From lz-advisor
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.
How this skill is triggered — by the user, by Claude, or both
Slash command
/lz-advisor:lz-advisor.reviewThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
The lz-advisor:reviewer agent is backed by a stronger model (Opus). Invoke it
The lz-advisor:reviewer agent is backed by a stronger model (Opus). Invoke it via the Agent tool at the strategic moment described below. For guidance on timing and context packaging, see:
@${CLAUDE_PLUGIN_ROOT}/references/advisor-timing.md
@${CLAUDE_PLUGIN_ROOT}/references/context-packaging.md
This skill follows a three-phase workflow: scan, consult, then output.
## Phase 1: ScanDetermine the review scope from the user's request:
git diff or git log to identify changed files, then read themRead any CLAUDE.md files in the reviewed directories -- project guidelines inform what counts as an issue.
Scan the code with high-signal criteria. Flag:
/lz-advisor.security-review)Skip (do not flag):
Curate the top 3-5 highest-signal findings with file:line references and relevant code context. Read thoroughly within scope -- do not skim.
Do not consult the reviewer agent during scanning. Scanning is preparation.
## Phase 2: Consult the ReviewerPackage the scan results and invoke the lz-advisor:reviewer agent via the
Agent tool. Package the consultation prompt per the Verification template
in @${CLAUDE_PLUGIN_ROOT}/references/context-packaging.md. The
executor's 3-5 curated findings from Phase 1 become the Findings section
of the template.
One reviewer consultation per review invocation. The reviewer starts with fresh context and cannot see the conversation -- all relevant context goes in the prompt.
## Phase 3: Structure OutputPresent findings to the user as console output.
Start with a summary header:
## Review Summary
Reviewed: [scope description -- files, directories, or change range]
Findings: [N] Critical, [N] Important, [N] Suggestion
Then group findings by severity (Critical / Important / Suggestion):
For each finding:
Include only findings the reviewer validated. Drop findings the reviewer rejected.
Do not include:
If the reviewer identified cross-cutting patterns, weave them into the findings naturally -- for example, note the shared root cause when presenting related findings.
Present the review findings to the user. If no significant issues were found during scanning, report that the reviewed code looks sound and note any minor observations.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub layzeedk/lz-advisor-claude-plugins --plugin lz-advisor