lz-advisor

Use this agent when a skill needs strategic advisor consultation from a stronger model. Requires structured context packaging from the executor; not intended for direct invocation. <example> Context: A planning skill completed orientation and needs strategic direction user: "Plan the implementation for the authentication refactor" assistant: "I've gathered the codebase context. Let me consult the advisor for strategic direction." <commentary> The plan skill has completed orientation. Before creating the plan, consult lz-advisor for Opus-level strategic guidance on approach. </commentary> assistant: "I'll use the lz-advisor agent for a strategic assessment." </example> <example> Context: An implementation skill is stuck on a recurring error user: "Implement the caching layer" assistant: "I've tried two approaches and both have issues. Let me consult the advisor." <commentary> Executor is stuck. This is a key advisor timing moment per Anthropic's guidance. </commentary> assistant: "I'll use the lz-advisor agent to get guidance on the caching approach." </example> <example> Context: Executor finished implementation and needs final verification user: "Build the database migration system" assistant: "Implementation is complete and committed. Let me get a final advisor review." <commentary> Executor has made deliverable durable. Final advisor consultation before declaring done. </commentary> assistant: "I'll use the lz-advisor agent for a final check." </example>

Use this agent when a skill needs code quality review analysis from a stronger model. Requires structured findings packaging from the executor; not intended for direct invocation. <example> Context: The review skill completed scanning a module and found potential issues user: "Review the authentication module for quality issues" assistant: "I've scanned the auth module and identified several concerns. Let me consult the reviewer for deep analysis." <commentary> The review skill has completed its scan phase. It packages the top findings with code context for the reviewer to validate and analyze. </commentary> assistant: "I'll use the lz-advisor reviewer agent for code quality analysis." </example> <example> Context: The review skill scanned recent git changes and curated findings user: "Check my recent changes for issues" assistant: "I've reviewed the recent commits and found areas that need attention. Let me get deeper analysis." <commentary> The review skill scanned git diff output and identified findings. It packages the most significant ones for reviewer analysis. </commentary> assistant: "I'll use the lz-advisor reviewer agent to validate these findings." </example> <example> Context: The review skill scanned a specific utility module for quality issues user: "Review src/utils/parser.ts for bugs and edge cases" assistant: "I've analyzed the parser module and found several edge cases. Let me get deeper analysis." <commentary> The review skill targeted a specific file. It packages the most significant findings from that file for the reviewer to validate. </commentary> assistant: "I'll use the lz-advisor reviewer agent to analyze these findings." </example>

Use this agent when a skill needs security-focused review analysis from a stronger model. Requires structured security findings packaging from the executor; not intended for direct invocation. <example> Context: The security review skill scanned an API module for vulnerabilities user: "Run a security review on the API routes" assistant: "I've scanned the API routes for security concerns and identified potential vulnerabilities. Let me consult the security reviewer for threat analysis." <commentary> The security review skill completed its scan phase with a security lens. It packages the top findings with attack surface context for the security reviewer to validate with OWASP methodology. </commentary> assistant: "I'll use the lz-advisor security-reviewer agent for threat analysis." </example> <example> Context: The security review skill scanned authentication code user: "Check the auth module for security issues" assistant: "I've reviewed the authentication flow and found areas of concern. Let me get a deeper security analysis." <commentary> The security review skill identified potential auth vulnerabilities. It packages findings with code context for OWASP-informed analysis. </commentary> assistant: "I'll use the lz-advisor security-reviewer agent to assess these findings." </example> <example> Context: The security review skill scanned project dependencies for known vulnerabilities user: "Check our dependencies for security issues" assistant: "I've reviewed the dependency tree and identified outdated packages with known CVEs. Let me get a security assessment." <commentary> The security review skill scanned package manifests and lock files. It packages findings about vulnerable dependencies for OWASP-informed analysis. </commentary> assistant: "I'll use the lz-advisor security-reviewer agent for vulnerability assessment." </example>

This skill should be used when the user wants to implement, build, or execute a coding task with strategic advisor guidance. Trigger phrases include "implement this task", "execute this plan", "build this feature", "code this up", "lz-advisor.execute", "start building", "implement with guidance", "build this with advisor help", "execute the plan", and "code this feature". This skill pairs Sonnet execution with Opus strategic consultation for near-Opus intelligence at Sonnet cost. It follows a six-phase workflow: orient, consult, execute, make durable, final review, and complete. Optionally accepts a plan file from lz-advisor.plan via @ file mention. This skill should NOT be used when the user wants to plan before coding, review completed code, or run security audits -- those are handled by sibling skills lz-advisor.plan, lz-advisor.review, and lz-advisor.security-review respectively.

This skill should be used when the user wants to plan a coding task before starting implementation. Trigger phrases include "plan a task", "create an implementation plan", "think through the approach", "plan before coding", "lz-advisor.plan", "help me think through", "what's the best approach for", "before I start coding", "plan out the architecture", and "how should I approach this". This skill provides Opus-level strategic direction at Sonnet cost by consulting the advisor agent for high-leverage planning guidance. It produces a written plan file the user can review and later pass to lz-advisor.execute. This skill should NOT be used when the user wants to implement, build, review code, fix bugs, or run security audits -- those are handled by sibling skills lz-advisor.execute, lz-advisor.review, and lz-advisor.security-review respectively.

This skill should be used when the user wants a code quality review of completed work, looking for bugs, logic errors, and edge cases. Trigger phrases include "review this code", "check my changes", "review these files", "look for issues", "lz-advisor.review", "check this module for bugs", "look over my code", "find bugs in", "review my recent commits", and "check for correctness". This skill provides Opus-level code quality review at Sonnet cost by consulting the reviewer agent for deep analysis of correctness, edge cases, and maintainability. Findings are classified as Critical, Important, or Suggestion. This skill should NOT be used for security-focused reviews, vulnerability audits, or threat modeling -- use lz-advisor.security-review instead. It should also NOT be used for planning or implementing tasks -- use lz-advisor.plan or lz-advisor.execute instead.

This skill should be used when the user wants a security-focused review of code, looking for vulnerabilities, attack surfaces, and threat patterns. Trigger phrases include "security review this code", "check for vulnerabilities", "audit security", "lz-advisor.security-review", "check for security issues", "threat model this code", "review for injection risks", "find vulnerabilities in", "security scan", "check for SQL injection", and "audit for security". This skill provides Opus-level security review at Sonnet cost by consulting the security-reviewer agent for OWASP Top 10-informed threat analysis. Findings are classified as Critical, High, or Medium with OWASP category tags. This skill should NOT be used for general code quality reviews, bug finding, or style issues -- use lz-advisor.review instead. It should also NOT be used for planning or implementing tasks -- use lz-advisor.plan or lz-advisor.execute instead.