Review a spec, proposal, or design before implementation to catch gaps, risks, and ambiguities. Scans codebase for context before review. Supports iterative review+fix with --fix flag and parallel multi-angle review. Use when you want to validate specs before coding.
From reviewernpx claudepluginhub shdennlin/agent-plugins --plugin reviewerThis skill uses the workspace's default tool permissions.
spec-reviewer.mdGuides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.
Review feature specifications, proposals, designs, or task lists before implementation starts.
Provide the paths to spec files or folders to review:
$spec docs/plans/auth-flow/
$spec proposal.md spec.md tasks.md
With iterative auto-fix:
$spec docs/plans/auth-flow/ --fix
$spec docs/plan/ --fix -n 5 --fix-all
$spec docs/plan/ --fix --parallel "scope,tasks"
Skip codebase exploration:
$spec docs/plan/ --no-explore
If no paths are given, ask which files to review.
--no-explore)--fix)Before either dispatch, the code-explorer agent scans the codebase for relevant context based on spec content. Pass --no-explore to skip this step.
Without --fix: use the companion spec-reviewer.md in this directory as the agent prompt.
With --fix: dispatch reviewer:spec-fix-orchestrator with parameters (paths, max_iterations, parallel, angles, fix_all, codebase_context, review-angles template content).
The agent will cd to the git root automatically. Provide it with: