ByeongminLee/nextjs-claude-code

ByeongminLee/nextjs-claude-code

Agent Claude Code

Installs NCC plugin into a test project via dev/npx/marketplace method, generates feature specs, runs spec→dev workflow, and executes non-spec-dev feature tests. Logs all results.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Orchestrates NCC plugin E2E tests. Supports quick (Phase 1), full (Phase 1+2), install-test (npx vs marketplace), security, a11y, codequality, and custom modes. Spawns executor+reviewer pairs per project, writes aggregated reports.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Reviews a completed plugin test project. Analyzes spec quality, dev execution, TDD compliance, skill selection, hook effectiveness, token efficiency, and non-spec-dev features. Writes a structured review report.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Analyzes and optimizes token usage across the NCC plugin. Audits file sizes, skill loading costs, agent prompt bloat, MCP overhead, subagent delegation, and context engineering patterns. Always produces a report before making changes.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Bumps NCC version (semver), updates package.json, plugin.json, CHANGELOG.md, READMEs, and web content. For NCC plugin developers only — not for end users. Invoked by the /version-update skill.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Compare two outputs WITHOUT knowing which skill produced them.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Evaluate expectations against an execution transcript and outputs.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Explores feature design through Socratic questioning before spec writing. Asks clarifying questions one at a time, proposes 2-3 approaches with trade-offs, presents design in sections for approval, and produces a spec-ready summary. Invoked by the /brainstorm skill.

ByeongminLee/nextjs-claude-code

Agent Claude Code

AI-driven browser testing agent. Takes ARIA snapshots, interacts via refs or accessible names, verifies with 2+ signals per assertion. Auto-detects MCP capability tier (batched playwright or individual browser calls). Supports spec-driven, basic, visual, and a11y modes.

ByeongminLee/nextjs-claude-code

Agent Claude Code

CDO (Chief Design Officer) reviewer for /create pipeline. Evaluates information architecture, interaction design, visual direction, AI slop detection, and accessibility. Spawned by create-orchestrator as part of the C-suite team.

ByeongminLee/nextjs-claude-code

Agent Claude Code

CEO reviewer for /create pipeline. Evaluates vision alignment, scope, demand validation, resource allocation, and 10-star product thinking. Spawned by create-orchestrator as part of the C-suite team.

ByeongminLee/nextjs-claude-code

Agent Claude Code

CMO reviewer for /create pipeline. Evaluates market positioning, competitive landscape, messaging clarity, and growth potential using marketing psychology principles. Spawned by create-orchestrator as part of the C-suite team.

ByeongminLee/nextjs-claude-code

Agent Claude Code

CPO reviewer for /create pipeline. Evaluates user value, user stories, success metrics, UX complexity, and accessibility. Spawned by create-orchestrator as part of the C-suite team.

ByeongminLee/nextjs-claude-code

Agent Claude Code

CTO reviewer for /create pipeline. Evaluates architecture fit, technical feasibility, tech debt, scalability, and security implications. Spawned by create-orchestrator as part of the C-suite team.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Builds CI/CD pipeline configurations by analyzing the project stack, git branch strategy, and test strategy. Uses find-skills to discover and install platform-specific deployment skills. Generates workflow files and spec/CICD.md documentation.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Reviews code quality across security, React/Next.js patterns, performance, and best practices. Does not modify code. Called as part of the /review skill (paired with reviewer).

ByeongminLee/nextjs-claude-code

Agent Claude Code

Deep code analysis agent for legacy projects. Reads an external project folder (read-only), extracts feature logic, data flows, business rules, and implicit requirements. Outputs a structured ANALYSIS.md. Invoked by reforge-orchestrator during Phase 1.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Analyzes staged and unstaged changes, generates a commit message following the project's commit convention from GITSTRATEGY.md, and commits after user confirmation. Invoked by the /commit skill.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Orchestrates the /create ideation pipeline. 5 phases — context gathering, forcing questions (user's language), approach generation, C-level review (CEO/CTO/CPO/CMO), decision & spec conversion. Writes to spec/create/[name]/. Invoked by the /create skill.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Database implementation engineer. Handles schema, ORM setup, migrations, queries, seed data, and RLS policies. Supports Prisma, Drizzle, Supabase, and raw SQL. Spawned per [db] task as a fresh-context subagent (solo mode) or team member (team mode).

ByeongminLee/nextjs-claude-code

Agent Claude Code

Systematic bug analysis and resolution agent. Uses hypothesis-driven debugging, records process in DEBUG.md, and updates STATE.md. Invoked by the /debug skill.

ByeongminLee/nextjs-claude-code

Agent Claude Code

Detects the project's git branch strategy by analyzing remote branches and user confirmation. Generates spec/GITSTRATEGY.md. Invoked during /init, /commit, or /pr when GITSTRATEGY.md is missing.

ByeongminLee/nextjs-claude-code

Agent Claude Code

One-time codebase analysis agent for Next.js/React projects. Populates PROJECT.md, ARCHITECTURE.md, spec/rules/, and draft feature spec files by reading the existing codebase. Invoked by the /init skill.