用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/a5c-ai/babysitter --skill customer-data-platform命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Reference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)
Atlas turns your STATED NEED into a real systems atlas by SCANNING your actual sources (Azure via `az`, git repos, local dirs) and process/data mining them, THEN enriching against the Atlas knowledge graph. Use this skill when asked to inventory/map your real systems, scan your cloud + repos + directories, mine the real processes or data they contain, or collect their real constraints/gotchas. (atlas, scan my systems, inventory our azure account, map my repos, real systems atlas, process mining, data mining, collect nuances, system discovery)
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.
正在显示 SKILL.md
基于 SOC 职业分类
| name | customer-data-platform |
| description | CDP operations for unified customer data management and audience activation |
| allowed-tools | ["Read","Write","Glob","Grep","Bash","WebFetch"] |
| metadata | {"specialization":"marketing","domain":"business","category":"Marketing Analytics","skill-id":"SK-015"} |
| graph | {"domains":["domain:marketing"],"skillAreas":["skill-area:brand-strategy","skill-area:brand-positioning","skill-area:content-marketing"],"workflows":["workflow:brand-campaign-launch"],"roles":["role:marketing-manager","role:marketing-strategist","role:brand-manager"]} |
The Customer Data Platform Skill enables comprehensive CDP operations for unified customer data management, audience segmentation, and activation across marketing channels. This skill provides integration with major CDP platforms including Segment, mParticle, and Adobe Real-Time CDP, supporting identity resolution, event tracking, and privacy-compliant data orchestration.
This skill integrates with the following marketing processes:
skill: customer-data-platform
action: configure-event-tracking
parameters:
platform: segment
tracking_plan:
name: "Marketing Events"
events:
- name: Page Viewed
properties:
page_name: string
page_category: string
referrer: string
- name: Product Viewed
properties:
product_id: string
product_name: string
category: string
price: number
- name: Campaign Clicked
properties:
campaign_id: string
campaign_name: string
channel: string
creative_id: string
skill: customer-data-platform
action: create-audience
parameters:
platform: segment
audience_name: "High Value Prospects"
definition:
conditions:
- type: event
event: Product Viewed
count: ">= 3"
timeframe: last_30_days
- type: trait
property: customer_ltv
operator: ">="
value: 500
- type: event
event: Order Completed
count: "= 0"
logic: AND
destinations:
- facebook-ads
- google-ads
- braze
skill: customer-data-platform
action: configure-identity
parameters:
platform: mparticle
identity_strategy:
priority_order:
- customer_id
- email
- phone
- device_id
matching_rules:
- type: deterministic
identifiers: [customer_id, email]
- type: probabilistic
confidence_threshold: 0.85
identifiers: [device_id, ip_address]
merge_policy: most_recent
skill: customer-data-platform
action: activate-audience
parameters:
platform: adobe-rtcdp
audience_id: "high-intent-shoppers"
destinations:
- destination: google-ads
mapping:
user_id: customer_id
hashed_email: email_sha256
schedule: real-time
- destination: facebook-ads
mapping:
extern_id: customer_id
email: email_hash
schedule: daily
skill: customer-data-platform
action: configure-privacy
parameters:
platform: segment
consent_categories:
- name: marketing
description: "Marketing and advertising"
default: opt-out
- name: analytics
description: "Analytics and measurement"
default: opt-in
- name: functional
description: "Required for site functionality"
default: required
regulations:
gdpr:
enabled: true
data_subject_request_automation: true
ccpa:
enabled: true
do_not_sell_signal: true