javakishore-veleti/chiefarchitect-agentic-workbench-for-developers/diagnose-azure

Claude Code and agent skill by javakishore-veleti/chiefarchitect-agentic-workbench-for-developers

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Diagnose Azure application and platform issues across dynamically resolved tenants, subscriptions, environments, applications, AKS, ACR, Key Vault, Redis, Cosmos DB, Entra, and Application Insights.

Install

npx vskill@latest install javakishore-veleti/chiefarchitect-agentic-workbench-for-developers/diagnose-azure

SKILL.md

The same SKILL.md was published earlier as javakishore-veleti/chiefarchitect-agentic-workbench-for-developers/diagnose-azure.

Diagnose Azure

Resolve scope before querying Azure. Require an environment and either a configured application/resource or an unambiguous resource ID. Load azure/shared/config/azure-config.example.json, or the path in AZURE_DIAGNOSTICS_CONFIG; apply an optional external override from --override-uri or AZURE_DIAGNOSTICS_CONFIG_OVERRIDE_URI. Run azure/shared/config/resolve-context.mjs; never infer a tenant, subscription, or production target.

Classify the symptom with scripts/classify-azure-issue.mjs. Read only the route selected from patterns/index.json; a route may point to an existing leaf skill. Load patterns/cross-service.md only when evidence spans services.

Start with Azure Resource Graph or narrowly scoped metadata. Add Azure CLI, Kubernetes, KQL, control-plane events, and application telemetry only as needed. Record inaccessible scopes rather than treating them as empty. Correlate evidence by immutable resource ID, environment, deployment/image identity, correlation ID, and UTC time.

Default to read-only diagnostics. Validate proposed commands with scripts/validate-diagnostic-plan.mjs. Never retrieve secret values, tokens, patient data, unrestricted logs, or full configuration payloads. Redact output with scripts/redact-evidence.mjs. Any mutation requires separate explicit authorization for exact targets; this skill does not grant it.

Return the finding, resolved scope, observations, inference, confidence, gaps, and next safe probe.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/javakishore-veleti/chiefarchitect-agentic-workbench-for-developers/diagnose-azure/badge)](https://verified-skill.com/skills/javakishore-veleti/chiefarchitect-agentic-workbench-for-developers/diagnose-azure)

Something wrong with this skill or its page? Tell us.