conversion-optimization

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Conversion Optimization

转化优化

Turn one leaking conversion flow — a landing page, a signup, a checkout, an in-app onboarding — into a measured, tested funnel. This is an interactive, resumable journey of seven phases: the agent asks before every decision and records the outcome in your project's

docs/

folder, so you can stop after any phase and pick up later. It works on websites and inside products alike; the unit of work is the flow and its ONE action, not the whole site.

将存在漏洞的转化流程——着陆页、注册、结账、应用内引导——转变为可衡量、可测试的漏斗。这是一个包含七个阶段的交互式可恢复流程：Agent会在每个决策前提问，并将结果记录在项目的

docs/

文件夹中，您可以在任意阶段暂停，之后继续。该流程适用于网站和产品内部，核心优化单元是流程及其唯一目标动作，而非整个站点。

Core Principle

核心原则

Find the leak with numbers, learn the reason from customers, fix message → offer → proof → friction in that order, and prove every fix with a pre-committed test. The order is causal: a number tells you where, only research tells you why, motivation must be raised before friction-cutting pays, and an untested fix is a guess that compounds. This skill sequences the phases, asks the decision questions, and records every choice in

docs/

. The constituent skills carry the method — invoke them rather than improvising their frameworks.

用数据定位漏洞，从用户处了解原因，按“信息传递→报价→信任证明→消除摩擦”的顺序修复问题，并用预先约定的测试验证每一项修复。 顺序至关重要：数据告诉您漏洞位置，只有用户研究能解释原因；提升用户动机后，消除摩擦才能见效；未经测试的修复只是猜测，会不断累积误差。本技能会按顺序执行各阶段，提出决策问题，并将所有选择记录在

docs/

文件夹中。各阶段的方法由对应技能承载——请直接调用这些技能，而非自行摸索框架。

Journey Map

流程地图

Phase	Skill	Question it answers	Artifact
1	lean-analytics	Where does the flow actually leak, and what is the one metric?	Extends docs/METRICS.md — GATE
2	cro-methodology	Why do people drop at the leak — which objections and friction?	Creates docs/FUNNEL.md; extends docs/EXPERIMENTS.md — GATE
3	storybrand-messaging	Does the leaking step promise the visitor's own desired outcome in five seconds?	Extends docs/POSITIONING.md + docs/FUNNEL.md + docs/EXPERIMENTS.md
4	hundred-million-offers	Is the offer at the conversion point worth acting on now?	Extends docs/OFFER.md + docs/EXPERIMENTS.md
5	influence-psychology	Is there honest proof at every point of doubt?	Extends docs/FUNNEL.md + docs/EXPERIMENTS.md
6	design-everyday-things	Can a visitor who decided to act complete the flow without stumbling?	Extends docs/FUNNEL.md + docs/DESIGN.md + docs/EXPERIMENTS.md
7	cro-methodology	Will we know the fix worked — pre-committed metric, sample size, no peeking?	Extends docs/EXPERIMENTS.md + docs/METRICS.md

阶段	技能	解决的问题	产出文件
1	lean-analytics	流程的漏洞具体在哪里？核心指标是什么？	扩展docs/METRICS.md —— 关键准入阶段
2	cro-methodology	用户为何在漏洞环节流失？存在哪些异议和摩擦？	创建docs/FUNNEL.md；扩展docs/EXPERIMENTS.md —— 关键准入阶段
3	storybrand-messaging	漏洞环节能否在5秒内传达用户期望的结果？	扩展docs/POSITIONING.md + docs/FUNNEL.md + docs/EXPERIMENTS.md
4	hundred-million-offers	转化节点的报价是否足够吸引用户立即行动？	扩展docs/OFFER.md + docs/EXPERIMENTS.md
5	influence-psychology	每个用户存疑的节点是否有真实可信的证明？	扩展docs/FUNNEL.md + docs/EXPERIMENTS.md
6	design-everyday-things	决定行动的用户能否顺利完成整个流程？	扩展docs/FUNNEL.md + docs/DESIGN.md + docs/EXPERIMENTS.md
7	cro-methodology	我们如何确认修复有效？需包含预先约定的指标、样本量，且中途不查看结果？	扩展docs/EXPERIMENTS.md + docs/METRICS.md

Operating Rules

操作规则

Resume first. Before anything else, read
```
docs/CONVERSION-OPTIMIZATION-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.
Intake on first run only. No tracker: run the Intake below, then create
```
docs/CONVERSION-OPTIMIZATION-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.
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.
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.
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.
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
```
.
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.
Measure, research, then change — and every change is a test. No fix ships without a Phase 1 leak and a Phase 2 researched reason behind it, and every shipped change lands in docs/EXPERIMENTS.md with a pre-committed primary metric and a guardrail. A fix with no research behind it goes back to Phase 2; a bold change with no test attached stays in the backlog until it has one.

优先恢复流程：首先读取
```
docs/CONVERSION-OPTIMIZATION-PLAN.md
```
和流程地图中的所有产出文件。若存在跟踪文件，用3-5行总结当前流程状态，并询问进入哪个阶段。用户确认进入点后完成此步骤。已有跟踪文件的流程需恢复，而非重启。
仅首次运行时收集信息：若无跟踪文件，先执行下方的信息收集步骤，然后创建
```
docs/CONVERSION-OPTIMIZATION-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。
阶段进入：告知用户：本阶段的作用、需做出的决策、产出的文件、大致工作量。提供“继续/跳过/推迟”选项——标记为GATE的阶段可推迟，但不可跳过。若用户选择继续，将阶段标记为
```
in-progress
```
。用户做出选择后完成此步骤。
技能调用与备选方案：加载对应阶段的技能并使用：每个阶段的调用行以slug命名技能——使用该技能执行阶段。若技能不可用，提供选项：
```
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，并说明当前使用的模式。
阶段内决策：询问“与用户共同决策”下的所有问题——提供具体选项和推荐方案。将选择记录在跟踪文件的“关键决策”部分。未明确询问的决策视为缺陷。
阶段退出：在写入文件前，向用户展示产出文件的草稿内容以确认。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。
文件规范：先读取再写入；仅在文件不存在时创建，否则扩展内容——添加或更新您负责的章节，保留其他内容。docs/文件夹中的文件均为大写。所有建议需以复选框或包含负责人和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——从完整框架（所有章节标题）创建文件，然后填充当前阶段涉及的章节。
先衡量、研究，再修改——每一项修改都需测试：若没有阶段1定位的漏洞和阶段2研究的原因，不得发布任何修复；每一项发布的修改都需记录在docs/EXPERIMENTS.md中，包含预先约定的核心指标和防护措施。无研究依据的修复需退回阶段2；未附加测试的重大修改需留在待办事项中，直到添加测试为止。

Intake

信息收集

Ask these before creating the tracker:

Which flow are we optimizing, and what is the ONE action at its end? (Scopes every phase — a flow with three competing CTAs has no goal.)
Where do the numbers say people drop — analytics, funnel steps, cohort data? Paste what you have. (Feeds the Phase 1 leak diagnosis; no instrumentation means Phase 1 starts by adding it.)
Roughly how much traffic or volume enters the flow per week? (Gates Phase 7 — decides whether A/B tests can reach significance or the journey leans on qualitative evidence and before/after windows.)
What voice-of-customer sources exist or can be gotten — exit surveys, session recordings, support tickets, sales calls, reviews — and can you paste or export the raw text of the best one? (Phase 2 objections must quote the customer's own words, so the phase needs the content, not just the source name.)
What is the current offer at the conversion point — price, guarantee, bonuses — and can it change? (Gates Phase 4; a contractually fixed offer narrows it to presentation.)
Do docs/POSITIONING.md or docs/OFFER.md already exist from another journey? (Phases 3-4 build on them rather than restarting.)
How much of the journey do you want now? (Phases 1-2 are the mandatory diagnosis; 3-6 are the fix passes aimed by it; 7 turns fixes into proof.)

Skip heuristics: skip Phase 3 when messaging was already validated (e.g. an improve-website journey completed its message phases); skip Phase 4 when the offer is fixed by contract — record

skipped: reason

. Phase 7 may be

deferred: reason

at very low traffic in favor of before/after evidence with an explicit revert trigger, never silently skipped. Never skip Phases 1-2 — an unfound leak and an unresearched reason turn every later phase into guessing.

Then create

docs/CONVERSION-OPTIMIZATION-PLAN.md

from the template and confirm the plan. Done when the tracker exists with every phase statused and the user has confirmed the plan.

创建跟踪文件前需询问以下问题：

我们要优化哪个流程？其最终的唯一目标动作是什么？（限定所有阶段的范围——存在三个竞争CTA的流程没有明确目标。）
数据显示用户在哪个环节流失——分析数据、漏斗步骤、群组数据？请粘贴现有数据。（为阶段1的漏洞诊断提供依据；若无数据采集，阶段1需先添加数据采集。）
每周进入该流程的流量或用户量大致有多少？（决定阶段7的执行方式——判断A/B测试能否达到显著性，或流程是否依赖定性证据和前后对比窗口。）
现有或可获取的用户反馈来源有哪些——退出调查、会话录制、支持工单、销售通话、评论——能否粘贴或导出最相关的原始文本？（阶段2的异议需引用用户原话，因此需要具体内容，而非仅来源名称。）
转化节点当前的报价是什么——价格、担保、附加福利——能否调整？（决定阶段4的执行方式；若报价受合同约束，则仅优化呈现方式。）
是否已有来自其他流程的docs/POSITIONING.md或docs/OFFER.md文件？（阶段3-4会基于这些文件继续，而非重新开始。）
