メニュー
Structured root cause analysis for incidents and problems
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/a5c-ai/babysitter --skill rca-analysisコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
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/.
SOC 職業分類に基づく
| name | rca-analysis |
| description | Structured root cause analysis for incidents and problems |
| allowed-tools | ["Read","Write","Glob","Grep","Bash"] |
| metadata | {"specialization":"customer-experience","domain":"business","category":"Service Management","id":"SK-015"} |
| graph | {"domains":["domain:customer-experience"],"skillAreas":["skill-area:customer-success","skill-area:business-analysis","skill-area:statistical-analysis"],"workflows":["workflow:customer-journey-optimization","workflow:user-feedback-loop"],"roles":["role:customer-success-manager","role:operations-analyst","role:business-analyst"]} |
The Root Cause Analysis (RCA) skill provides structured methodologies and tools for conducting thorough root cause investigations for incidents and problems. This skill supports multiple analysis frameworks including 5-Whys, Fishbone/Ishikawa diagrams, and Fault Tree Analysis to identify underlying causes and drive permanent corrective actions.
skill: rca-analysis
action: five-whys
parameters:
incident_id: "INC-2025-001"
problem_statement: "Customer dashboard failed to load for 2 hours"
analysis:
why_1:
question: "Why did the dashboard fail to load?"
answer: "The API gateway returned 503 errors"
why_2:
question: "Why did the API gateway return 503?"
answer: "Backend services were unresponsive"
why_3:
question: "Why were backend services unresponsive?"
answer: "Database connection pool was exhausted"
why_4:
question: "Why was the connection pool exhausted?"
answer: "A slow query was holding connections for extended periods"
why_5:
question: "Why was there a slow query?"
answer: "Missing database index on newly added column"
root_cause: "Missing database index caused slow queries that exhausted connection pool"
skill: rca-analysis
action: fishbone-diagram
parameters:
problem: "High customer churn rate in Q4"
categories:
people:
- "Insufficient CSM staffing"
- "High CSM turnover"
- "Lack of proactive outreach training"
process:
- "No early warning system"
- "Delayed QBR scheduling"
- "Reactive-only engagement model"
technology:
- "Health score not capturing usage decline"
- "CRM data quality issues"
- "No automated alerting"
measurement:
- "Churn identified too late"
- "NPS not correlated to churn"
environment:
- "Economic downturn pressure"
- "Competitor aggressive pricing"
output_format: mermaid
skill: rca-analysis
action: fault-tree
parameters:
top_event: "Complete service outage"
tree:
gate: OR
events:
- name: "Infrastructure failure"
gate: AND
events:
- name: "Primary DC failure"
probability: 0.001
- name: "DR failover failure"
probability: 0.01
- name: "Application failure"
gate: OR
events:
- name: "Code deployment error"
probability: 0.02
- name: "Configuration error"
probability: 0.015
calculate:
- top_event_probability
- minimal_cut_sets
- critical_events
skill: rca-analysis
action: generate-report
parameters:
incident_id: "INC-2025-001"
report_type: comprehensive
include:
- executive_summary
- incident_timeline
- impact_assessment
- analysis_methodology
- root_causes
- contributing_factors
- corrective_actions
- lessons_learned
format: markdown
skill: rca-analysis
action: track-actions
parameters:
rca_id: "RCA-2025-001"
actions:
- id: "CA-001"
description: "Add missing database index"
owner: "database-team"
due_date: "2025-01-20"
status: completed
verification: "Query performance improved from 30s to 50ms"
- id: "CA-002"
description: "Implement connection pool monitoring"
owner: "sre-team"
due_date: "2025-01-25"
status: in_progress
This skill integrates with the following customer experience processes:
| Process | Integration Points |
|---|---|
| problem-management.js | Core RCA methodology, known error documentation, permanent fixes |
| itil-incident-management.js | Post-incident review, PIR documentation, preventive actions |
| closed-loop-feedback.js | Customer complaint root causes, systemic issue identification |
This skill is a strong candidate for extraction to a shared library with applicability to: