Back to Details

grow-app

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Grow an App

打造高留存应用

Your app has users who sign up and then quietly disappear — cohorts decay, daily actives are flat, the activation funnel leaks where it always has, and nothing looks obviously broken. This journey seals the bucket: it turns first-time users into activated, then habitual, then would-miss-it users across eight interactive phases. The agent asks before every decision and records the outcome in 
docs/
, so the work resumes across sessions instead of restarting. Growth here is an engineering and design problem, not a bigger ad budget.
您的应用存在用户注册后便悄然流失的问题——用户群体持续衰减，日活跃用户数停滞不前，激活漏斗始终存在流失点，但表面看并无明显故障。本旅程将帮您“补好漏洞”：通过八个互动阶段，将首次用户转化为活跃用户、习惯性用户，最终成为离不开应用的用户。Agent会在每次决策前发起询问，并将结果记录在
docs/
文件夹中，确保工作可跨会话继续推进，无需从头开始。此处的增长是工程与设计问题，而非单纯增加广告预算。

Core Principle

核心原则

Fix the leaky bucket before pouring in acquisition: habit, activation, and retention come before any growth spend. This skill sequences the eight phases, asks every decision question, and records each choice in 
docs/
. The constituent skills carry the method — invoke them rather than improvising their frameworks.
先补好漏洞再投入获客资源：习惯养成、用户激活与留存优先于任何增长投入。 本技能会按顺序执行八个阶段，提出所有决策问题，并将每个选择记录在
docs/
中。各阶段的方法由对应技能承载——请调用这些技能，而非自行套用框架。

Journey Map

旅程地图

PhaseSkillQuestion it answersArtifact
1hooked-uxWhy do users come back without us paying?Extends docs/PRODUCT.md
2improve-retentionWhy don't new users reach the loop?Extends docs/PRODUCT.md
3continuous-discoveryWhat do our own users actually need?Extends docs/PRODUCT.md + docs/CUSTOMER.md
4lean-uxWhich bet is worth building?Extends docs/EXPERIMENTS.md
5inspired-productIs the team building the right things?Extends docs/PRODUCT.md
6lean-analyticsWhich single number tells the truth?Creates docs/METRICS.md — sets the Rule 8 bar
7microinteractionsDoes it feel alive in the hand?Extends docs/DESIGN.md
8drive-motivationWill engagement last, or curdle?Extends docs/PRODUCT.md
Phases 1-2 seal the loop and the funnel; 3-5 steer with evidence; 6 is the instrument panel; 7-8 are the finish and the ethical backstop. Take the lean-analytics baseline (Phase 6) early — before the Phase 1-2 fixes land — so every change is read against a pre-change number, then keep updating it. Habit formation is slow: read Phase 1's success against the "5% rule" (a habit has formed when 5%+ of users return unprompted), not a single cohort.
阶段技能解决的问题产出物
1hooked-ux用户为何无需付费激励就主动回归？扩展 docs/PRODUCT.md
2improve-retention新用户为何无法进入习惯循环？扩展 docs/PRODUCT.md
3continuous-discovery我们的用户真正需要什么？扩展 docs/PRODUCT.md + docs/CUSTOMER.md
4lean-ux哪些方案值得投入开发？扩展 docs/EXPERIMENTS.md
5inspired-product团队是否在开发正确的产品？扩展 docs/PRODUCT.md
6lean-analytics哪个单一指标能反映真实状况？创建 docs/METRICS.md —— 设置Rule 8门槛
7microinteractions应用使用起来是否鲜活灵动？扩展 docs/DESIGN.md
8drive-motivation用户活跃度能否持久，还是会逐渐消退？扩展 docs/PRODUCT.md
阶段1-2用于修复习惯循环与激活漏斗的漏洞；阶段3-5基于数据指引方向；阶段6是核心指标面板；阶段7-8是体验优化与道德底线保障。尽早完成lean-analytics基线（阶段6）——在阶段1-2的修复落地前完成，这样所有变更都能与变更前的数据对比，之后持续更新该基线。习惯养成是一个缓慢的过程：阶段1的成功需参照“5%规则”（当5%以上用户主动回访时，说明习惯已形成），而非单一用户群体数据。