您现在希望推进流程的哪些部分？（阶段1-2是必须的诊断环节；阶段3-6是针对诊断结果的修复环节；阶段7将修复转化为可验证的成果。）

跳过规则：若信息传递已验证（例如完成improve-website流程的信息传递阶段），则跳过阶段3；若报价受合同约束，则跳过阶段4——记录

skipped: reason

。若流量极低，阶段7可标记为

deferred: reason

，改用前后对比证据并明确回滚触发条件，不得直接跳过。不得跳过阶段1-2——未找到漏洞和未研究原因的情况下，后续所有阶段都是猜测。

之后从模板创建

docs/CONVERSION-OPTIMIZATION-PLAN.md

并确认计划。跟踪文件创建完成且所有阶段已标记状态、用户确认计划后完成此步骤。

Phases

各阶段详情

Phases run in the listed order — each assumes the previous phase's artifact exists. Any phase can be entered, skipped, or deferred per the Operating Rules, but Phases 1-2 gate them all: nothing downstream fixes a problem that isn't a measured leak with a researched reason. When running any phase from its Brief (constituent skill not installed), read references/methods.md first — it carries each phase's full method, checklists, formulas, and benchmarks; the Brief is only the summary.

阶段按列出的顺序执行——每个阶段都假设前一阶段的产出文件已存在。根据操作规则，任何阶段都可进入、跳过或推迟，但阶段1-2是所有后续阶段的前提：若没有可衡量的漏洞和研究得出的原因，后续环节无法真正解决问题。若使用简要说明执行阶段（未安装对应技能），请先阅读references/methods.md——该文件包含每个阶段的完整方法、检查清单、公式和基准；简要说明仅为摘要。

Phase 1 — Find the leak (lean-analytics) — GATE

阶段1——定位漏洞（lean-analytics）——关键准入阶段

Purpose: Locate where the flow actually loses people and pick the one metric this journey moves — before any opinion about why.

Brief (fallback): A good metric is a comparative ratio that changes what you do next; totals and cumulative charts are vanity. Express each step of the flow as a conversion rate, compare against your own history and published benchmarks (e-commerce converts ~1-3% of visitors; landing pages on paid traffic low single digits), and find the biggest absolute drop on the highest-value path. Pick the One Metric That Matters for this journey, pair it with a counter-metric so it can't be gamed (signup rate × 30-day retention), and draw a line in the sand: target, date, pre-committed miss response. Cohort and segment (channel, device, plan) — one collapsing segment hides inside a flat average.

Invoke: Use the

lean-analytics

skill with the flow steps and analytics from intake. Ask for a step-by-step funnel table with baselines and benchmarks, the OMTM plus counter-metric for this journey, and the biggest leak ranked by absolute lost value.

Decide with the user: (1) Confirm the OMTM and its counter-metric. (2) Which leak to attack first — biggest absolute loss on the money path, not the easiest percentage. (3) If instrumentation is missing, which minimal events to add first — the phase stays

awaiting-evidence

until the numbers exist.

Artifact: Extend docs/METRICS.md

## Funnel

(stage | conversion | benchmark | bottleneck?),

## Stage & One Metric That Matters

, and

## Baselines & Targets

. Update the tracker.

Done when: the funnel is measured at the coarsest granularity that still localizes the leak to a single step, the OMTM and counter-metric are recorded with a line in the sand, and the leak is named — only then are Phases 2-7 unlocked. Finer sub-steps awaiting instrumentation stay

awaiting-evidence

in Next Actions and do not block the journey, provided the named leak does not depend on them.

目标：确定流程的具体流失环节，并选择本次流程要优化的核心指标——在猜测原因前完成此步骤。

简要说明（备选方案）：优质指标是能指导后续行动的对比比率；总量和累积图表属于 vanity 指标。将流程的每个步骤转化为转化率，与自身历史数据和公开基准对比（电商转化率约为1-3%；付费流量的着陆页转化率为低个位数），找到高价值路径上最大的绝对流失点。选择本次流程的核心指标（One Metric That Matters, OMTM），并搭配一个反指标以避免作弊（例如注册率×30天留存率），设定明确目标：指标目标、完成日期、未达成目标的应对方案。按群组和细分维度（渠道、设备、方案）分析——单一细分维度的流失可能被平均数据掩盖。

调用方式：使用

lean-analytics

技能，输入流程步骤和信息收集中的分析数据。要求提供包含基准和对比数据的分步漏斗表格、本次流程的OMTM及反指标、按绝对损失值排序的最大漏洞。

与用户共同决策：(1) 确认OMTM及其反指标。(2) 优先解决哪个漏洞——高价值路径上的最大绝对损失，而非最易优化的环节。(3) 若无数据采集，先添加哪些必要事件——在数据到位前，阶段状态保持为

awaiting-evidence

。

产出文件：扩展docs/METRICS.md中的

## Funnel

（阶段 | 转化率 | 基准 | 是否为瓶颈？）、

## Stage & One Metric That Matters

和

## Baselines & Targets

章节。更新跟踪文件。

完成标准：漏斗已按最粗粒度测量（仍能将漏洞定位到单个步骤），OMTM和反指标已记录并设定明确目标，漏洞已命名——此时解锁阶段2-7。更细的子步骤若需等待数据采集，可在“下一步行动”中标记为

awaiting-evidence

，不阻碍流程推进，前提是已命名的漏洞不依赖这些子步骤。

Phase 2 — Research why they leave (cro-methodology) — GATE

阶段2——研究流失原因（cro-methodology）——关键准入阶段

Purpose: Replace guesses about the leak with evidence from real visitors. Phases 3-6 may only fix problems traceable to a finding here.

