You MUST use this before creative implementation work. Use Codex (gpt-5.4) during brainstorming/research, then hand off approved plans for Codex (gpt-5.3-codex) execution.
From superpower-routernpx claudepluginhub charliechan53/superpower-router --plugin superpower-routerThis skill uses the workspace's default tool permissions.
Guides 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.
Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.
<HARD-GATE> Do NOT invoke any implementation skill, write any code, scaffold any project, or take any implementation action until you have presented a design and the user has approved it. This applies to EVERY project regardless of perceived simplicity. </HARD-GATE>Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.
You MUST create a task for each of these items and complete them in order:
docs/plans/YYYY-MM-DD-<topic>-design.md and commitsuperpower-router:plan-and-execute to create/execute a routed implementation plan (Codex gpt-5.4 for analysis/research, Codex gpt-5.3-codex for implementation)digraph brainstorming {
"Explore project context" [shape=box];
"Ask clarifying questions" [shape=box];
"Propose 2-3 approaches" [shape=box];
"Present design sections" [shape=box];
"User approves design?" [shape=diamond];
"Write design doc" [shape=box];
"Invoke superpower-router:plan-and-execute" [shape=doublecircle];
"Explore project context" -> "Ask clarifying questions";
"Ask clarifying questions" -> "Propose 2-3 approaches";
"Propose 2-3 approaches" -> "Present design sections";
"Present design sections" -> "User approves design?";
"User approves design?" -> "Present design sections" [label="no, revise"];
"User approves design?" -> "Write design doc" [label="yes"];
"Write design doc" -> "Invoke superpower-router:plan-and-execute";
}
The terminal state is invoking superpower-router:plan-and-execute. Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is superpower-router:plan-and-execute, and brainstorming should use Codex (gpt-5.4) for analysis/research before Codex (gpt-5.3-codex) implementation work begins.
Understanding the idea:
Exploring approaches:
Presenting the design:
Documentation:
docs/plans/YYYY-MM-DD-<topic>-design.mdImplementation:
superpower-router:plan-and-execute immediately after user approvalsuperpower-router:plan-and-execute is the next step.