Operating Rules

操作规则

  1. Resume first. Before anything else, read 
    docs/GROW-APP-PLAN.md
    and every artifact in the Journey Map. If the tracker exists, summarize the journey state in 3-5 lines and ask which phase to enter. Done when the user has confirmed an entry point. A journey with a tracker is resumed, never restarted.
  2. Intake on first run only. No tracker: run the Intake below, then create 
    docs/GROW-APP-PLAN.md
    with every phase statused 
    pending | in-progress | awaiting-evidence | done | deferred: reason | skipped: reason
    . Done when the tracker exists and the user has confirmed the phase plan.
  3. Phase entry. Announce: what the phase does, the decision it forces, the artifact it produces, rough effort. Offer proceed / skip / defer — phases marked GATE may be deferred, never skipped. Mark the phase 
    in-progress
    on proceed. Done when the user chose.
  4. Skill invocation and fallback. Load the phase's skill and use it: each phase's Invoke line names the skill by slug — use that skill to run the phase. If it is not available, offer: 
    npx skills add wondelai/skills/<slug> --global
    . If the user declines, run the phase from its Brief — the minimum viable method. State which mode you are in.
  5. In-phase decisions. Ask every question under "Decide with the user" — with concrete options and your recommendation. Record the choice in the tracker's Key Decisions. A decision made silently is a defect.
  6. Phase exit. Present the draft artifact content for sign-off before writing. On approval: write or extend the docs/ files, update the tracker (status, Key Decisions, Next Actions). Done when the files are written and the phase row shows 
    done
    .
  7. Artifact discipline. Read before writing; create a file only if missing, otherwise extend — add or update your sections, preserve everyone else's. Files are UPPERCASE in 
    docs/
    . Every recommendation lands as a checkbox or a table row with owner and priority. See references/artifact-templates.md when creating a docs/ file for the first time — create it from the full skeleton (all section headings), then fill the sections your phase names.
  8. Retention before acquisition. Acquisition-oriented phases — the optional cold-start-problem, contagious, and crossing-the-chasm, plus any paid-growth work — stay locked while activation and retention sit below the bar set at intake; unlock them only once the cohort curve clears that bar. Every habit loop and reward must pass the Manipulation Matrix: build only what the maker would use and honestly believes materially improves users. When a tactic needs manufactured anxiety or loss aversion, replace it with one built on real value.
  1. 优先恢复进度。在开展任何工作前，先读取
    docs/GROW-APP-PLAN.md
    以及旅程地图中的所有产出物。若存在进度跟踪文件，用3-5行总结当前旅程状态，并询问进入哪个阶段。用户确认进入点后完成此步骤。已有跟踪文件的旅程需恢复进度，而非重新启动。
  2. 仅首次运行时进行初始调研。若没有跟踪文件：执行下方的初始调研，然后创建
    docs/GROW-APP-PLAN.md
    ，将每个阶段标记为
    pending | in-progress | awaiting-evidence | done | deferred: reason | skipped: reason
    。跟踪文件创建完成且用户确认阶段计划后完成此步骤。
  3. 阶段启动。告知用户：该阶段的作用、需要做出的决策、产出的文件、大致工作量。提供继续/跳过/延期选项——标记为GATE的阶段可延期，但不可跳过。选择继续则将阶段标记为
    in-progress
    。用户做出选择后完成此步骤。
  4. 技能调用与备选方案。加载对应阶段的技能并使用：每个阶段的调用行通过短名称指定技能——使用该技能执行阶段任务。若技能不可用，提供方案：
    npx skills add wondelai/skills/<slug> --global
    。若用户拒绝，使用该技能的简要说明（最小可行方法）执行阶段任务。说明当前使用的模式。
  5. 阶段内决策。提出“与用户共同决策”下的所有问题——提供具体选项与推荐方案。将选择记录在跟踪文件的“关键决策”部分。未经用户确认的静默决策视为缺陷。
  6. 阶段收尾。在写入文件前，向用户展示产出物草稿并请求确认。获得批准后：写入或扩展docs/文件夹中的文件，更新跟踪文件（状态、关键决策、下一步行动）。文件写入完成且阶段状态显示为
    done
    后完成此步骤。
  7. 产出物规范。先读取再写入；仅当文件不存在时创建，否则进行扩展——添加或更新对应部分，保留其他内容。docs/文件夹中的文件为大写格式。所有建议需以复选框或带负责人与优先级的表格行形式呈现。首次创建docs/文件时，请参考references/artifact-templates.md——先创建完整框架（所有章节标题），再填充当前阶段对应的内容。
  8. 留存优先于获客。获客导向的阶段——可选的cold-start-problem、contagious、crossing-the-chasm，以及任何付费增长工作——在激活与留存率未达到初始调研设定的门槛前保持锁定；仅当用户群体曲线突破该门槛后解锁。每个习惯循环与奖励机制必须通过“操纵矩阵”检验：仅开发开发者自身会使用且确实能为用户带来实质价值的功能。若策略需制造焦虑或损失厌恶感，需替换为基于真实价值的方案。

