Modeling Conversion Metrics
PostHog/posthog
Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project.
对转化执行完整的分析流程，算清楚用户转不转、转化率多少、有没有变化，含口径定义、取数、转化率计算，及可选的异常分析、维度拆分与对比/归因。触发条件：对话涉及转化率分析、转化表现评估、转化变化归因等任务时触发，如出现「分析对话转化率」「转化率表现如何」「不同群体/地区/时间的转化率对比」「分维度后转化情况」「转化率是否异常」等相似问题时触发。
Apache-2.0Auto-check passed
Install Bi Conversion Analysis
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-conversion-analysis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data bi-conversion-analysis --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis .claude/skills/bi-conversion-analysis && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "bi-conversion-analysis" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis into .claude/skills/bi-conversion-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-conversion-analysis", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysisType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-conversion-analysis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data bi-conversion-analysis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis .agents/skills/bi-conversion-analysis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "bi-conversion-analysis" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis into .agents/skills/bi-conversion-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-conversion-analysis", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-conversion-analysis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data bi-conversion-analysis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis .cursor/skills/bi-conversion-analysis && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "bi-conversion-analysis" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis into .cursor/skills/bi-conversion-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-conversion-analysis", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/agentscope-ai/QwenPaw-Data.git --path packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-conversion-analysis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data bi-conversion-analysis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis .gemini/skills/bi-conversion-analysis && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "bi-conversion-analysis" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis into .gemini/skills/bi-conversion-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-conversion-analysis", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install agentscope-ai/QwenPaw-Data bi-conversion-analysisInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-conversion-analysis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis .github/skills/bi-conversion-analysis && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "bi-conversion-analysis" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis into .github/skills/bi-conversion-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-conversion-analysis", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add agentscope-ai/QwenPaw-Data --skill bi-conversion-analysis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agentscope-ai/QwenPaw-Data bi-conversion-analysis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentscope-ai/QwenPaw-Data.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis .opencode/skills/bi-conversion-analysis && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "bi-conversion-analysis" agent skill from https://github.com/agentscope-ai/QwenPaw-Data/tree/main/packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis into .opencode/skills/bi-conversion-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bi-conversion-analysis", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
bi-conversion-analysis- GitHub stars
- 113
- Token cost
- ~971 tokens
- SKILL.md length
- 241 words
- Files
- 1
- Skills in repo
- 26
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
对转化执行完整的分析流程，算清楚用户转不转、转化率多少、有没有变化，含口径定义、取数、转化率计算，及可选的异常分析、维度拆分与对比/归因。触发条件：对话涉及转化率分析、转化表现评估、转化变化归因等任务时触发，如出现「分析对话转化率」「转化率表现如何」「不同群体/地区/时间的转化率对比」「分维度后转化情况」「转化率是否异常」等相似问题时触发。
- Works in 6 steps: 定义口径 → 取数 → 计算转化率 → …
- SKILL.md covers 前置条件, 分析原则, 1. 定义口径 and 2. 取数, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Bi Conversion Analysis is an agent skill from agentscope-ai/QwenPaw-Data. 对转化执行完整的分析流程，算清楚用户转不转、转化率多少、有没有变化，含口径定义、取数、转化率计算，及可选的异常分析、维度拆分与对比/归因。触发条件：对话涉及转化率分析、转化表现评估、转化变化归因等任务时触发，如出现「分析对话转化率」「转化率表现如何」「不同群体/地区/时间的转化率对比」「分维度后转化情况」「转化率是否异常」等相似问题时触发。
Its SKILL.md is about 970 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Agentic enterprise data analytics: governed facts (DataBridge), reusable methodology (Skill-Hub), and controllable execution (Host). The licence is Apache-2.0.
Example prompts
- “/bi-conversion-analysis”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e0bae36. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are csv).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Bi Conversion Analysis loads about 971 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 241 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from agentscope-ai/QwenPaw-Data at commit e0bae36, republished under its Apache-2.0 licence (© agentscope-ai). 241 words, ~971 tokens.
