npx skills add https://github.com/vasilyu1983/ai-agents-public --skill product-management此技能将助手转变为操作者,而非讲师。
这里的一切都是:
现代最佳实践 (2026年1月):
当用户要求进行实际的产品工作时,请使用此技能,例如:
不要将此技能用于:
| 任务 | 模板 |
|---|
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 领域 |
|---|
| 输出 |
|---|
| 探索访谈 | customer-interview-template.md | 探索 | 包含“妈妈测试”模式的访谈脚本 |
| 机会映射 | opportunity-solution-tree.md | 探索 | 包含结果、问题、解决方案的 OST |
| PMF 调查 | pmf-survey-template.md | 探索 | Sean Ellis + NPS + 使用情况调查 |
| 结果路线图 | outcome-roadmap.md | 路线图 | 包含结果和主题的 现在/下一步/以后 |
| OKR 定义 | okr-template.md | 指标 | 1-3 个目标,每个目标包含 2-4 个关键结果 |
| 产品定位 | positioning-template.md | 战略 | 竞争替代品 -> 价值 -> 细分市场 |
| 产品愿景 | product-vision-template.md | 战略 | 从→到 的叙述,时间范围为 3-5 年 |
| 季度回顾 | quarterly-product-review.md | 战略 | 保持 / 削减 / 加倍投入的产品审计 |
| 优先级排序 | prioritization-scorecard.md | 优先级排序 | 带有终止标准的 RICE/ICE 评分 |
| 终止标准 | kill-criteria-template.md | 优先级排序 | 每个计划的预定义停止条件 |
| 一对一会议 | 1-1-template.md | 领导力 | 检查、进展、阻碍、成长 |
| 事后复盘 | a3-debrief.md | 领导力 | 意图与实际、根本原因、行动项 |
User needs: [Product Work Type]
├─ Discovery / Validation?
│ ├─ Customer insights? → Customer interview template
│ ├─ Hypothesis testing? → Assumption test template
│ └─ Opportunity mapping? → Opportunity Solution Tree
│
├─ Strategy / Vision?
│ ├─ Long-term direction? → Product vision template
│ ├─ Market positioning? → Positioning template (Dunford)
│ ├─ Big opportunity? → Opportunity assessment
│ └─ Amazon-style spec? → PR/FAQ template
│
├─ Planning / Roadmap?
│ ├─ Outcome-driven? → Outcome roadmap (Now/Next/Later)
│ ├─ Theme-based? → Theme roadmap
│ └─ Metrics / OKRs? → Metric tree + OKR template
│
├─ Prioritization / Focus?
│ ├─ What to build next? → Prioritization scorecard (RICE/ICE)
│ ├─ What to stop? → Kill criteria template + quarterly review
│ ├─ Scope too large? → Scope negotiation patterns
│ └─ PMF check? → PMF survey + retention curve analysis
│
└─ Leadership / Team Ops?
├─ 1:1 meeting? → 1-1 template
├─ Giving feedback? → Feedback template (SBI model)
├─ Post-incident? → A3 debrief
├─ Stakeholder pushback? → Stakeholder management patterns
└─ Negotiation? → Negotiation one-sheet (Voss)
创始人/产品经理最常见的失败:构建一切,不淘汰任何东西,在产生影响之前耗尽时间。
| 框架 | 公式 / 方法 | 最适用于 | 注意事项 |
|---|---|---|---|
| RICE | (触及范围 x 影响 x 信心) / 工作量 | 用数据比较功能 | 操纵信心分数 |
| ICE | 影响 x 信心 x 简易性 | 快速的直觉检查优先级排序 | 过度简化 |
| 机会评分 | 重要性 x (重要性 - 满意度) | 探索驱动,与 JTBD 一致 | 需要用户研究数据 |
| 延迟成本 | 单位时间价值 / 持续时间 | 时间敏感的决策 | 难以准确估计 |
| 加权最短作业优先 (WSJF) | 延迟成本 / 作业规模 | SAFe/精益,流程优化 | 需要校准的估计 |
选择一个。始终如一地使用它。框架本身不如以相同方式对所有事物进行评分的纪律重要。
每个计划都应具有预定义的停止条件:
在开始前使用 assets/prioritization/kill-criteria-template.md 来定义这些标准。
当用新功能替换现有功能时,不要直接强行终止旧功能。使用桥接迁移模式来防止用户流失。
桥接模式:同时运行新旧功能。默认将用户引导至新体验,但保持旧路径可访问(通过链接、回退或设置切换)。
基于替代的终止规则:
BRIDGE MIGRATION SEQUENCE:
1. Ship new feature alongside old feature
2. Default new users to new experience
3. Migrate existing users gradually (progressive rollout)
4. Monitor: absorption rate, retention by cohort, support tickets
5. Old feature absorbs ≥80% for 14 days + no retention drop?
├─ Yes → Kill old feature, remove code
└─ No → Investigate gaps, iterate new feature, extend bridge
何时不应桥接:安全漏洞、合规要求或使用率极低(<1% MAU)的功能。这些可以在通知后直接终止。
当利益相关者要求扩大范围时:
每个季度,使用 assets/strategy/quarterly-product-review.md 审查产品:
有关详细的优先级排序模式和示例,请参阅 references/prioritization-frameworks.md。
PMF 不是一个二元事件。它是一个你需要在多个维度上测量的信号。
调查用户:“如果您不能再使用 [产品],您会有什么感觉?”
使用 assets/discovery/pmf-survey-template.md 获取完整调查(结合了 Sean Ellis + NPS + 使用情况问题)。
精确定义激活(公式 + 时间范围 + 数据源):
定期审计功能使用情况,以确定保留、改进或移除的内容:
PMF 因细分市场而异。分别测量:
有关详细的 PMF 测量方法,请参阅 references/pmf-measurement.md。
创始人管理董事会成员、投资者、早期客户、联合创始人以及(最终)团队负责人——通常没有经过正式的产品管理培训。
关键模式:
有关详细的利益相关者管理模式,请参阅 references/stakeholder-management.md。
对于 PRD/规格说明和高质量的文档撰写,请使用 ../docs-ai-prd/ 中的模板:
仅在明确请求且符合政策时使用。
资源
模板
相关技能
有关详细模式、模板演练、示例流程和执行检查清单,请参阅 references/operational-guide.md。将 SKILL.md 作为导航中心;在产出工件时使用 assets/ 目录。
有关官方框架(精益创业、OST、PR/FAQ、OKRs)和 AI/LLM 安全参考,请参阅 data/sources.json。
使用上面的快速参考和决策树选择一个模板,然后按照操作指南获取深度内容。
重要提示:当用户询问有关产品管理工具、框架或实践的建议问题时,在回答前使用网络搜索工具检查当前趋势。如果网络搜索不可用,请使用 data/sources.json 并清楚说明您已验证的内容与假设的内容。
"product management best practices 2026""[specific tool] vs alternatives 2026""product management trends January 2026""[discovery/roadmap/OKR] frameworks 2026"搜索后,提供:
每周安装量
410
仓库
GitHub 星标数
47
首次出现
2026年1月23日
安全审计
安装于
opencode355
gemini-cli352
cursor351
codex348
github-copilot339
kimi-cli311
This skill turns the assistant into an operator, not a lecturer.
Everything here is:
Modern Best Practices (Jan 2026) :
Use this skill when the user asks to do real product work, such as:
Do not use this skill for:
| Task | Template | Domain | Output |
|---|---|---|---|
| Discovery interview | customer-interview-template.md | Discovery | Interview script with Mom Test patterns |
| Opportunity mapping | opportunity-solution-tree.md | Discovery | OST with outcomes, problems, solutions |
| PMF survey | pmf-survey-template.md | Discovery | Sean Ellis + NPS + usage survey |
| Outcome roadmap | outcome-roadmap.md | Roadmap |
User needs: [Product Work Type]
├─ Discovery / Validation?
│ ├─ Customer insights? → Customer interview template
│ ├─ Hypothesis testing? → Assumption test template
│ └─ Opportunity mapping? → Opportunity Solution Tree
│
├─ Strategy / Vision?
│ ├─ Long-term direction? → Product vision template
│ ├─ Market positioning? → Positioning template (Dunford)
│ ├─ Big opportunity? → Opportunity assessment
│ └─ Amazon-style spec? → PR/FAQ template
│
├─ Planning / Roadmap?
│ ├─ Outcome-driven? → Outcome roadmap (Now/Next/Later)
│ ├─ Theme-based? → Theme roadmap
│ └─ Metrics / OKRs? → Metric tree + OKR template
│
├─ Prioritization / Focus?
│ ├─ What to build next? → Prioritization scorecard (RICE/ICE)
│ ├─ What to stop? → Kill criteria template + quarterly review
│ ├─ Scope too large? → Scope negotiation patterns
│ └─ PMF check? → PMF survey + retention curve analysis
│
└─ Leadership / Team Ops?