Intake

初始调研

Run only on first start (no tracker). Ask:
  1. What does the app do, and what core action does a retained user repeat? (defines the Hook loop and the OMTM)
  2. What are the current retention numbers — day-1/7/30 or week-4 cohorts? (sets the Rule 8 acquisition bar; feeds lean-analytics)
  3. Where does the activation funnel leak, and what is the first-run flow? (gates improve-retention)
  4. Solo/small team or a full product trio (PM, designer, engineer)? (scales continuous-discovery and inspired-product)
  5. Is the app a network/marketplace product, and do engaged users fail to convert to revenue? (flags optional cold-start-problem / monetizing-innovation)
  6. What analytics and instrumentation exist today? (gates lean-analytics and every experiment)
  7. Is retention broken by UX or performance rather than missing engagement? (if yes, route to improve-app first)
Skip heuristics: skip Phase 5 for a solo founder with no team to realign; defer Phase 7 until the loop and activation clear their bars; run Phase 3's cadence degraded if no user access exists yet. Then create the tracker from references/artifact-templates.md with every phase statused, and confirm the plan.
Done when 
docs/GROW-APP-PLAN.md
exists with every phase statused and the user has confirmed the plan.
仅在首次启动（无跟踪文件）时执行。询问：
  1. 应用的功能是什么，留存用户会重复执行的核心操作是什么？（定义Hook循环与OMTM核心指标）
  2. 当前的留存数据是多少——第1/7/30天或第4周用户群体留存率？（设置Rule 8获客门槛；为lean-analytics提供数据）
  3. 激活漏斗的流失点在哪里，首次使用流程是怎样的？（决定是否启动improve-retention）
  4. 是个人/小型团队，还是完整的产品三人组（产品经理、设计师、工程师）？（调整continuous-discovery与inspired-product的执行方式）
  5. 应用是否为网络/平台产品，活跃用户是否无法转化为收入？（标记可选的cold-start-problem / monetizing-innovation）
  6. 当前有哪些分析与监控工具？（决定是否启动lean-analytics与所有实验）
  7. 留存问题是由UX或性能缺陷导致，而非缺乏互动机制？（若是，先引导至improve-app技能）
跳过规则：若为独立创始人且无团队需要对齐，跳过阶段5；若习惯循环与激活率未达标，延期阶段7；若尚未能接触用户，降低continuous-discovery的执行频率。然后根据references/artifact-templates.md创建跟踪文件，标记每个阶段的状态，并确认计划。
docs/GROW-APP-PLAN.md
创建完成且所有阶段状态已标记、用户确认计划后完成此步骤。

Phases

各阶段详情

Phase 1 — Design the habit loop that brings users back (hooked-ux)

阶段1 — 设计促使用户回归的习惯循环（hooked-ux）

Purpose: Build the engine of return — a Hook loop strong enough that users come back on an internal trigger, not a paid notification.
Brief (fallback): The Hook Model runs Trigger → Action → Variable Reward → Investment. Migrate external triggers (push, email) to internal ones (an emotion — boredom, FOMO, anxiety). Make the action trivially simple. Make the reward variable across tribe/hunt/self. Sequence investment after the reward so it raises switching cost and loads the next trigger. A loop with one weak phase stalls, not half-works.
Invoke: Use the 
hooked-ux
skill with the core loop and how daily-active users return today. Ask it to (a) map the loop across all four phases, rate each 0-10, and name the weakest, and (b) design honest variable-reward concepts powered by data you already have, each checked against the Manipulation Matrix.
Decide with the user:
  • Which internal trigger (emotion) should pull users back — confirm one.
  • Which single phase is weakest and gets the highest-leverage fix now — or defer if the loop is already forming (5%+ unprompted return).
  • Which reward type to strengthen — tribe (social), hunt (resources), or self (mastery) — rejecting any concept that fails the Manipulation Matrix.
Artifact: Extend docs/PRODUCT.md 
## Hook Model
(trigger → action → variable reward → investment; weakest phase named). Update the tracker.
Done when: PRODUCT.md names the internal trigger and all four phases, the weakest phase and its fix are recorded, onboarding is re-engineered so a new user completes one full Hook cycle in the first session, and the user picked the fix to ship.
目标： 打造用户主动回归的引擎——一个足够强大的Hook循环，让用户基于内在触发而非付费通知回归。
备选简要说明： Hook模型包含触发（Trigger）→ 行动（Action）→ 可变奖励（Variable Reward）→ 投入（Investment）四个环节。将外部触发（推送、邮件）迁移为内在触发（一种情绪——无聊、错失恐惧、焦虑）。让行动变得极其简单。奖励需在社交、资源、自我实现三个维度保持可变。将投入环节安排在奖励之后，以提升转换成本并加载下一个触发信号。若循环中某一环节薄弱，整个循环将停滞，而非部分失效。
调用： 使用
hooked-ux
技能，提供核心循环以及当前日活跃用户的回归方式。要求它（a）梳理四个环节的循环流程，为每个环节打分（0-10分），并指出最薄弱的环节；（b）基于现有数据设计符合“操纵矩阵”的真实可变奖励方案。
与用户共同决策：
  • 选择哪种内在触发（情绪）来吸引用户回归——确认一种。
  • 确定最薄弱的环节并优先进行高杠杆修复——若循环已初步形成（5%以上用户主动回归）可延期。
  • 选择强化哪种奖励类型——社交、资源或自我实现——拒绝任何未通过“操纵矩阵”检验的方案。
产出物： 扩展docs/PRODUCT.md中的
## Hook Model
部分（触发→行动→可变奖励→投入；标注最薄弱环节）。更新跟踪文件。
完成标准： PRODUCT.md中明确内在触发与四个环节，记录最薄弱环节及其修复方案，重新设计新用户引导流程，让新用户在首次会话中完成完整的Hook循环，且用户确认要上线的修复方案。

Phase 2 — Fix activation by making the first action almost effortless (improve-retention)