Download SKILL.mdSave it as
.claude/skills/bi-conversion-analysis/SKILL.md (or your agent's skills folder).- name
- bi-conversion-analysis
- description
- 对转化执行完整的分析流程，算清楚用户转不转、转化率多少、有没有变化，含口径定义、取数、转化率计算，及可选的异常分析、维度拆分与对比/归因。触发条件：对话涉及转化率分析、转化表现评估、转化变化归因等任务时触发，如出现「分析对话转化率」「转化率表现如何」「不同群体/地区/时间的转化率对比」「分维度后转化情况」「转化率是否异常」等相似问题时触发。
bi-conversion-analysis
对转化执行完整的分析流程，核心目标是算清楚用户转不转、转化率多少、有没有变化：定义口径 → 取数 → 计算转化率 →（可选）异常分析 →（可选）拆分维度 / 对比归因 → 解读与输出。
前置条件
开始执行前，确认以下信息已就绪：
- 转化漏斗明确，即起始行为（接触目标行为，如访问、曝光、进入页面）与结束行为（完成目标行为，如对话、注册、付费）已定义
- 转化率指标已确定（如对话转化率、付费转化率等），对应分子/分母口径清晰
- 数据获取能力可用，能取到计算转化率所需的 CSV 或等价数据
- 分析范围明确，包括时间窗口、对象范围，以及是否需要拆分维度或做对比
若转化漏斗或指标口径不明确，需先回到规划阶段补充，或向用户确认后再开始执行。
分析原则
主要步骤
| 步骤 | 用途 | 是否必选 |
|---|---|---|
| 定义口径 | 确定转化漏斗与转化率指标 | 必选，见步骤 1 |
| 取数 | 按口径取分子/分母数据 | 必选，见步骤 2 |
| 计算转化率 | 计算起始行为到结束行为的转化率 | 必选，见步骤 3 |
| 异常分析 | 识别转化率时间序列中的异常波动点 | 可选，见步骤 4 |
| 拆分维度 / 对比 | 按维度分别计算并跨时间、群体对比差异 | 可选，见步骤 5 |
| 解读 & 输出 | 转化漏斗、关键节点、异常点、差异结论 | 必选，见步骤 6 |
典型产出：转化率表、转化漏斗图、转化率时间序列（含异常点标注）、分维度转化对比。
最短路径：定义口径 → 取数 → 算转化率 → 报数字 / 看趋势（即步骤 1 → 2 → 3 → 6，跳过步骤 4、5）。
本 workflow 主要提供转化率分析场景下的编排与数据衔接逻辑，各步骤的具体执行按相应分析方法的标准流程进行。
1. 定义口径
明确转化漏斗与转化率指标，这是后续取数与计算的基础：
| 要素 | 含义 | 常见取值 |
|---|---|---|
| 起始行为（分母） | 进入漏斗、接触目标行为的口径 | 访问、曝光、进入页面、加购等 |
| 结束行为（分子） | 完成目标行为的口径 | 对话、注册、下单、付费等 |
| 转化率指标 | 由分子/分母构成的比率 | 对话转化率、付费转化率、下单转化率等 |
要点：
- 同一分析可包含多级漏斗（如访问 → 对话 → 付费），需为每一环节分别定义分子/分母
- 同一分析可包含多种转化率指标，需分别定义口径
- 口径一旦确定，后续取数、计算、对比须保持一致，避免分子分母错配
2. 取数
按步骤 1 确定的口径取数，准备转化率计算所需的数据。
数据准备
整理 CSV，包含转化率计算所需的列：
- 起始行为用户数（分母，如访问用户数）
- 结束行为用户数（分子，如对话用户数）
- 如需多级漏斗或多种转化率指标，分别取对应的分子/分母列
示例：
date,访问用户数,对话用户数,付费用户数
2025-01-01,10000,3000,300
2025-01-02,10500,3200,280若计划在步骤 5 拆分维度，取数时一并带出维度列（如渠道、端、国家、版本），或按维度分别取数。
3. 计算转化率
计算从起始行为到结束行为的转化率。
计算执行
- 对每个需要报告的转化率指标按转化率公式（结束行为用户数 / 起始行为用户数）或可用脚本进行计算
- 多级漏斗时，计算各环节转化率（及整体转化率），供绘制转化漏斗图
- 不遗漏任何必要的转化率指标
- 保存计算结果
若已规划拆分维度，可在此步先算整体转化率，维度拆分在步骤 5 展开。
4. （可选）转化率异常分析
查看计算得到的转化率是否是时间相关的序列，若是，则对步骤 3 产出的转化率时间序列进行异常波动点识别，若否，则跳过本步骤。
数据准备
基于步骤 3 的转化率结果，整理含时间序列的 CSV，至少包含：
- 日期列：时间标识
- 指标列：转化率（如对话转化率）
示例：
date,对话转化率
2025-01-01,0.3000
2025-01-02,0.0952
2025-01-03,0.0095若已拆分维度，对需要报告的各维度/cohort 及总体分别准备时间序列并执行异常检测。
异常检测执行
- 按异常检测的对比逻辑（日异常检测建议同时检查日环比和周同比）
- 按优先级确定阈值（用户指定 → 域知识包 → 语义层 → 自适应）
- 按异常检测的标准原理或可用脚本自行实现
- 记录异常波动点、对应变化率及所用阈值
5. （可选）拆分维度 / 对比归因
根据分析要求，判断是否需要按维度分别计算转化率，或跨时间、群体、地区对比：
需要拆分/对比 → 执行后进入步骤 6 无需拆分/对比 → 跳过本步骤，直接进入步骤 6（最短路径在此跳过）
判断依据
| 信号 | 示例 |
|---|---|
| 按已有维度拆分 | 「按渠道/端/国家/版本看转化」（维度已在数据中，直接分组计算） |
| 需发现未知用户子结构 | 「哪些用户群体转化更高」「用户自然分群后的转化差异」（走聚类分群） |
| 时间维度对比 | 「环比/同比变化」「最近 vs 历史」「转化率是否下降」 |
| 群体/空间维度对比 | 「不同国家/渠道/端/实验组转化差异」「A 群 vs B 群」 |
