Install
$ agentstack add skill-azure-azure-functions-skills-azure-functions-diagnostics ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Azure Functions Diagnostics
Use this skill to diagnose and resolve Azure Functions issues by orchestrating focused skills and loading only the references needed for the current app.
Write final answers in the user's language.
Core principle
Do not load all diagnostic references up front. First collect the app inventory, infer runtime/language and trigger/binding/extension shape, then load only the matching language and extension reference files.
For multi-step reviews, source investigations, or remediation work, create a short checklist plan file or todo list and update it after each completed step. Do not require a checklist for quick read-only diagnosis because it adds token overhead.
Required inputs
Ask only for missing inputs needed to start:
- Function App name, unless already provided.
- Subscription ID/name and resource group, if needed to disambiguate.
- Symptom, error message, command output, or portal/deployment failure context.
- Time window, default
24hfor current or recent production issues.
If the user has a local workspace issue without a deployed app, skip Azure resource collection and start from local project/runtime/trigger discovery.
Diagnostic workflow
Follow [workflow.md](references/workflow.md). Use shared reference routing from [../azure-functions-common/references/routing.md](../azure-functions-common/references/routing.md) only after inventory/health data identifies the relevant runtime, trigger, binding, or symptom.
Fast path:
- Use
azure-functions-inventoryto collect static app specifications. - Use
azure-functions-health-statusto collect current health, metrics, telemetry, and Activity Log. - Use [../azure-functions-common/references/routing.md](../azure-functions-common/references/routing.md) to select only the required language and extension references.
- Use [evidence-checklist.md](references/evidence-checklist.md) before stating root cause or recommended fixes.
- Prefer official documentation, official repositories, official samples, and package/container registries before broader web sources.
Reference loading rules
Use azure-functions-common for shared runtime, language, and trigger/binding references.
- Load exactly one language reference when the runtime is known, plus Durable only when Durable is involved.
- Load only extension references matching the app's triggers/bindings or the symptom.
- Load Extension Bundles only for non-.NET apps or extension-version/binding-resolution symptoms.
- Do not load migration provenance during normal diagnostics.
Guardrails
- Redact secrets, connection strings, keys, tokens, SAS URLs, and storage credentials.
- Report setting names and whether values exist; do not reveal values.
- Ask before cloning large repositories, using sparse checkout, deploying to Azure, restarting apps, changing configuration, or running disruptive commands.
- Distinguish confirmed evidence from hypotheses.
- For transient issues, state whether the current app is healthy and identify the historical evidence used.
Next steps
- On success, suggest
azure-functions-inventoryif the app shape or configuration changed during remediation. - On failure, suggest
azure-functions-health-statusto re-check current health and telemetry before continuing diagnosis.
Output shape
Use this concise structure unless the user asks for a different format:
Target:
Symptom:
Inventory:
Health:
Relevant references loaded: ,
Findings:
Likely cause:
Recommended actions:
Validation plan:
Gaps:
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Azure
- Source: Azure/azure-functions-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.