Brief (fallback): Don't guess — discover. Mine primary sources (a one-question exit survey: "What's preventing you from [action] today?"; post-conversion: "What almost stopped you?"; chat logs, tickets, sales calls) and secondary sources (reviews, competitors) for the customer's own words. Sort objections into the Big 5 — Trust, Price, Fit, Timing, Effort — and build the O/CO table: every objection gets an evidence-backed counter placed at the exact step the doubt arises, never in an FAQ. Diagnose each step with the LIFT lenses (value proposition ± clarity, relevance, urgency, minus anxiety and distraction — Goward) and the MECLABS heuristic (conversion rises with motivation and value clarity, falls with friction and anxiety). Rank fix hypotheses by ICE and apply the 10x screen: if a change couldn't plausibly double the step, don't queue it.

Invoke: Use the

cro-methodology

skill with the Phase 1 leak, the flow, and the voice-of-customer sources from intake. Ask for the researched objection list in customer words, the O/CO table with placements, missing persuasion assets, and an ICE-ranked hypothesis backlog.

Decide with the user: (1) Which researched objection is the primary leak driver. (2) Low traffic: accept qualitative plus heuristic evidence — explicitly. (3) Which implicit objections need CO-Only counters (countered without being stated).

Artifact: Create docs/FUNNEL.md with

## Flow Map & ONE Action

## Leak Diagnosis

, and

## Objections & Counters (O/CO)

; extend docs/EXPERIMENTS.md

## Experiment Backlog

(ICE-ranked). METRICS.md

## Funnel

stays canonical for the conversion numbers — Leak Diagnosis cites them and adds the researched reason and severity. Update the tracker.

Done when: the flow map names the ONE action per step, every researched objection has an evidence-backed counter and a placement, and the backlog is ICE-ranked.

目标：用真实用户的证据替代对漏洞的猜测。阶段3-6仅能修复可追溯至本阶段发现的问题。

简要说明（备选方案）：不要猜测——要发现。从一手来源（单问题退出调查：“是什么阻止您今天完成[动作]？”；转化后调查：“是什么差点阻止您？”；聊天记录、工单、销售通话）和二手来源（评论、竞品）中提取用户原话。将异议分为五大类——信任、价格、适配性、时机、成本，并构建O/CO表格：每个异议都需有证据支持的应对方案，且放置在用户产生疑虑的 exact 环节，而非FAQ中。用LIFT模型（价值主张±清晰度、相关性、紧迫性，减去焦虑和干扰——Goward）和MECLABS启发式方法（转化率随动机和价值清晰度提升，随摩擦和焦虑降低）诊断每个步骤。按ICE评分排序修复假设，并应用10x筛选：若一项变更无法使步骤转化率翻倍，则不列入待办。

调用方式：使用

cro-methodology

技能，输入阶段1的漏洞、流程和信息收集中的用户反馈来源。要求提供用户原话的异议列表、带放置位置的O/CO表格、缺失的说服素材、按ICE评分排序的待办假设列表。

与用户共同决策：(1) 哪个研究得出的异议是主要流失原因。(2) 流量较低时：明确接受定性证据加启发式分析。(3) 哪些隐性异议需要仅应对（CO-Only）的方案（不直接提及异议，而是解决问题）。

产出文件：创建docs/FUNNEL.md，包含

## Flow Map & ONE Action

、

## Leak Diagnosis

和

## Objections & Counters (O/CO)

章节；扩展docs/EXPERIMENTS.md中的

## Experiment Backlog

（按ICE评分排序）章节。METRICS.md中的

## Funnel

章节是转化数据的权威来源——Leak Diagnosis章节引用这些数据，并添加研究得出的原因和严重程度。更新跟踪文件。

完成标准：流程地图明确每个步骤的唯一目标动作，每个研究得出的异议都有证据支持的应对方案和放置位置，待办列表已按ICE评分排序。

Phase 3 — Fix the message at the leak (storybrand-messaging)

阶段3——修复漏洞环节的信息传递（storybrand-messaging）

Purpose: Make the leaking step say what the visitor gets, in their words, in five seconds — clarity converts before persuasion can.

Brief (fallback): The customer is the hero; you are the guide. Run SB7 on the leaking step: a Character who wants one thing, their Problem at three levels (external, internal — the frustration the copy must name, philosophical), you as the Guide (empathy + authority), a 3-step Plan that makes acting feel safe, one Direct plus one Transitional CTA, and named failure/success stakes. Rewrite the step's headline in customer language pulled straight from Phase 2 — customer words outperform copywriter words. Then make it stick (Made to Stick): concrete beats abstract ("save 16 hours a month," not "boost productivity"), and pick the single Commander's Intent message the visitor must still remember tomorrow.

Invoke: Use the

storybrand-messaging

skill with the step's current copy, the Phase 2 objection evidence, and POSITIONING.md if it exists. Ask for above-the-fold rewrites that name the internal problem, a one-liner, and one Direct plus one Transitional CTA.

Decide with the user: Which rewrite passes the 5-second test (a stranger can say what's offered and why it matters); which internal problem the copy names; whether the step keeps a transitional CTA or goes single-CTA.

Artifact: Extend docs/POSITIONING.md

## Brand Script (StoryBrand)

## One-Liner

, and

## Key Messages

(surface | message | status); record the rewrite in the

Proposed message/CTA

column of docs/FUNNEL.md

## Flow Map & ONE Action

, leaving

Current message/CTA

intact as the before-state Phase 7 measures against; append copy tests to docs/EXPERIMENTS.md

## Experiment Backlog

. Update the tracker.