| 显式对比/差异/优劣 | 「对比」「差异」「哪个更高/更低」「是否显著」 |
| 信号 | 示例 |
|---|---|
| 仅报告整体水平 | 「当前转化率是多少」「整体转化表现如何」（步骤 3 结果已足够） |
| 单一对象无参照 | 只有一个时间点、一个群体，无对比参照物 |
拆分 / 对比执行（若启用）
- 拆分维度：
- 按已有维度拆分：以维度列（渠道 / 端 / 国家 / 版本等）为分组键，对每个维度值分别按步骤 3 计算转化率
- 按用户特征分群：整理用户级 CSV（对象标识列 + 分群特征列）完成聚类分群，结果保存为 JSON，再按用户 ID 关联转化数据，按群分别准备分子/分母后计算转化率
- 对比归因：基于转化率结果（可结合步骤 4 的异常点上下文），整理 对比分析用 CSV：
- 时间对比：每列对应一个时期，或一列时间序列供环比/同比计算
- 空间对比：每列对应一个国家/渠道/端/版本/cohort 等
- 选择合适比较维度（时间 / 空间 / 标准）与计算方式（绝对差值 / 相对差值）执行对比分析
- 多样本时按显著性检验规则执行
- 保存拆分与对比分析结果
示例（不同端转化对比）：
业务日期,web端转化率,app端转化率
20251101,0.7856,0.2343
20251102,0.2288,0.88226. 解读 & 输出
完成以上步骤后，围绕转不转、转化率多少、有没有变化汇总并输出。
| 字段 | 说明 |
|---|---|
| 执行内容 | 本步骤做了什么（含跳过的可选步骤及原因） |
| 取数文件 | 原始数据路径 |
| 中间产物 | 分群 JSON（若执行）、异常检测输入 CSV、对比用 CSV（若执行） |
| 计算结果 | 转化率、异常波动点及对比分析结果路径 |
| 结论 | 转化率水平、漏斗各环节、异常波动、变化趋势、群体差异及显著性 |
汇总结构建议：
- 分析范围：时间窗口、口径定义（转化漏斗 / 转化率指标）、是否拆分维度、是否做对比
- 转化率结果：整体及各维度/cohort 的转化率水平，含漏斗各环节（转化漏斗图）
- 异常发现（若执行步骤 4）：异常波动点、变化幅度、所用对比逻辑与阈值
- 对比发现（若执行步骤 5）：时间变化幅度、群体间差异、显著性结论
- 业务解读：转化表现评价、关键驱动因素与可执行建议
- 局限与不确定性：样本量、口径差异、分群稳定性、未覆盖维度等
© agentscope-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis of agentscope-ai/QwenPaw-Data.
Open the folder on GitHubat commit e0bae36
Compare with similar skills
Bi Conversion Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Bi Conversion Analysis this skillagentscope-ai/QwenPaw-Data | 113 | — | ~971 | Automated safety check: Pass | Apache-2.0 | |
| Modeling Conversion MetricsPostHog/posthog | 40k | — | ~1.4k | Automated safety check: Pass | Custom licence | |
| Cost Conversationruvnet/ruflo | 74k | — | ~407 | Automated safety check: Notes | MIT | |
| Conversation Memorydavila7/claude-code-templates | 32k | 5 repos | ~440 | Automated safety check: Pass | MIT | |
| Conversation Archivegarrytan/gbrain | 31k | — | ~5.6k | Automated safety check: Pass | MIT | |
| Landing Page Conversion Auditgithub/awesome-copilot | 40k | 1 repos | ~1.8k | Automated safety check: Pass | MIT |
Similar skills
- Official
Cost Conversation
ruvnet/ruflo
Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost
Conversation Memory
davila7/claude-code-templates
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.
Conversation Archive
garrytan/gbrain
Import AI-assistant chat exports (ChatGPT, Claude, Perplexity) and agent session transcripts into the brain as one dated page per conversation under conversations/, validate each page against the…
- Official
Landing Page Conversion Audit
github/awesome-copilot
Audit a landing page, sales page or checkout page for conversion leaks and return a fix list ordered by expected revenue impact.