阶段2 — 简化首次操作，修复激活漏斗（improve-retention）

Purpose: Get new users to the loop by making the first meaningful action almost effortless.
Brief (fallback): B=MAP — behavior fires only when Motivation, Ability, and a Prompt converge. Motivation is unreliable; raise Ability instead. Simplicity is capped by the scarcest of six resources: time, money, physical effort, mental effort, social deviance, non-routineness. Shrink the target to a Starter Step that delivers value in under 30s, anchor it to an existing routine, and celebrate the win immediately.
Invoke: Use the 
improve-retention
skill with the real activation flow step by step and the day-1/7/30 drop-offs. Ask for a B=MAP friction audit rating all six Ability-Chain factors, the scarcest resource named, a Starter Step redesign, and event-based prompt rules.
Decide with the user:
  • Which is the scarcest Ability resource for the first action — fix that link first, not the obvious one.
  • The Starter Step (tiniest valuable action) and its celebration moment.
  • Which time-based prompts convert to event-based, dropping any that fail "would I appreciate this now?".
Artifact: Extend docs/PRODUCT.md 
## Activation & Retention Plan
(friction/moment | fix | owner | status). Update the tracker.
Done when: the scarcest resource is named, the Starter Step, celebration, and prompt changes are rows with owners, each day-1/7/30 drop-off is mapped to its likely B=MAP failure, and the user approved the fix list.
目标： 通过让首次有意义操作变得几乎零门槛，引导新用户进入习惯循环。
备选简要说明： B=MAP模型——只有当动机（Motivation）、能力（Ability）与提示（Prompt）三者同时满足时，用户才会采取行动。动机不可靠；应提升能力。简洁性受六种资源中最稀缺的一种限制：时间、金钱、体力、脑力、社交偏差、非日常性。将目标缩小为“入门步骤”，在30秒内传递价值，锚定用户现有习惯，并立即给予正向反馈。
调用： 使用
improve-retention
技能，提供当前激活流程的详细步骤以及第1/7/30天的用户流失数据。要求它进行B=MAP摩擦审计，为六种能力链因素打分，指出最稀缺的资源，重新设计入门步骤，并提供基于事件的提示规则。
与用户共同决策：
  • 确定首次操作最稀缺的能力资源——优先修复该环节，而非最明显的问题。
  • 确定入门步骤（最小的有价值操作）及其正向反馈时刻。
  • 确定哪些基于时间的提示转换为基于事件的提示，移除任何不符合“我现在会希望收到这个提示吗？”标准的内容。
产出物： 扩展docs/PRODUCT.md中的
## Activation & Retention Plan
部分（摩擦/时刻 | 修复方案 | 负责人 | 状态）。更新跟踪文件。
完成标准： 明确最稀缺资源，入门步骤、正向反馈与提示变更均已添加带负责人的记录，每个第1/7/30天的流失点均已映射至可能的B=MAP失效原因，且用户批准修复列表。

Phase 3 — Run continuous discovery so you stop guessing (continuous-discovery)

阶段3 — 持续用户调研，停止主观猜测（continuous-discovery）

Purpose: Replace generic best-practice with a weekly stream of evidence about your own users.
Brief (fallback): Aim for at least one customer touchpoint per week. Build an Opportunity Solution Tree: outcome at the top → customer opportunities (needs/pains in the customer's words) → candidate solutions/experiments. Never leap outcome→solution. Interviews are story-based ("tell me about the last time you…"), captured as one-page snapshots. Test the riskiest leap-of-faith assumption first, cheaply.
Invoke: Use the 
continuous-discovery
skill with the retention outcome and known churn patterns. Ask for an Opportunity Solution Tree, a current-state experience map of how churned users try to succeed today, a weekly story-based interview snapshot template, and an assumption map for the next planned feature.
Decide with the user:
  • The single outcome at the top of the tree.
  • Which two or three opportunities to pursue first.
  • The weekly cadence and recruitment mechanism the team can actually sustain — set it now or run degraded.
  • The riskiest leap-of-faith assumption inside the next feature (desirability, viability, feasibility, usability) and the cheapest test for it.
Artifact: Extend docs/PRODUCT.md 
## Opportunity Solution Tree Notes
, 
## Outcome Roadmap
(outcome/problem | job served | priority | status), and 
## Discovery Cadence
; extend docs/CUSTOMER.md 
## Interview Evidence
(date | who | facts | commitment). Update the tracker.
Done when: the tree's outcome and top opportunities are recorded, the cadence is scheduled, the first interview snapshot template exists, and the riskiest assumption has a cheap test designed.
目标： 用每周的用户真实数据替代通用最佳实践。
备选简要说明： 目标为每周至少一次用户接触。构建机会解决方案树：顶部为目标成果 → 中间为用户机会（用户语言描述的需求/痛点） → 底部为候选方案/实验。绝不能直接从目标成果跳到解决方案。访谈需基于故事（“告诉我你上次……的经历”），记录为单页快照。优先以低成本测试最具风险的核心假设。
调用： 使用
continuous-discovery
技能，提供留存目标与已知用户流失模式。要求它构建机会解决方案树，绘制当前流失用户尝试完成任务的体验地图，提供每周基于故事的访谈快照模板，并为下一个计划功能构建假设地图。
与用户共同决策：
  • 确定树顶部的单一目标成果。
  • 选择优先推进的两到三个用户机会。
  • 确定团队实际可维持的每周调研节奏与用户招募机制——立即设定或降低频率执行。
  • 确定下一个功能中最具风险的核心假设（需求、可行性、可用性、可落地性），并设计最便宜的测试方案。
产出物： 扩展docs/PRODUCT.md中的
## Opportunity Solution Tree Notes
、
## Outcome Roadmap
（成果/问题 | 满足的用户需求 | 优先级 | 状态）以及
## Discovery Cadence
；扩展docs/CUSTOMER.md中的
## Interview Evidence
（日期 | 受访者 | 事实 | 承诺）。更新跟踪文件。
完成标准： 记录树的目标成果与顶部机会，安排好调研节奏，创建首个访谈快照模板，且为最具风险的假设设计了低成本测试方案。

