Is the Analyze Skill Issues skill free?

Yes. The skill itself is free from microsoft/GitHub-Copilot-for-Azure. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Analyze Skill Issues SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 5/5.

How do I install Analyze Skill Issues?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Analyze Skill Issues with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Analyze Skill Issues

Reads Azure blob-stored integration test results to explain why a skill's tests are failing

by microsoft · microsoft/GitHub-Copilot-for-Azure

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · ccccb93

Fetched SKILL.md and its one reference (references/blob-structure.md, HTTP 200) via raw GitHub. Frontmatter parses cleanly with name+description; no security smells (no curl|sh, base64, or secret exfiltration; uses $env:TEMP variable, no hardcoded user paths). Could not run Phase 1-4: the skill depends on the Azure MCP storage server plus an authenticated `az` CLI against the private Microsoft storage account strdashboarddevveobvk, none of which are available to me, so no baseline-vs-skill artifact could be produced. Trigger judgment: 5/5 phrasings decided correctly — "why are azure-storage tests failing", "debug foundry skill failing tests", "what errors caused azure-deploy test failures" load it; "compare the last two test runs" (routes to analyze-test-run per the DO NOT USE clause) and "why is my local Python unit test failing" do not.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 5/5

What Analyze Skill Issues does

Queries a Microsoft-internal Azure Storage account containing integration-test result blobs, downloads the per-skill JSON/JUnit files, and summarizes root cause, per-test pass/fail status, and error messages for a named skill. Triggers when the user asks why a skill's tests are failing or wants to debug/investigate a skill's recent integration-test errors. Requires the Azure MCP storage server and authenticated Azure CLI access to the private storage account.

How to install Analyze Skill Issues

git clone --depth 1 https://github.com/microsoft/GitHub-Copilot-for-Azure.git /tmp/analyze-skill-issues-src
mkdir -p ~/.claude/skills
cp -R /tmp/analyze-skill-issues-src/.github/skills/analyze-skill-issues ~/.claude/skills/analyze-skill-issues
# REQUIRES (skill is non-functional without these):
#  1. Azure MCP storage server exposing mcp_azure_mcp_storage_blob_get / _container_get
#  2. Azure CLI (az) authenticated via `az login` with read access to the
#     private storage account `strdashboarddevveobvk`, container `integration-reports`
#  3. This account is Microsoft-internal infra — external users cannot reach it.
#  Commands in the body are PowerShell (uses $env:TEMP) — assumes a Windows/pwsh shell.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Analyze Skill Issues

/analyze-skill-issues Reads Azure blob-stored integration test results to explain why a skill's tests are failing

It also activates on plain-language prompts like these:

Why is the deploy skill's test failing
Debug the failing tests for this skill
Investigate skill test errors from the last run

Frequently asked questions

Is the Analyze Skill Issues skill free?: Yes. The skill itself is free from microsoft/GitHub-Copilot-for-Azure. SkillProof publishes the install command and an independent test verdict at no cost.
Does Analyze Skill Issues work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Works with setup. Fetched SKILL.md and its one reference (references/blob-structure.md, HTTP 200) via raw GitHub. Frontmatter parses cleanly with name+description; no security smells (no curl|sh, base64, or secret exfiltration; uses $env:TEMP variable, no hardcoded user paths). Could not run Phase 1-4: the skill depends on the Azure MCP storage server plus an authenticated `az` CLI against the private Microsoft storage account strdashboarddevveobvk, none of which are available to me, so no baseline-vs-skill artifact could be produced. Trigger judgment: 5/5 phrasings decided correctly — "why are azure-storage tests failing", "debug foundry skill failing tests", "what errors caused azure-deploy test failures" load it; "compare the last two test runs" (routes to analyze-test-run per the DO NOT USE clause) and "why is my local Python unit test failing" do not.
What is the Analyze Skill Issues SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 5/5.
How do I install Analyze Skill Issues?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Analyze Skill Issues with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.