Done when: the leaking step has a rewritten message that names the internal problem, one primary CTA, and a logged test hypothesis.

目标：让漏洞环节在5秒内用用户的语言传达其能获得的价值——清晰的信息传递比说服更重要。

简要说明（备选方案）：用户是英雄；您是向导。对漏洞环节执行SB7框架：一个有明确需求的角色、三个层面的问题（外部、内部——文案需点明的挫败感、哲学层面）、您作为向导（共情+权威）、让行动更安全的三步计划、一个直接CTA加一个过渡CTA、明确的失败/成功后果。用阶段2提取的用户原话重写该环节的标题——用户的语言比文案的语言更有效。然后确保信息难忘（Made to Stick）：具体胜过抽象（例如“每月节省16小时”而非“提升生产力”），选择用户次日仍能记住的核心信息。

调用方式：使用

storybrand-messaging

技能，输入该环节当前的文案、阶段2的异议证据，以及已有的POSITIONING.md文件。要求提供点明内部问题的首屏重写文案、一句核心标语、一个直接CTA加一个过渡CTA。

与用户共同决策：哪个重写文案通过5秒测试（陌生人能说出提供的内容及其价值）；文案点明哪个内部问题；该环节是否保留过渡CTA或仅使用单个CTA。

产出文件：扩展docs/POSITIONING.md中的

## Brand Script (StoryBrand)

、

## One-Liner

和

## Key Messages

（呈现层 | 信息 | 状态）章节；在docs/FUNNEL.md的

## Flow Map & ONE Action

章节的

Proposed message/CTA

列记录重写内容，保留

Current message/CTA

列作为阶段7对比的原始状态；在docs/EXPERIMENTS.md的

## Experiment Backlog

章节添加文案测试。更新跟踪文件。

完成标准：漏洞环节有重写的文案（点明内部问题）、一个核心CTA，且已记录测试假设。

Phase 4 — Make the offer worth acting on (hundred-million-offers)

阶段4——让报价足够吸引用户行动（hundred-million-offers）

Purpose: Strengthen what is actually exchanged at the conversion point — the best flow cannot sell a weak offer, and the offer is the biggest single lever.

Brief (fallback): Value = (Dream Outcome × Perceived Likelihood) ÷ (Time Delay × Effort & Sacrifice). Raise the numerator with outcome language and proof; crush the denominator with speed ("first result in 5 minutes") and done-for-you framing. Reverse the risk with a guarantee aimed at the top Phase 2 objection — it raises perceived likelihood and lowers anxiety at once. Stack named, honestly-valued bonuses that each kill one objection; present price after value, anchored against the stack. Scarcity and urgency only when real — fake deadlines convert once and churn forever.

Invoke: Use the

hundred-million-offers

skill with the current offer from intake and the Phase 2 Price/Timing/Effort objections. Ask for a Value Equation score per lever, a guarantee design matched to the top objection, and a trim-and-stack pass on the offer components.

Decide with the user: Which guarantee the business can actually honor; which bonuses are real and sustainable; whether price presentation changes (anchoring, payment plans) — pricing itself may be out of scope; record that.

Artifact: Extend docs/OFFER.md

## Offer Stack

(element | description | honest value | objection it kills),

## Price Metric

when the flow raises what the price is charged per, plus

## Willingness-to-Pay Evidence

if new evidence surfaced; append offer tests to docs/EXPERIMENTS.md

## Experiment Backlog

. Update the tracker.

Done when: each Value Equation lever has a concrete change or a reason it stays, the guarantee targets the top researched objection, and every offer change carries a test hypothesis.

目标：强化转化节点的实际价值交换——再好的流程也无法推销薄弱的报价，报价是提升转化率的最大杠杆。

简要说明（备选方案）：价值 =（理想结果 × 感知可能性）÷（时间延迟 × 成本与牺牲）。用结果语言和证明提升分子；用速度（例如“5分钟内获得首个结果”）和“为您完成”的表述降低分母。针对阶段2的首要异议设计担保——同时提升感知可能性和降低焦虑。叠加有明确价值、能解决单个异议的附加福利；先呈现价值，再呈现价格，并以附加福利为锚点。仅在真实情况下使用稀缺性和紧迫感——虚假截止日期只能转化一次，且会导致永久流失。

调用方式：使用

hundred-million-offers

技能，输入信息收集中的当前报价和阶段2的价格/时机/成本异议。要求提供每个杠杆的价值等式评分、匹配首要异议的担保设计、对报价组件的精简和叠加优化。

与用户共同决策：企业能实际兑现的担保方案；哪些附加福利真实且可持续；是否调整价格呈现方式（锚定、付款计划）——价格本身可能不在优化范围内，需记录这一点。

产出文件：扩展docs/OFFER.md中的

## Offer Stack

（元素 | 描述 | 真实价值 | 解决的异议）、

## Price Metric

（若流程涉及价格计费单位）章节，以及

## Willingness-to-Pay Evidence

章节（若有新证据）；在docs/EXPERIMENTS.md的

## Experiment Backlog

章节添加报价测试。更新跟踪文件。

完成标准：价值等式的每个杠杆都有具体变更或不变更的原因，担保针对首要研究异议，每一项报价变更都附带测试假设。

Phase 5 — Put proof at every doubt (influence-psychology)

阶段5——在每个疑虑节点添加信任证明（influence-psychology）

Purpose: Answer each remaining objection with honest evidence placed at the exact step the doubt arises.

Brief (fallback): Under uncertainty people use shortcuts: social proof (specific numbers — "2,347 teams" — and similar-others beat generic praise), authority (credentials, certifications), commitment (a small first yes makes the big yes consistent — ask for the card after the value moment, not before), reciprocity (give the useful thing first), and scarcity (real only). Audit the flow for proof gaps: every O/CO row needs its counter actually rendered — testimonial, data point, logo bar, guarantee seal — at its placement. Proof hierarchy: specific results with context > named testimonials with faces > case studies > statistics > logos. The transparency test gates everything: if knowing the technique would make the visitor feel tricked, it fails. Fabricated proof and hidden costs are defects, not tactics.

Invoke: Use the

influence-psychology

skill with the FUNNEL.md O/CO table and the flow's current proof. Ask for a per-step proof audit, which principle answers each open objection, and copy for the two highest-impact placements.

Decide with the user: Which proof assets exist versus must be acquired (testimonial requests, case studies — log acquisition as Next Actions); where scarcity or urgency claims are genuinely true; which steps get a commitment micro-ask.

Artifact: Extend docs/FUNNEL.md

## Proof Inventory

(asset | type | placement | status) and complete the

## Objections & Counters (O/CO)

placements; append proof tests to docs/EXPERIMENTS.md

## Experiment Backlog

. Update the tracker.

Done when: every open objection row has a real proof asset placed or an acquisition task with an owner, and no claim in the flow is unverifiable.

目标：用真实证据在用户产生疑虑的 exact 环节解决剩余异议。

简要说明（备选方案）：不确定情况下，用户会使用决策捷径：社会证明（具体数字——“2347个团队”——和相似用户的评价胜过泛泛的赞美）、权威（资质、认证）、承诺（小的前置同意会让后续的大同意更一致——在价值呈现后再请求付款信息，而非之前）、互惠（先提供有价值的内容）、稀缺性（仅真实情况）。审计流程中的信任证明缺口：O/CO表格的每一行都需在对应位置呈现应对方案—— testimonial、数据点、logo栏、担保印章。信任证明优先级：带上下文的具体结果 > 带头像的用户评价 > 案例研究 > 统计数据 > logo。透明度测试是底线：若用户知道使用该技巧会感到被欺骗，则不可行。伪造的信任证明和隐藏成本是缺陷，而非策略。

调用方式：使用

influence-psychology

技能，输入FUNNEL.md的O/CO表格和流程当前的信任证明。要求提供分步信任证明审计、解决每个未决异议的心理学原则、两个最高影响位置的文案。

与用户共同决策：哪些信任证明素材已存在，哪些需要获取（请求评价、案例研究——将获取任务记录在下一步行动中）；哪些稀缺性或紧迫感声明是真实的；哪些环节需要添加微小的承诺请求。

产出文件：扩展docs/FUNNEL.md中的

## Proof Inventory

（素材 | 类型 | 放置位置 | 状态）章节，并完成

## Objections & Counters (O/CO)

章节的放置位置；在docs/EXPERIMENTS.md的

## Experiment Backlog

章节添加信任证明测试。更新跟踪文件。

完成标准：每个未决异议行都有真实的信任证明素材或带负责人的获取任务，流程中无不可验证的声明。

Phase 6 — Remove the friction (design-everyday-things)

阶段6——消除流程摩擦（design-everyday-things）

Purpose: Protect the visitors who decided to act. B=MAP: behavior happens when Motivation, Ability, and a Prompt converge — Phases 3-5 raised motivation; this phase raises ability and sharpens prompts.

Brief (fallback): Bridge Norman's two gulfs. Execution: clear signifiers (buttons look pressable, fields look editable) and constraints that make errors impossible (date picker over free text, submit disabled until valid). Evaluation: feedback within 0.1s of every action, progress indication on multi-step flows. Forms (Baymard): every field costs conversions — cut to the minimum, ask for payment as late as possible, show all costs before the final step (surprise shipping and taxes is the #1 checkout killer), offer guest checkout, validate inline with messages that say how to fix. Error messages state what went wrong and how to fix it, without blame; slips get undo, not are-you-sure dialogs.

Invoke: Use the

design-everyday-things

skill with the conversion-critical steps (form, payment, confirmation). Ask for weak signifiers, where constraints replace error messages, feedback gaps, field-by-field form cuts, and message rewrites.

Decide with the user: Which fields are truly required now versus collectable later; where a constraint replaces a warning; whether the flow shows total cost earlier; which severity-4 friction items ship immediately as a logged before/after card versus wait for a full test.

Artifact: Extend docs/FUNNEL.md

## Flow Friction Audit

(step | issue | severity 0-4 | fix | status); extend docs/DESIGN.md

## UX Audit Findings

for reusable component fixes, naming the Norman gulf (execution or evaluation) in the

Heuristic

column; append fixes to docs/EXPERIMENTS.md

## Experiment Backlog

. Update the tracker.

Done when: every step has a friction audit row, forms are cut to minimum fields, severity-4 items have owners, and error messages meet the checklist. Where money changes hands in this flow, all costs are visible before the final step and guest checkout is offered; in a flow that takes no payment, mark those two rows

n/a

目标：保护已决定行动的用户。B=MAP模型：行为发生在动机、能力和提示三者结合时——阶段3-5提升了动机；本阶段提升能力并优化提示。

简要说明（备选方案）：跨越Norman的两个鸿沟。执行层面：清晰的标识（按钮看起来可点击，输入框看起来可编辑）和防止错误的约束（用日期选择器替代自由文本，表单验证通过前禁用提交按钮）。评估层面：每个动作后0.1秒内给出反馈，多步骤流程显示进度。表单（Baymard）：每个字段都会降低转化率——精简到最少，尽可能晚地请求付款信息，在最终步骤前显示所有成本（意外运费和税费是结账弃用的头号原因），提供访客结账选项，实时验证并给出修复提示。错误信息需说明问题和修复方法，不得指责用户；操作失误需提供撤销选项，而非确认对话框。

调用方式：使用

design-everyday-things

