Agent skill

rca

Root cause analysis workflows - systematic investigation of failures

View SKILL.md on GitHub Repository
Stars 163
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/rca

SKILL.md

mermaid
flowchart TD
    FAIL([Failure]) --> RCA{"/rca"}
    RCA -->|CI failure, no cluster| RCACI["rca:ci"]:::rca
    RCA -->|HyperShift available| RCAHS["rca:hypershift"]:::rca
    RCA -->|Kind available| RCAKIND["rca:kind"]:::rca

    RCACI -->|Inconclusive| NEED{"Need cluster?"}
    NEED -->|Yes| RCAHS
    NEED -->|Reproduce locally| RCAKIND

    RCACI --> ROOT[Root Cause Found]
    RCAHS --> ROOT
    RCAKIND --> ROOT
    ROOT --> TDD["tdd:*"]:::tdd

    classDef rca fill:#FF5722,stroke:#333,color:white
    classDef tdd fill:#4CAF50,stroke:#333,color:white

Follow this diagram as the workflow.

RCA Skills

Root cause analysis workflows for systematic failure investigation.

Auto-Select Sub-Skill

When this skill is invoked, determine the right sub-skill based on context:

Step 1: Determine what's available

Check for HyperShift cluster:

bash
ls ~/clusters/hcp/kagenti-hypershift-custom-*/auth/kubeconfig 2>/dev/null

Check for Kind cluster:

bash
kind get clusters 2>/dev/null

Step 2: Route based on failure source and access

Where did the failure occur?
    │
    ├─ CI pipeline (GitHub Actions) ─────────────────────────┐
    │                                                         │
    │   Do you have a live cluster matching the CI env?       │
    │       │                                                 │
    │       ├─ HyperShift cluster available                   │
    │       │   → Use `rca:hypershift` (deep investigation)   │
    │       │                                                 │
    │       ├─ Kind cluster available (for Kind CI failures)  │
    │       │   → Use `rca:kind` (reproduce locally)          │
    │       │                                                 │
    │       └─ No cluster                                     │
    │           → Use `rca:ci` (logs and artifacts only)      │
    │           → If inconclusive, ask user to create cluster │
    │                                                         │
    ├─ Local Kind cluster ──────────────────────────────────┐ │
    │   → Use `rca:kind` (full local access)                │ │
    │                                                       │ │
    └─ HyperShift cluster ─────────────────────────────────┐│ │
        → Use `rca:hypershift` (full remote access)        ││ │
                                                           ││ │
After RCA is complete, switch to TDD for fix iteration: ◄──┘┘ │
    - `tdd:ci` (CI-only)                                       │
    - `tdd:hypershift` (live cluster)                          │
    - `tdd:kind` (local cluster)                               │

Available Skills

Skill Access Auto-approve Best for
rca:ci CI logs/artifacts only N/A CI failures, no cluster
rca:hypershift Full cluster access All read ops Deep investigation
rca:kind Full local access All ops Kind failures, fast repro

Concurrency limit: Only one rca:kind session at a time (one Kind cluster fits locally). Before routing to rca:kind, run kind get clusters — if a cluster exists from another session, route to rca:ci instead or ask the user.

Related Skills

  • tdd:ci - Fix iteration after RCA (CI-driven)
  • tdd:hypershift - Fix iteration with live cluster
  • tdd:kind - Fix iteration on Kind
  • k8s:logs - Query and analyze component logs
  • k8s:pods - Debug pod issues

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

majiayu000/claude-skill-registry

agent-ops-spec

Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-state

Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-spec

Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-testing

Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-testing

Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.

163 31
Explore
majiayu000/claude-skill-registry

agent-ops-state

Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.

163 31
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results