$ loading_
Review skill PRs with severity-rated feedback on quality and repository conventions.
The material indicates a prompt-only/document-style review skill with no required secrets, no declared remote endpoints, and no stated local execution or data exfiltration capability, so the overall risk is low. The main caveat is reduced supply-chain transparency due to an undeclared license and unknown maintenance status.
The material explicitly states there are no required keys or environment variables; no API tokens, account credentials, or other sensitive authentication data are requested, so credential exposure and misuse risk is low.
No remote endpoint host is declared, and the README does not describe sending content to external services, calling APIs, or syncing PR data; based on the material, there is no clear data-egress path.
The system flags it as prompt-only, and the documentation only describes a review workflow and checklist references; there is no indication of spawning local processes, running scripts, invoking a shell, or using other system capabilities.
The description only involves reviewing skill PR changes and related file categories, with no stated ability to read/write arbitrary local files, access resources outside the repo, or persist data; the material suggests limited data access with no sign of overbroad authorization.
The source is an open-source GitHub repository with some community adoption (222 stars), which materially lowers risk; however, the license is undeclared and maintenance status is unknown, so repository activity and dependencies should still be verified before adoption.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "skill-reviewer" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/GitHub-Copilot-for-Azure/main/.github/skills/skill-reviewer/SKILL.md 2. Save it as ~/.claude/skills/skill-reviewer/SKILL.md 3. Reload skills and tell me it's ready
Please review this skill PR. Focus on token budgets, routing conflicts, required sections, and repository conventions. Output a severity-rated issue list with suggested fixes.
A structured review with high/medium/low severity issues, explanations, and actionable fix suggestions.
Check whether these skill changes may cause routing conflicts, missing required content, or exceed the recommended token budget, and identify the highest-priority fixes.
A prioritized risk list clearly describing potential issues and their impact.
Based on the current skill PR content, generate review feedback that can be sent directly to the contributor, using a professional tone, clear structure, and severity-based categories.
A PR-ready feedback message with categorized issues, rationale, and recommended revisions.
Performs thorough, structured code reviews of skill PRs — severity-classified findings with actionable fixes, positive acknowledgment, and a summary table.
plugin/skills/ or .github/skills/💡 Note:
.github/skills/meta-skills have different conventions — checklist sections 8-9 apply only toplugin/skills/service skills.
| Error | Remediation |
|---|---|
| Cannot determine changed files | Ask user for the file list or PR number |
| Token counting unavailable | Estimate at ~4 chars per token |
Set up Entra ID app registration, OAuth, permissions, and MSAL integration.
Set up Azure Application Insights telemetry for web apps with best practices.
Troubleshoot Azure Event Hubs and Service Bus SDK connection and messaging issues.
Find, list, and inspect Azure resources across subscriptions and resource groups.
Deploy, evaluate, fine-tune, and optimize Microsoft Foundry agents and models.
Deploy prepared Azure apps with built-in recovery for common release errors.
Iteratively audit and fix skill frontmatter compliance, scoring, and token issues.
Review code deeply across correctness, tests, security, performance, and product quality.
Investigate why a specific skill’s tests failed and surface error details.
Write, review, and standardize Agent Skills to match agentskills.io requirements.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.