技能，输入转化关键步骤（表单、付款、确认）。要求提供薄弱标识、用约束替代错误提示的位置、反馈缺口、逐字段的表单精简、文案重写。

与用户共同决策：哪些字段是当前必需的，哪些可后续收集；哪些位置用约束替代警告；流程是否提前显示总成本；哪些严重程度为4的摩擦项立即发布（记录为前后对比卡片），哪些等待完整测试。

产出文件：扩展docs/FUNNEL.md中的

## Flow Friction Audit

（步骤 | 问题 | 严重程度0-4 | 修复方案 | 状态）章节；扩展docs/DESIGN.md中的

## UX Audit Findings

章节（针对可复用组件的修复，在

Heuristic

列注明Norman鸿沟类型：执行或评估）；在docs/EXPERIMENTS.md的

## Experiment Backlog

章节添加修复方案。更新跟踪文件。

完成标准：每个步骤都有摩擦审计行，表单已精简到最少字段，严重程度为4的项有负责人，错误信息符合检查清单。若流程涉及资金交易，最终步骤前需显示所有成本并提供访客结账选项；若流程不涉及付款，将这两行标记为

n/a

。

Phase 7 — Prove it (cro-methodology)

阶段7——验证修复效果（cro-methodology）

Purpose: Turn the high-ICE fixes into trustworthy experiments — without rigor you cannot tell a real lift from noise, and a false winner compounds forever.

Brief (fallback): Pre-commit everything (Kohavi): primary metric, guardrail metrics (the Phase 1 counter-metric, revenue per visitor, support volume), sample size computed from baseline rate and minimum detectable effect at 95% significance / 80% power, and a duration of at least one full business cycle covering weekdays and weekends. Never peek and stop early — it manufactures false positives; never rerun until you like the answer. Test bold changes — meek tweaks rarely reach significance. Low traffic: run a before/after window with qualitative confirmation, or ship as a reversible bet with an explicit revert trigger — and say which you are doing. Practical significance gates rollout: a statistically significant 0.1% lift may not pay for its complexity. Winners become the new control; losers become learnings written down.

Invoke: Use the

cro-methodology

skill with the top ICE hypotheses from the backlog. Ask for full experiment designs: hypothesis in "If [change], then [metric] because [research]" form, pre-committed sample size and duration, and the decision rule.

Decide with the user: Which 1-3 hypotheses run first (highest ICE on the money path); the guardrail metrics; what happens on a flat result — iterate the fix, or return to Phase 2 for better research.

Artifact: Promote backlog rows to docs/EXPERIMENTS.md

## Experiment Cards

, adding the pre-committed sample size per arm, planned duration, and the minimum lift worth keeping as extra bullets on the card (the skeleton's bullets carry hypothesis, metrics, and decision rule; extra bullets are additive and allowed); record results and verdicts as they land; extend docs/METRICS.md

## Baselines & Targets

with a new dated row per tested metric, leaving the pre-test baseline row intact. Update the tracker.

Done when: each shipped fix is a card with a pre-committed metric, sample size, and decision rule; results carry verdicts; and the OMTM's new baseline is written down.

目标：将高ICE评分的修复转化为可信的实验——若无严谨性，无法区分真实提升和随机波动，错误的“成功”会不断累积。

简要说明（备选方案）：预先约定所有内容（Kohavi）：核心指标、防护指标（阶段1的反指标、每访客收入、支持量）、基于基准转化率和最小可检测效果计算的样本量（95%显著性/80%功效）、至少覆盖一个完整业务周期（包含工作日和周末）的时长。中途不得查看结果并提前停止——这会制造假阳性结果；不得反复测试直到得到满意结果。测试重大变更——微小调整很难达到显著性。流量较低时：运行前后对比窗口并搭配定性确认，或作为可逆方案发布并明确回滚触发条件——需说明使用哪种方式。实际显著性决定是否推广：统计上显著但仅提升0.1%的效果可能不值得投入成本。成功方案成为新的基准；失败方案记录为经验教训。

调用方式：使用

cro-methodology

技能，输入待办列表中高ICE评分的假设。要求提供完整的实验设计：假设采用“如果[变更]，那么[指标]会[变化]，因为[研究依据]”的形式，预先约定的样本量和时长，决策规则。

与用户共同决策：优先运行哪1-3个假设（高价值路径上ICE评分最高的）；防护指标；若结果无变化——迭代修复方案，还是返回阶段2做更深入的研究。

产出文件：将待办列表中的行升级为docs/EXPERIMENTS.md中的

## Experiment Cards

，添加每个分组的预先约定样本量、计划时长、值得保留的最小提升（框架的项目符号包含假设、指标、决策规则；额外项目符号为补充内容）；记录结果和结论；扩展docs/METRICS.md中的

## Baselines & Targets

章节，为每个测试指标添加新的日期行，保留测试前的基准行。更新跟踪文件。

完成标准：每个发布的修复都有包含预先约定指标、样本量和决策规则的实验卡片；结果已记录结论；OMTM的新基准已写入文件。

Optional Phases

可选阶段

Skill	Add when	Artifact
ux-heuristics	the whole page confuses, not just the flow — visitors stumble before reaching the conversion steps	Extends docs/DESIGN.md `## UX Audit Findings`
microinteractions	the flow's moments feel dead — silent taps, unexplained waits, abrupt state changes	Extends docs/DESIGN.md `## Microinteraction Inventory`
scorecard-marketing	the flow needs a lower-commitment entry — a quiz or assessment as the transitional conversion	Extends docs/WEBSITE.md `## Lead Capture`
hooked-ux	the conversion sticks but the next visit doesn't — post-conversion activation is the real leak	Extends docs/PRODUCT.md `## Hook Model`

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. They carry no inline Brief: standalone, run ux-heuristics as a severity-rated pass over Nielsen's 10 heuristics, microinteractions as a trigger/rules/feedback/loops inventory, scorecard-marketing as a quiz-funnel design ending in a personalized result, and hooked-ux as a trigger → action → variable reward → investment loop audit — or install the named skill for its full framework.