Phase 4 — Replace debate with cheap experiments (lean-ux)

阶段4 — 用低成本实验替代争论（lean-ux）

Purpose: Turn opportunities into falsifiable bets settled by behavior, not meetings.
Brief (fallback): Outcomes over outputs — value is the behavior change, not the deliverable. Write a hypothesis: "We believe [outcome] will happen if [persona] achieves [action] with [feature]," with the metric and threshold committed before the test. Match fidelity to risk (a paper prototype with five users finds ~85% of usability issues); reserve A/B tests for tuning a proven concept. When invalidated, remove from the backlog — don't defer.
Invoke: Use the 
lean-ux
skill with the biggest current design debate or a top discovery opportunity. Ask for three hypothesis statements in the standard format, the lowest-fidelity experiment that could validate the top one, and its pre-committed metric, threshold, and timebox.
Decide with the user:
  • Which hypothesis to test first.
  • The experiment fidelity — the lowest that answers the actual question.
  • The pass/fail line and what leaves the backlog if it fails.
Artifact: Extend docs/EXPERIMENTS.md 
## Experiment Cards
(hypothesis, type, primary metric + threshold, guardrail, decision rule) and 
## Experiment Backlog
(idea | ICE | status). Update the tracker.
Done when: at least one experiment card has a pre-committed threshold and decision rule, the backlog is triaged, and the user chose the first test.
目标： 将用户机会转化为可通过用户行为验证的假设，而非通过会议争论。
备选简要说明： 成果优先于产出——价值是用户行为的改变，而非交付物。撰写假设：“我们认为，如果[用户群体]通过[功能]完成[操作]，将实现[成果]”，并在测试前确定衡量指标与阈值。实验保真度需匹配风险（纸原型测试5名用户可发现约85%的可用性问题）；仅在验证概念后使用A/B测试进行调优。若假设被证伪，从待办清单中移除——不要延期。
调用： 使用
lean-ux
技能，提供当前最大的设计争论或顶级用户机会。要求它按标准格式撰写三个假设语句，设计验证顶级假设的最低保真度实验，并确定预先约定的衡量指标、阈值与时间范围。
与用户共同决策：
  • 选择首先测试的假设。
  • 确定实验保真度——满足问题需求的最低标准。
  • 确定通过/失败标准，以及假设失败时从待办清单中移除的内容。
产出物： 扩展docs/EXPERIMENTS.md中的
## Experiment Cards
（假设、类型、核心指标+阈值、防护指标、决策规则）与
## Experiment Backlog
（想法 | ICE评分 | 状态）。更新跟踪文件。
完成标准： 至少一个实验卡片包含预先约定的阈值与决策规则，待办清单已排序，且用户选定首个测试。

Phase 5 — Build the right things with an empowered team (inspired-product)

阶段5 — 赋能团队，开发正确的产品（inspired-product）

Purpose: Move the team from feature factory to outcome ownership — problems to solve, not features to ship.
Brief (fallback): Empowered teams get problems, not backlogs, and answer for outcomes. Dual-track: discovery (what's worth building — addressing value, usability, feasibility, viability) runs continuously alongside delivery. Expect 10-20 discovery iterations per shipped feature. Give the team a product vision and an outcome-based roadmap so it can decide autonomously.
Invoke: Use the 
inspired-product
skill with the top three backlog requests and the current roadmap. Ask for an opportunity assessment of each (objective, target user, problem, success measure, alternatives) and a one-paragraph vision plus a quarter of outcome-based roadmap items.
Decide with the user:
  • Which backlog request has the strongest evidence — and which to kill before it reaches a sprint.
  • The one-paragraph product vision.
  • Whether the roadmap is reframed as problems + key results rather than dated features.
Artifact: Extend docs/PRODUCT.md 
## Vision
and 
## Outcome Roadmap
(outcome/problem | job served | priority | status). Update the tracker.
Done when: the vision paragraph exists, each of the three requests has a build/kill verdict, and the roadmap rows are outcomes, not features.
目标： 将团队从“功能工厂”转变为“成果所有者”——聚焦需要解决的问题，而非需要交付的功能。
备选简要说明： 赋能团队接收的是问题，而非待办清单，并对成果负责。双轨并行：调研（确定值得开发的内容——解决价值、可用性、可行性、可落地性问题）与交付持续同步进行。每交付一个功能，预计需进行10-20次调研迭代。为团队提供产品愿景与基于成果的路线图，使其能够自主决策。
调用： 使用
inspired-product
技能，提供待办清单中排名前三的需求与当前路线图。要求它对每个需求进行机会评估（目标、目标用户、问题、成功衡量标准、替代方案），并撰写一段产品愿景以及一个季度的基于成果的路线图条目。
与用户共同决策：
  • 确定哪个待办需求有最强的数据支撑——以及哪个需求在进入迭代前就应终止。
  • 确定一段式产品愿景。
  • 确定是否将路线图重构为“问题+关键结果”，而非带日期的功能列表。
产出物： 扩展docs/PRODUCT.md中的
## Vision
与
## Outcome Roadmap
（成果/问题 | 满足的用户需求 | 优先级 | 状态）。更新跟踪文件。
完成标准： 愿景段落已撰写，三个需求均已确定开发/终止结论，且路线图条目为成果而非功能。

Phase 6 — Measure the one number that actually matters (lean-analytics)

阶段6 — 衡量真正重要的单一指标（lean-analytics）

Purpose: Point the whole team at the One Metric That Matters and expose the vanity metrics hiding the decay.
Brief (fallback): A good metric is comparative, a ratio/rate (not a cumulative total), and behavior-changing. Business model dictates which metrics matter; stage dictates sequencing (Empathy → Stickiness → Virality → Revenue → Scale). Weak retention = Stickiness stage, so retention is the OMTM — working a later stage first is the canonical mistake. Draw a line in the sand (target, date, miss response), pair the OMTM with a counter-metric, and cohort the data.
Invoke: Use the 
lean-analytics
skill with the current dashboard/metrics and the business model. Ask it to flag vanity metrics, pick the Stickiness-stage OMTM plus a counter-metric, design a one-screen dashboard (OMTM big, ≤6 supporting), and a cohorted retention view.
Decide with the user:
  • The OMTM and its counter-metric.
  • The line in the sand — target, date, pre-committed miss response.
  • Which current metrics are retired as vanity.
Artifact: Create docs/METRICS.md with 
## Stage & One Metric That Matters
, 
## KPI Definitions
, 
## Baselines & Targets
, 
## Funnel
, and 
## Cohort Notes
. Update the tracker.
Done when: METRICS.md names the OMTM + counter-metric, records the line in the sand with a date, lists cohorted baselines, the vanity metrics are marked retired, the one-screen dashboard is specified, and the retention bar for the Rule 8 acquisition gate is set.
目标： 引导全团队聚焦核心指标（One Metric That Matters, OMTM），揭露掩盖用户衰减的虚荣指标。
备选简要说明： 优质指标具备可比性、为比率/速率（而非累计总数）、能驱动行为改变。商业模式决定关键指标；产品阶段决定指标优先级（共情 → 粘性 → 病毒性 → 收入 → 规模化）。留存率低处于“粘性”阶段，因此留存率是OMTM——优先关注后续阶段是典型错误。设定明确目标（指标、日期、未达标应对方案），为OMTM搭配一个反向指标，并按用户群体分析数据。
调用： 使用
lean-analytics
技能，提供当前仪表盘/指标与商业模式。要求它标记虚荣指标，选择“粘性”阶段的OMTM与反向指标，设计单屏仪表盘（OMTM突出显示，支持≤6个辅助指标），并提供按用户群体划分的留存视图。
与用户共同决策：
  • 确定OMTM及其反向指标。
  • 设定明确目标——指标值、日期、预先约定的未达标应对方案。
  • 确定哪些现有指标作为虚荣指标停用。
产出物： 创建docs/METRICS.md，包含
## Stage & One Metric That Matters
、
## KPI Definitions
、
## Baselines & Targets
、
## Funnel
与
## Cohort Notes
部分。更新跟踪文件。
完成标准： METRICS.md中明确OMTM+反向指标，记录带日期的明确目标，列出按用户群体划分的基线数据，标记停用的虚荣指标，指定单屏仪表盘内容，并设置Rule 8获客门槛的留存率标准。

Phase 7 — Polish the micro-moments that make it feel alive (microinteractions)

阶段7 — 优化微交互，提升鲜活体验（microinteractions）

Purpose: Close the gap between an app people tolerate and one they love, in the moments they touch daily.
Brief (fallback): Every microinteraction has Trigger → Rules → Feedback → Loops & Modes. Feedback is immediate (<100ms for direct manipulation) and proportionate; animate the element the user touched over a separate toast. Map every state: empty, loading, partial, error, disabled, double-tap. Invest in one or two signature moments that pass the removal test; use long loops to retire hints for power users.
Invoke: Use the 
microinteractions
skill with the five most-used interactions. Ask for a Trigger/Rules/Feedback/Loops audit of each, the sub-100ms feedback and missing edge-case states, and one signature moment implemented in real code.
Decide with the user:
  • Which five interactions to audit.
  • Which one becomes the signature moment (removal test applied).
  • Which edge-case states to implement first.
Artifact: Extend docs/DESIGN.md 
## Microinteraction Inventory
(interaction | trigger/rules/feedback/loops | fix | status). Update the tracker.
Done when: the five interactions are in the inventory with their missing states and fixes, the signature moment is chosen, and each fix has a status.
目标： 缩小用户可容忍应用与用户喜爱应用之间的差距，优化日常使用的细微时刻。
备选简要说明： 每个微交互包含触发（Trigger）→ 规则（Rules）→ 反馈（Feedback）→ 循环与模式（Loops & Modes）四个环节。反馈需即时（直接操作反馈≤100ms）且适度；对用户触摸的元素进行动画处理，而非单独弹出提示。梳理所有状态：空状态、加载中、部分完成、错误、禁用、双击。投入资源打造一两个通过“移除测试”的标志性时刻；为资深用户使用长循环来隐藏提示。
调用： 使用
microinteractions
技能，提供五个最常用的交互场景。要求它对每个场景进行触发/规则/反馈/循环审计，指出≤100ms的反馈与缺失的边缘状态，并提供一个标志性时刻的代码实现方案。
与用户共同决策：
  • 选择五个要审计的交互场景。
  • 选择哪个场景成为标志性时刻（应用“移除测试”）。
  • 选择优先实现的边缘状态。
产出物： 扩展docs/DESIGN.md中的
## Microinteraction Inventory
（交互场景 | 触发/规则/反馈/循环 | 修复方案 | 状态）。更新跟踪文件。
完成标准： 五个交互场景已纳入清单，记录缺失状态与修复方案，选定标志性时刻，且每个修复方案均已标记状态。

Phase 8 — Sustain engagement with intrinsic motivation (drive-motivation)

阶段8 — 以内在动机维持用户活跃度（drive-motivation）

Purpose: Keep the loops from curdling — engagement that runs on Autonomy, Mastery, and Purpose instead of exploitation.
Brief (fallback): For any task needing cognitive effort, "if-then" rewards crush intrinsic motivation. Lasting engagement is Autonomy (choice over what/when/how/with whom), Mastery (visible progress, flow-calibrated challenge), and Purpose (why it matters). Autonomy killers: forced tutorials, unskippable steps, mandatory notifications. Reserve rewards for meaningful milestones; prefer "now-that" recognition over "if-then" bargains.
Invoke: Use the 
drive-motivation
skill with the app's gamification, streaks, points, and notification patterns. Ask for an AMP audit rated 0-10, every autonomy violation flagged, the point at which streaks tipped into loss aversion, and a progression redesign around real mastery and purpose.
Decide with the user:
  • Which autonomy violations to remove (forced/unskippable steps).
  • Which "if-then" rewards convert to "now-that" recognition.
  • Whether any streak/points mechanic exploits loss aversion and must change.
Artifact: Extend docs/PRODUCT.md 
## Activation & Retention Plan
with AMP-audit rows (violation/finding | fix | owner | status). Update the tracker.
Done when: the AMP score and every autonomy violation are recorded, the reward/streak fixes are rows with owners, and the loops pass the Manipulation Matrix from Rule 8.
目标： 避免习惯循环变质——让活跃度基于自主性（Autonomy）、精通（Mastery）与目标（Purpose），而非剥削式机制。
备选简要说明： 对于任何需要认知投入的任务，“如果-那么”式奖励会削弱内在动机。持久的活跃度来自自主性（对做什么/何时做/如何做/与谁做的选择权）、精通（可见的进度、匹配能力的挑战）与目标（意义所在）。自主性杀手：强制教程、无法跳过的步骤、强制通知。仅为有意义的里程碑提供奖励；优先选择“既然-那么”式认可，而非“如果-那么”式交易。
调用： 使用
drive-motivation
技能，提供应用的游戏化、连续登录奖励、积分与通知模式。要求它进行AMP（自主性/精通/目标）审计并打分（0-10分），标记所有自主性违规情况，指出连续登录奖励何时演变为损失厌恶，并围绕真实的精通与目标重新设计成长体系。
与用户共同决策：
  • 确定要移除的自主性违规情况（强制/无法跳过的步骤）。
  • 确定哪些“如果-那么”式奖励转换为“既然-那么”式认可。
  • 确定是否存在利用损失厌恶的连续登录/积分机制并需要修改。
产出物： 扩展docs/PRODUCT.md中的
## Activation & Retention Plan
，添加AMP审计条目（违规/发现 | 修复方案 | 负责人 | 状态）。更新跟踪文件。
完成标准： 记录AMP评分与所有自主性违规情况，奖励/连续登录修复方案均已添加带负责人的记录，且习惯循环通过Rule 8的“操纵矩阵”检验。