├─ 1:1 meeting? → 1-1 template
├─ Giving feedback? → Feedback template (SBI model)
├─ Post-incident? → A3 debrief
├─ Stakeholder pushback? → Stakeholder management patterns
└─ Negotiation? → Negotiation one-sheet (Voss)
The most common founder-PM failure: building everything, killing nothing, and running out of time before impact.
| Framework | Formula / Method | Best For | Watch For |
|---|---|---|---|
| RICE | (Reach x Impact x Confidence) / Effort | Comparing features with data | Gaming confidence scores |
| ICE | Impact x Confidence x Ease | Quick gut-check prioritization | Over-simplification |
| Opportunity Scoring | Importance x (Importance - Satisfaction) | Discovery-driven, JTBD-aligned | Requires user research data |
| Cost of Delay | Value per unit time / Duration | Time-sensitive decisions | Harder to estimate accurately |
| Weighted Shortest Job First (WSJF) | Cost of Delay / Job Size | SAFe/Lean, flow optimization | Requires calibrated estimates |
Pick one. Use it consistently. The framework matters less than the discipline of scoring everything the same way.
Every initiative should have pre-defined conditions for stopping:
Use assets/prioritization/kill-criteria-template.md to define these before starting.
When replacing an existing feature with a new one, don't hard-kill the old feature. Use a bridge migration pattern to prevent user loss.
Bridge mode : Run both old and new features simultaneously. Route users to the new experience by default but keep the old path accessible (via link, fallback, or settings toggle).
Substitution-based kill rule :
BRIDGE MIGRATION SEQUENCE:
1. Ship new feature alongside old feature
2. Default new users to new experience
3. Migrate existing users gradually (progressive rollout)
4. Monitor: absorption rate, retention by cohort, support tickets
5. Old feature absorbs ≥80% for 14 days + no retention drop?
├─ Yes → Kill old feature, remove code
└─ No → Investigate gaps, iterate new feature, extend bridge
When NOT to bridge : Security vulnerabilities, compliance requirements, or features with near-zero usage (<1% MAU). These can be killed directly with notice.
When stakeholders push for more scope:
Every quarter, review the product with assets/strategy/quarterly-product-review.md:
For detailed prioritization patterns and worked examples: see references/prioritization-frameworks.md.
PMF is not a binary event. It's a signal you measure across multiple dimensions.
Survey users: "How would you feel if you could no longer use [product]?"
Use assets/discovery/pmf-survey-template.md for the full survey (combines Sean Ellis + NPS + usage questions).
Define activation precisely (formula + timeframe + data source):
Periodically audit feature usage to identify what to keep, improve, or remove:
PMF varies by segment. Measure separately for:
For detailed PMF measurement methodology: see references/pmf-measurement.md.
Founders manage board members, investors, early customers, co-founders, and (eventually) team leads — often without formal PM training.
Key patterns:
For detailed stakeholder management patterns: see references/stakeholder-management.md.
For PRDs/specs and writing-quality requirements, use the templates in ../docs-ai-prd/:
Use only when explicitly requested and policy-compliant.
Resources
Templates
Related Skills
See references/operational-guide.md for detailed patterns, template walkthroughs, example flows, and execution checklists. Keep SKILL.md as the navigation hub; use assets/ when producing artifacts.
See data/sources.json for official frameworks (Lean Startup, OST, PR/FAQ, OKRs) and AI/LLM safety references.
Use the quick reference and decision tree above to choose a template, then follow the operational guide for depth.
IMPORTANT : When users ask recommendation questions about product management tools, frameworks, or practices, use a web search tool to check current trends before answering. If web search is unavailable, use data/sources.json and state clearly what you verified vs assumed.
"product management best practices 2026""[specific tool] vs alternatives 2026""product management trends January 2026""[discovery/roadmap/OKR] frameworks 2026"After searching, provide:
Weekly Installs
410
Repository
GitHub Stars
47
First Seen
Jan 23, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
opencode355
gemini-cli352
cursor351
codex348
github-copilot339
kimi-cli311
飞书日程待办摘要工作流:AI自动生成每日/每周开工报告,提升个人生产力
3,100 周安装
| Now/Next/Later with outcomes and themes |
| OKR definition | okr-template.md | Metrics | 1-3 objectives with 2-4 key results each |
| Product positioning | positioning-template.md | Strategy | Competitive alternatives -> value -> segment |
| Product vision | product-vision-template.md | Strategy | From→To narrative with 3-5 year horizon |
| Quarterly review | quarterly-product-review.md | Strategy | Keep / cut / double-down product audit |
| Prioritization | prioritization-scorecard.md | Prioritization | RICE/ICE scoring with kill criteria |
| Kill criteria | kill-criteria-template.md | Prioritization | Pre-defined stop conditions per initiative |
| 1:1 meeting | 1-1-template.md | Leadership | Check-in, progress, blockers, growth |
| Post-incident debrief | a3-debrief.md | Leadership | Intent vs actual, root cause, action items |