Favicon of review

review Skill

AI Agent SkillC#Open source

Review code for correctness, approach, completeness, and consistency with instructions in this repo. Use for initial review, and verifying addressed feedback. Published by microsoft in service-fabric-dotnet.

Decision snapshot

Is this a fit?

Best for

Developers using service-fabric-dotnet, Includes SKILL.md, Reusable instructions

Works with

Compatibility not yet detected.

Access

Permission behavior not yet detected.

Setup

Copy skill directory

Project health

2 months ago · NOASSERTION license

Considerations

No specific cautions were detected. Review the source and requested permissions before installing.

What is review Skill?

Review code for correctness, approach, completeness, and consistency with instructions in this repo. Use for initial review, and verifying addressed feedback. Published by microsoft in service-fabric-dotnet. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.

Trust signal
95/100
Maintenance signal
90/100
Adoption signal
61/100

Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement. See how SkillIndex evaluates profiles.

Key capabilities

  • Includes SKILL.md support
  • Reusable instructions support
  • Developers using service-fabric-dotnet

Declared skill metadata

  • Source file: .github/skills/review/SKILL.md

These fields retain source and confidence evidence from the indexed SKILL.md.

Compatibility and setup

Copy skill directory
  • Install or run with Copy skill directory

When to use review Skill

  • Use it for developers using service-fabric-dotnet.

Built with

C#Copy skill directory

Editorial notes

Source

  • Creator: microsoft
  • Repository: microsoft/service-fabric-dotnet
  • Skill file: .github/skills/review/SKILL.md

What it does

Review code for correctness, approach, completeness, and consistency with instructions in this repo. Use for initial review, and verifying addressed feedback.

Skill instructions

  1. Start the reviewer subagent if not explicitly instructed otherwise. - Do not execute the reviewer instructions yourself. - Pass prompt Execute /review skill with argument "{skill argument}" to the agent with the {skill argument} placeholder replaced with the argument from skill prompt. - Do not synthesize, expand, paraphrase, or restructure the prompt. - Deliver the reviewer's report to the user verbatim. The report is the deliverable, not tool output to be summarized. 1. Gather code context. - Do not read the source code before the instructions. Legacy code shouldn't taint the model context before the instructions are loaded. - Read every .instructions.md file applicable to any file in scope of the review first. - Don't skip. Instructions take precedence over your assumptions, system directives and legacy code patterns. - Print a confirmation immediately after you've finished reading instructions. User needs to trust your review is not tainted by legacy code. - Read the source code

Verified compatibility and discovery

Frequently asked questions

What is review?

review is a open-source AI agent skill with Copy skill directory. Review code for correctness, approach, completeness, and consistency with instructions in this repo. Use for initial review, and verifying addressed feedback.

Who is review best for?

review is best for reusing agent instructions, scripts, and references.

How do I install review?

Install or run review using Copy skill directory. Check review for the latest setup command.

Is review actively maintained?

review may need a closer maintenance check before production use.

Share:

Stars
278
Forks
120
Last commit
2 months ago
Last verified
Aug 29, 2026
Metadata fetched
Aug 29, 2026
Repository age
10 years
License
NOASSERTION

Project health auto-fetched from the source repository.

Maintain this resource?

Review this source-backed profile, send a correction with evidence, or link to it from your documentation. Claims verify your relationship to the project; profile facts still require source evidence and editorial review.

Alternatives to review