Capture Conversation
outline/outline
Save the current conversation, a decision, or a set of notes as a document in an Outline collection; use when the user wants to keep what was discussed in their knowledge base.
More from agentscope-ai/QwenPaw-Data
All 26 skills in this repoBi Report Generation
agentscope-ai/QwenPaw-Data
将 BI 数据分析结果组织成可视化 HTML 报告。当分析完成、需要生成报告时调用. An agent skill from agentscope-ai/QwenPaw-Data.
Fetch Data
agentscope-ai/QwenPaw-Data
取数 / 查数据 / 拉数据 / 跑 SQL。把自然语言取数需求转为 SQL，经数据湖仓执行后返回查询结果供下游分析。任何需要业务数据的任务在工作区缺少对应文件时都必须先调用此技能——覆盖 BI 业务分析、留存 / 转化 / 同期群分析、数据探索 EDA、统计建模、定量计算、元数据查询、数据查询。命中任一即触发：(1) 直接索要指标或记录，如「DAU 多少」「上月销售额」「3…
Bi Adaptive Threshold
agentscope-ai/QwenPaw-Data
通过量化历史数据的自然波动幅度，自适应计算判定阈值。当需要从数据本身确定阈值（如波动阈值、影响度阈值等）、而非使用固定值时调用。仅适用于日/周粒度阈值确定。
Bi Anomaly Detection
agentscope-ai/QwenPaw-Data
基于阈值检测时间序列中的显著异常波动点。当需要找出指标异常波动日期、识别数据异动时调用. An agent skill from agentscope-ai/QwenPaw-Data.
Bi Attribution Analysis
agentscope-ai/QwenPaw-Data
计算各维度（组）值对指标变动的贡献度，支持可加型量值指标和加权平均型/率值指标。当需要计算贡献度、解释指标"为什么涨/跌"时调用。
Bi Causal Attribution
agentscope-ai/QwenPaw-Data
从运营周报、活动文档、对话输入或文档工具 API 中提取业务事件，与指标异常时间窗口对齐，生成有证据支撑的因果归因假设并排序。当已知指标存在异常波动、需要从外部文档证据中解释"为什么"时调用。
Questions about Bi Conversion Analysis
What does Bi Conversion Analysis do?
对转化执行完整的分析流程，算清楚用户转不转、转化率多少、有没有变化，含口径定义、取数、转化率计算，及可选的异常分析、维度拆分与对比/归因。触发条件：对话涉及转化率分析、转化表现评估、转化变化归因等任务时触发，如出现「分析对话转化率」「转化率表现如何」「不同群体/地区/时间的转化率对比」「分维度后转化情况」「转化率是否异常」等相似问题时触发。. Bi Conversion Analysis is an agent skill from agentscope-ai/QwenPaw-Data.
How do I install Bi Conversion Analysis in Claude Code?
Run `npx skills add agentscope-ai/QwenPaw-Data --skill bi-conversion-analysis -a claude-code`. Or copy the skill folder (packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis in agentscope-ai/QwenPaw-Data) into .claude/skills/bi-conversion-analysis in your project. Claude Code loads it when a task matches its description.
How do I install Bi Conversion Analysis in Codex?
Run `npx skills add agentscope-ai/QwenPaw-Data --skill bi-conversion-analysis -a codex`. Or copy the skill folder (packages/qwenpaw-data-skills/skills/workflows/bi-conversion-analysis in agentscope-ai/QwenPaw-Data) into .agents/skills/bi-conversion-analysis in your project. Codex loads it when a task matches its description.
Can I use Bi Conversion Analysis in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentscope-ai/QwenPaw-Data --skill bi-conversion-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bi-conversion-analysis, .gemini/skills/bi-conversion-analysis, .github/skills/bi-conversion-analysis and .opencode/skills/bi-conversion-analysis in your project.
What does Bi Conversion Analysis need to run?
SKILL.md names no scripts, command-line tools or credentials: Bi Conversion Analysis is instructions for the agent only.
Does Bi Conversion Analysis access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Bi Conversion Analysis safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Bi Conversion Analysis use?
Bi Conversion Analysis is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Bi Conversion Analysis use?
About 971 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Bi Conversion Analysis?
Skills that share tags, products or a category with Bi Conversion Analysis: Modeling Conversion Metrics (PostHog/posthog, 40k stars), Cost Conversation (ruvnet/ruflo, 74k stars), Conversation Memory (davila7/claude-code-templates, 32k stars) and Conversation Archive (garrytan/gbrain, 31k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Bi Conversion Analysis?
agentscope-ai (a GitHub organization) maintains it in agentscope-ai/QwenPaw-Data, which has 113 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 5, 2026.
Source: agentscope-ai/QwenPaw-Data on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.