Optional Phases

可选阶段

SkillAdd whenArtifact
cold-start-problemthe app is a network or marketplace productExtends docs/PRODUCT.md
monetizing-innovationengaged users do not translate into revenueExtends docs/OFFER.md
contagioususers love the app but never mention itExtends docs/MARKETING.md
crossing-the-chasmgrowth stalls at the early-adopter boundaryExtends docs/STRATEGY.md
jobs-to-be-doneusage patterns say the app is hired for a different jobExtends docs/CUSTOMER.md
Optional phases follow the same operating rules — load and use each listed skill exactly as a core phase would; insert where the Add-when condition first becomes true. The acquisition-leaning ones — cold-start-problem, contagious, crossing-the-chasm — stay locked behind Rule 8 until retention clears the bar.
技能添加时机产出物
cold-start-problem应用为网络或平台产品时扩展 docs/PRODUCT.md
monetizing-innovation活跃用户无法转化为收入时扩展 docs/OFFER.md
contagious用户喜爱应用但从不分享时扩展 docs/MARKETING.md
crossing-the-chasm增长在早期采用者阶段停滞时扩展 docs/STRATEGY.md
jobs-to-be-done使用模式显示应用被用于其他用途时扩展 docs/CUSTOMER.md
可选阶段遵循相同的操作规则——完全按照核心阶段的方式加载并使用对应技能；在添加时机的条件首次满足时插入。获客导向的阶段——cold-start-problem、contagious、crossing-the-chasm——在留存率未达标前按Rule 8保持锁定。

Common Mistakes

常见错误

MistakeFix
Buying growth before fixing retentionPass the Stickiness gate (a flattening cohort curve) before any acquisition spend; keep acquisition phases locked per Rule 8.
Relying on external triggers foreverMigrate to an internal trigger via hooked-ux; treat notifications as scaffolding, not the load-bearing wall.
Optimizing the wrong Ability-Chain linkRate all six factors in improve-retention and fix the scarcest resource, not the most obvious one.
Jumping from outcome straight to solutionBuild the Opportunity Solution Tree in continuous-discovery first; the obvious feature is often the worst of five.
Measuring outputs, not outcomesInstrument every release; in lean-ux and inspired-product, success is a change in user behavior, not stories shipped.
Gamifying with points for everythingReserve rewards for meaningful milestones and run the drive-motivation AMP audit; "if-then" rewards crowd out your power users.
错误修复方案
在修复留存前投入获客资源在通过“粘性”门槛（用户群体曲线趋于平稳）前不进行任何获客投入；按Rule 8保持获客阶段锁定。
永远依赖外部触发通过hooked-ux迁移至内在触发；将通知视为临时支撑，而非核心机制。
优化错误的能力链环节在improve-retention中为所有六个因素打分，修复最稀缺的资源，而非最明显的问题。
直接从目标成果跳到解决方案先在continuous-discovery中构建机会解决方案树；看似明显的功能往往是五个方案中最差的。
衡量产出而非成果为每个版本添加监控；在lean-ux与inspired-product中，成功是用户行为的改变，而非完成的故事点数。
所有行为都用积分游戏化仅为有意义的里程碑提供奖励，并执行drive-motivation的AMP审计；“如果-那么”式奖励会赶走资深用户。

Completing the Journey

旅程完成标准

  • PRODUCT.md holds a Hook loop with the weakest phase fixed, an activation Starter Step, a living Opportunity Solution Tree, and an AMP-clean engagement design.
  • METRICS.md names the Stickiness-stage OMTM plus a counter-metric with a line in the sand (target, date, miss response).
  • At least one lean-ux experiment has resolved with a recorded verdict, and invalidated ideas are out of the backlog.
  • The retention bar set at intake is met — or the remaining gap is quantified — before any acquisition phase runs.
Close the tracker: every phase 
done
or 
skipped
, with Next Actions carried into PRODUCT.md, METRICS.md, and EXPERIMENTS.md. Then route forward:
  • When engagement mechanics cannot fix a product held back by broken UX or performance, continue with the 
    improve-app
    skill.
  • When the app is sticking and the business around it must keep pace — revenue, channels, operations — continue with the 
    grow-business
    skill.
  • PRODUCT.md包含已修复最薄弱环节的Hook循环、激活入门步骤、动态机会解决方案树，以及通过AMP审计的活跃度设计。
  • METRICS.md明确“粘性”阶段的OMTM与反向指标，并记录带日期的明确目标（指标值、日期、未达标应对方案）。
  • 至少一个lean-ux实验已完成并记录结论，被证伪的想法已从待办清单中移除。
  • 达到初始调研设定的留存率门槛——或已量化剩余差距——之后再启动任何获客阶段。
关闭跟踪文件：所有阶段标记为
done
或
skipped
，下一步行动已纳入PRODUCT.md、METRICS.md与EXPERIMENTS.md。之后引导至：
  • 若互动机制无法修复因UX或性能缺陷导致的产品问题，继续使用
    improve-app
    技能。
  • 若应用已实现高留存，需同步推进业务（收入、渠道、运营），继续使用
    grow-business
    技能。