cubha

cubha/claude-workflow-plugins

Plugin Claude Code

Plugin marketplace listing 10 plugins: scope, braintrust, analyze, init-design, debugger.

cubha/claude-workflow-plugins

Plugin Claude Code

Brownfield codebase audit: architecture, tech debt, security, and performance, distilled into a comprehensive Markdown report with an improvement roadmap.

cubha/claude-workflow-plugins

Skill Claude CodeCodex

A codebase analysis workflow for existing projects. It explores the code, adds outside research, and produces a Markdown report about architecture, technical debt, security, performance, and possible improvements.

cubha/claude-workflow-plugins

Plugin Claude Code

In-session adversarial review panel: 3-5 independent fork agents re-examine the session's design, plan, or decision through different lenses, then reconcile conflicts into a verdict. A context-inheriting red team.

cubha/claude-workflow-plugins

Skill Claude CodeCodex

An in-session review panel that has several independent agents examine a design, plan, policy, or decision from different critical viewpoints. It reviews the material already discussed in the current conversation and combines the findings.

cubha/claude-workflow-plugins

Plugin Claude Code

Log-driven debugging workflow: insert logs, pinpoint the root cause, fix, verify, and clean up. --pw mode auto-reproduces web UI bugs via a bundled Playwright MCP. Supports JS/TS, Python, Java, and Kotlin.

cubha/claude-workflow-plugins

Skill Claude CodeCodex

A debugging workflow that uses system logs to identify a bug's cause, then applies, verifies, and cleans up the fix. It supports JavaScript, TypeScript, Python, Java, and Kotlin, with optional Playwright browser testing and recordings.

cubha/claude-workflow-plugins

Plugin Claude Code

Deterministic (no-LLM) design anti-pattern linter with 47 detectors for token hygiene, color/font/spacing consistency, and AI-default clichés (beige backgrounds, text gradients, uppercase eyebrows). Same input always yields the same verdict at zero token cost, so it doubles as a CI gate (--gate).

cubha/claude-workflow-plugins

Skill Claude CodeCodex

A repeatable checker for design problems in rendered HTML and CSS, standalone prototype pages, or live URLs. It compares them with a DESIGN-TOKENS.md file, a document defining approved colors, fonts, spacing, and other visual rules, and reports pass or fail results.

cubha/claude-workflow-plugins

Plugin Claude Code

Reverse-extracts a design system from an existing codebase into Ground Truth files (DESIGN-TOKENS.md, UX-BRIEF.md) that downstream UI work can obey.

cubha/claude-workflow-plugins

Skill Claude CodeCodex

A Korean-language procedure for extracting an existing project’s design system into DESIGN-TOKENS.md and UX-BRIEF.md files under docs/design. A design system is the documented set of visual and interface rules used across a product.

cubha/claude-workflow-plugins

Plugin Claude Code

Pre-project decision gate: MoSCoW feature scoping, effort sizing, and tech-stack confirmation (user-approval gated). Produces a SCOPE-.md that your scaffolding workflow consumes. Fills the gap between "requirements" and "create the project".

cubha/claude-workflow-plugins

Skill Claude CodeCodex

A planning tool that defines a project's feature scope, priorities, estimated effort, and technology choices before coding begins. MoSCoW is a method for sorting features into must-have, should-have, could-have, and not-now groups.

cubha/claude-workflow-plugins

Plugin Claude Code

One-shot release pipeline: commit, push, PR, merge, and branch cleanup. Auto-adapts branch strategy -- git-flow (feature to develop to main) if a develop branch exists, otherwise GitHub Flow (feature to main). Runs a pre-merge gate bundle: functional check (verify.sh or the project's test command), security scan…

cubha/claude-workflow-plugins

Agent

A database schema and migration reviewer examines changes to the structure of a database, such as tables, columns, indexes, and data updates. It reviews only the files provided and produces a report without changing code.

cubha/claude-workflow-plugins

Agent

A security-review agent that scans specified code files or changes for common vulnerabilities, including broken access controls, exposed secrets, injection, and weak encryption.

cubha/claude-workflow-plugins

Skill Claude CodeCodex

An automated release workflow that commits current changes, pushes them, opens and merges a pull request, and cleans up the branch. A pull request is a proposed code change for review; the workflow adapts to repositories using either a develop branch or direct feature-to-main merging.

cubha/claude-workflow-plugins

Plugin Claude Code

Parallel development orchestrator: dependency-analyzes SubTasks, groups them, and implements them concurrently in git-worktree isolation (bundled feature-builder agent). Includes an opt-in TDD RED-gate flow.

cubha/claude-workflow-plugins

Agent

A specialist agent for implementing one assigned feature in an isolated Git worktree, which is a separate working copy of the repository. It is intended to run as part of a team development coordinator when different features are built in parallel.

cubha/claude-workflow-plugins

Skill Claude CodeCodex

A workflow for splitting a software task into smaller jobs and assigning independent jobs to coding agents working in separate Git worktrees. A worktree is an isolated working folder connected to the same Git repository.

cubha/claude-workflow-plugins

Plugin Claude Code

Pre-project research orchestrator: tech-stack, architecture, competitor, and UX researcher subagents run in parallel (4 bundled agents), cross-validated into one report.

cubha/claude-workflow-plugins

Agent

A research agent that studies architecture patterns and real-world examples for a planned software project. Software architecture is the way a project organizes its code, data flow, and responsibilities.

cubha/claude-workflow-plugins

Agent

A market research role that compares real products serving the same kind of users or problem. It examines their features, audiences, pricing, user feedback, strengths, and weaknesses.

cubha/claude-workflow-plugins

Agent

A technical-stack research agent that compares possible programming technologies before a project starts. It produces an objective comparison covering trade-offs, current information, benchmarks, community activity, and sources.