技能	适用场景	产出文件
ux-heuristics	整个页面存在混淆，而非仅流程问题——用户在到达转化步骤前就遇到障碍	扩展docs/DESIGN.md `## UX Audit Findings`
microinteractions	流程交互缺乏活力——点击无反馈、等待无说明、状态切换突兀	扩展docs/DESIGN.md `## Microinteraction Inventory`
scorecard-marketing	流程需要更低门槛的入口——以测验或评估作为过渡转化方式	扩展docs/WEBSITE.md `## Lead Capture`
hooked-ux	转化成功但用户不再回访——转化后的激活是真正的漏洞	扩展docs/PRODUCT.md `## Hook Model`

可选阶段遵循相同的操作规则——按核心阶段的方式加载并使用对应技能；在适用场景首次出现时插入。这些阶段无内置简要说明：单独运行时，ux-heuristics是基于Nielsen十大启发式的严重程度评分审计，microinteractions是触发/规则/反馈/循环的清单，scorecard-marketing是生成个性化结果的测验漏斗设计，hooked-ux是触发→动作→可变奖励→投入的循环审计——或安装对应技能以使用完整框架。

Common Mistakes

常见错误

Mistake	Fix
Redesigning the step before measuring where the leak is	Run Phase 1 first — the biggest drop is rarely where opinion points; optimize the money path, not the loudest complaint.
Guessing objections instead of mining customer words	Exit surveys, tickets, and sales calls (cro-methodology) — teams are almost always wrong about why visitors leave.
Polishing persuasion on top of an unclear message	Clarity before psychology: pass the 5-second test (storybrand-messaging) before adding proof and urgency.
Treating the offer as fixed and testing only cosmetics	The offer is the biggest lever (hundred-million-offers); a guarantee change outlifts a button change by orders of magnitude.
Faking scarcity or cherry-picking proof	Converts once, churns forever, caps trust permanently — real scarcity and verifiable proof only (influence-psychology).
Adding form fields "while we're at it"	Every field costs conversions (Baymard); collect later what you don't need now (design-everyday-things).
Peeking at test results and stopping early	Pre-commit sample size and duration, then report whatever comes back (cro-methodology, Kohavi).

错误	修复方案
在测量漏洞位置前重新设计环节	先运行阶段1——最大的流失点往往不是主观认为的位置；优化高价值路径，而非最受抱怨的环节。
猜测异议而非提取用户原话	使用退出调查、工单和销售通话（cro-methodology）——团队几乎总是错误判断用户流失的原因。
在信息传递不清晰的情况下优化说服内容	先确保清晰，再使用心理学：通过5秒测试（storybrand-messaging）后再添加信任证明和紧迫感。
将报价视为固定项，仅测试表面内容	报价是最大的杠杆（hundred-million-offers）；担保变更的提升效果比按钮变更高几个数量级。
伪造稀缺性或挑选片面的信任证明	只能转化一次，导致永久流失，永久限制信任——仅使用真实的稀缺性和可验证的信任证明（influence-psychology）。
顺便添加表单字段	每个字段都会降低转化率（Baymard）；当前不需要的信息后续再收集（design-everyday-things）。
查看测试结果并提前停止	预先约定样本量和时长，然后如实报告结果（cro-methodology, Kohavi）。

Completing the Journey

流程完成

A funnel always has a next-biggest leak: when the Phase 7 verdicts land, re-enter Phase 1 with fresh numbers rather than declaring victory — the journey is a loop with an exit condition, and the exit condition is the line in the sand from Phase 1, not exhaustion.

Exit checklist — every box tied to an artifact:

Every phase in

docs/CONVERSION-OPTIMIZATION-PLAN.md

done

deferred: reason

, or

skipped: reason

The OMTM, counter-metric, and line in the sand are recorded with pre- and post-test baselines (METRICS.md).
Every researched objection has a placed, verifiable counter (FUNNEL.md O/CO and Proof Inventory — no open rows on the money path).
The flow's forms and steps carry no severity-4 friction without an owner (FUNNEL.md Flow Friction Audit).
Each shipped change is an Experiment Card with a pre-committed metric and a recorded verdict (EXPERIMENTS.md).

Close the tracker: remaining Next Actions carried into FUNNEL.md and EXPERIMENTS.md so nothing is lost. Then route forward: when the flow converts and needs more qualified traffic, continue with the

grow-website

skill; when the leak has moved past conversion into engagement and retention, continue with the

improve-app

skill; when the whole site — look, typography, speed, message — needs the broader pass, continue with the

improve-website

skill.

漏斗永远存在下一个最大的漏洞：阶段7的结论出来后，用新数据重新进入阶段1，而非宣告胜利——流程是一个带有退出条件的循环，退出条件是阶段1设定的明确目标，而非疲惫。

退出检查清单——每个项都对应产出文件：

docs/CONVERSION-OPTIMIZATION-PLAN.md

中的每个阶段都标记为

done

、

deferred: reason

或

skipped: reason

。

OMTM、反指标和明确目标已记录测试前后的基准（METRICS.md）。
每个研究得出的异议都有放置到位的可验证应对方案（FUNNEL.md的O/CO和信任证明清单——高价值路径无未完成项）。
流程的表单和步骤中，严重程度为4的摩擦项都有负责人（FUNNEL.md的流程摩擦审计）。
每个发布的变更都有包含预先约定指标和记录结论的实验卡片（EXPERIMENTS.md）。

关闭跟踪文件：将剩余的下一步行动转移到FUNNEL.md和EXPERIMENTS.md中，确保无遗漏。然后引导后续：若流程转化率良好且需要更多精准流量，继续使用

grow-website

技能；若漏洞从转化环节转移到用户参与和留存环节，继续使用

improve-app

技能；若需对整个网站的外观、排版、速度、信息传递进行全面优化，继续使用

improve-website

技能。