Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

K8sGPT Analyzer — AI-Powered Kubernetes Intelligence · lloydchang | DecimalAI

devopsby lloydchang

K8sGPT Analyzer — AI-Powered Kubernetes Intelligence

lloydchang/k8sgpt-analyzer

Source lloydchang/agentic-reconciliation-engine ↗License AGPL-3.0

Provides AI-powered Kubernetes cluster analysis and troubleshooting using K8sGPT with Qwen LLM.

SkillScore91Maintained

Automatic

DevOps & SRE pack

Last verified 8/4/2026

What it changes

Passed 20 of 22 test cases with the skill, and 7 of 22 without it.

Without skill32%

With skill91%

Checks it passed that the model alone missed

Specifies qwen as the LLM backend
Sets the scope parameter to cluster
Specifies model qwen2.5-7b-instruct

and 19 more in the full report

14 fixed6 passed either way1 still failing1 broke

Pass-rate lift: +59 pp
Tokens: +164%
Agent turns: 0%
Response time: -53%

Model gemini-3.6-flashMeasured 8/4/2026v120 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/lloydchang-k8sgpt-analyzer/SKILL.md https://app.decimal.ai/s/lloydchang-k8sgpt-analyzer/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add lloydchang-k8sgpt-analyzer, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/lloydchang-k8sgpt-analyzer/ and pins it in .decimal/skills.lock

decimalai skills add lloydchang-k8sgpt-analyzer

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/lloydchang-k8sgpt-analyzer/SKILL.md https://app.decimal.ai/s/lloydchang-k8sgpt-analyzer/SKILL.md

Raw file: /s/lloydchang-k8sgpt-analyzer/SKILL.md ↗ · machine-readable summary at /s/lloydchang-k8sgpt-analyzer.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 14

Prompt

If an analysis request specifies targetResource as 'pod' but omits the scope parameter, what scope value does the analyzer default to?

What was checked, without and with the skill
Checked	Without skill	With skill
Defaults the scope parameter to cluster	Missed	Passed

case-14 · gemini-3.6-flash · 8/4/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md382 lines4 filesincludes scripts

K8sGPT Analyzer — AI-Powered Kubernetes Intelligence

Purpose

Enterprise-grade AI-powered Kubernetes cluster analysis and troubleshooting solution that leverages K8sGPT with Qwen LLM to provide intelligent insights, automated problem detection, and contextual recommendations across multi-cloud Kubernetes environments.

When to Use

Cluster analysis and automated problem detection
Intelligent troubleshooting with AI-powered insights
Resource optimization and configuration recommendations
Multi-cluster monitoring and health assessments
Incident response and root cause analysis
Capacity planning and performance optimization

Inputs

operation: Operation type - analyze|diagnose|optimize|monitor|report (required)
targetResource: Target resource identifier - namespace|deployment|pod|service|cluster (required)
scope: Analysis scope - cluster|namespace|resource|all (optional, default: cluster)
backend: LLM backend - qwen|openai|localai|ollama (optional, default: qwen)
explain: Enable AI explanations (optional, default: true)
output: Output format - json|yaml|table|summary (optional, default: json)
filters: Resource filters and constraints (optional)
environment: Target environment (optional, default: production)

Process

Environment Validation: Verify Kubernetes connectivity and permissions
K8sGPT Configuration: Setup Qwen LLM backend and authentication
Resource Discovery: Identify target resources based on scope and filters
AI Analysis: Execute K8sGPT analysis with specified parameters
Intelligence Processing: Process AI insights and recommendations
Context Enrichment: Add operational context and historical data
Report Generation: Create comprehensive analysis reports
Action Planning: Generate actionable recommendations

Outputs

AI Analysis Results: Detailed findings from K8sGPT analysis
Problem Detection: Identified issues and their severity levels
Recommendations: Actionable improvement suggestions
Resource Insights: Performance and configuration analysis
Risk Assessment: Security and compliance evaluation
Optimization Opportunities: Cost and performance improvements

Track record

Benchmark

20 / 22

test cases passed, vs 7 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

lloydchang / agentic-reconciliation-engine

core/ai/skills/k8sgpt-analyzer/SKILL.md

View on GitHub ↗

License AGPLv3Imported 8/1/2026Version v1Bundled 3 files · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

K8sGPT Analyzer — AI-Powered Kubernetes Intelligence

Purpose

When to Use

Inputs

Process

Outputs

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills