advisor-collaboration_skill

This skill provides independent architecture reviews and code feedback from an advisor-level expert to sharpen designs and quality.
  • Python

0

GitHub Stars

3

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill lynricsy/oh-my-claudecode --skill advisor-collaboration

  • advisor-guide.md2.5 KB
  • frontend-guide.md2.4 KB
  • SKILL.md1.9 KB

Overview

This skill provides an on-demand Advisor for high-level technical consultation, architecture design, independent review, and prototype implementation. It acts as a senior expert offering alternative perspectives and second opinions to improve design quality and reduce risk. Use it when you need a critical, expert evaluation separate from regular development agents.

How this skill works

The Advisor inspects architecture proposals, performs code reviews, recommends technology choices, and can produce prototype code for validation. It accepts session context to preserve conversation history and can be invoked directly by user request or by other agents seeking a second opinion. Frontend/UI tasks are routed to a dedicated frontend agent; this skill focuses on backend, architecture, and review responsibilities.

When to use it

  • When the user explicitly requests an Advisor-level expert
  • When you need an independent second opinion on architecture or design
  • During technology selection and trade-off analysis
  • For detailed code review and actionable remediation steps
  • When a prototype is needed to validate a design choice

Best practices

  • Provide clear scope and acceptance criteria before requesting review
  • Attach architecture diagrams, sample code, and telemetry where available
  • Preserve SESSION_ID to maintain context across follow-ups
  • Keep frontend/UI requests separate and route them to the frontend agent
  • Ask for concrete remediation steps and test suggestions with each review

Example use cases

  • Evaluate microservice boundaries and data partitioning strategies
  • Perform a security and maintainability code review for a critical module
  • Compare database and caching options and recommend trade-offs
  • Produce a minimal prototype to validate a performance-sensitive design
  • Review CI/CD and observability plans and suggest hardening steps

FAQ

Yes — the Advisor can produce prototype or sample code to validate designs, but productionization should follow team standards and further review.

How is Advisor different from other agents?

Advisor focuses on high-level architecture, independent reviews, and expert second opinions. It is not the dedicated frontend/UI agent, which should be used for UI work.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational