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 master-data-quality-manager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。
正在显示 SKILL.md
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/.
基于 SOC 职业分类
| name | master-data-quality-manager |
| description | Supply chain master data quality monitoring and improvement skill |
| allowed-tools | ["Read","Write","Glob","Grep","Bash"] |
| metadata | {"specialization":"supply-chain","domain":"business","category":"cross-functional","priority":"future"} |
| graph | {"domains":["domain:supply-chain"],"specializations":["specialization:supply-chain-optimization"],"skillAreas":["skill-area:procurement-management","skill-area:data-quality","skill-area:data-governance"],"workflows":["workflow:vendor-onboarding","workflow:vendor-evaluation"],"roles":["role:supply-chain-analyst","role:procurement-manager","role:information-architect"]} |
The Master Data Quality Manager provides supply chain master data quality monitoring, validation, and improvement capabilities. It ensures data accuracy across item, supplier, location, and BOM master data to support reliable supply chain operations and analytics.
data_quality_request:
data_domains:
item_master: boolean
supplier_master: boolean
location_master: boolean
bom_master: boolean
lead_time: boolean
validation_rules:
completeness_rules: array
accuracy_rules: array
consistency_rules: array
timeliness_rules: array
data_sources:
erp_system: string
extract_files: array
quality_thresholds:
critical_fields: object
acceptable_error_rate: float
data_quality_output:
quality_scorecard:
overall_score: float
by_domain: object
item_master:
completeness: float
accuracy: float
consistency: float
timeliness: float
supplier_master:
completeness: float
accuracy: float
consistency: float
timeliness: float
location_master:
completeness: float
accuracy: float
bom_master:
completeness: float
accuracy: float
lead_time:
accuracy: float
issues_identified:
critical: array
high: array
medium: array
low: array
duplicate_analysis:
potential_duplicates: array
merge_recommendations: array
completeness_report:
missing_fields: array
missing_by_domain: object
data_cleansing_actions:
recommended_fixes: array
automated_corrections: array
manual_review_required: array
trend_analysis:
quality_over_time: object
improvement_areas: array
degradation_alerts: array
Input: Master data extracts, validation rules
Process: Validate against quality rules
Output: Data quality scorecard with issues
Input: Supplier or item master data
Process: Identify potential duplicates
Output: Duplicate report with merge recommendations
Input: Lead time master, historical receipt data
Process: Compare stated vs. actual lead times
Output: Lead time accuracy report