By cdubiel08
Polymorphic UI testing plugin: story generation, E2E execution, a11y scanning, Storybook integration, and visual regression for ralph-hero.
Freeform exploration agent. Navigates a web app via playwright-cli toward a stated goal, maps interactive elements and paths, captures screenshots and snapshots at each step, and writes a journey trace YAML.
Executes a single user story YAML via playwright-cli. Captures screenshots and accessibility snapshots per step, captures console errors on failure, and writes a structured journey trace YAML to the session directory.
Run a WCAG 2.2 AA accessibility audit against a URL using playwright-cli. Captures accessibility snapshots, analyzes for violations, and creates issues for findings. Uses the execute → reflect → act pipeline with an a11y-focused goal.
Raw browser automation via playwright-cli with ralph-hero conventions. Use when you need direct access to playwright-cli commands — navigation, interaction, screenshots, snapshots, cookies, storage, network, devtools. All other ralph-playwright skills compose through this one. Requires global install of @playwright/cli.
Quick one-shot — screenshot a URL and optionally promote the screenshot to a research note in thoughts/. Runs execute (1-step) → reflect (minimal) → act (promote). Use for grabbing a screenshot of a specific page state.
Explore a running website to discover user flows, analyze findings, and produce research notes with promoted screenshots. Uses the execute → reflect → act pipeline via playwright-cli. Works on localhost or any accessible URL.
Analyze a journey trace and its screenshots to produce a signal report. Use when you have a journey trace from a previous execute run and want to analyze it separately. Reads screenshots and accessibility snapshots to identify anomalies, regressions, a11y violations, and UX issues.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin that turns Claude into an autonomous software engineer. Ralph triages issues, researches codebases, writes implementation plans, codes in isolated worktrees, creates PRs, and merges -- all driven by a GitHub Projects V2 board.
The naive hero picks tickets, does their best work, and moves on.
Ralph manages GitHub issues through a structured workflow state machine:
Backlog → Research Needed → Research in Progress → Ready for Plan
→ Plan in Progress → Plan in Review → In Progress → In Review → Done
Each transition is enforced by hooks and validated by the MCP server. Issues flow through phases -- triage, research, planning, review, implementation, and merge -- with human checkpoints at plan review and code review.
Autonomous mode (/ralph-hero:hero): Ralph drives an issue tree end-to-end, splitting large tickets, researching each sub-issue, creating plans, and implementing them sequentially.
Interactive mode: Use individual skills like /ralph-hero:plan or /ralph-hero:impl with human-in-the-loop verification at each step.
Team mode (/ralph-hero:team): Spawns parallel specialist agents (analyst, builder, integrator) to process issues concurrently.
repo and project scopesclaude plugins add cdubiel08/ralph-hero
Add your GitHub token and project settings to .claude/settings.local.json (gitignored):
{
"env": {
"RALPH_HERO_GITHUB_TOKEN": "ghp_your_token_here",
"RALPH_GH_OWNER": "your-github-username",
"RALPH_GH_PROJECT_NUMBER": "1"
}
}
/ralph-hero:setup
This creates a GitHub Projects V2 board with the required custom fields: Workflow State, Priority, and Estimate.
Run the full pipeline or individual phases:
| Skill | Description |
|---|---|
/ralph-hero:hero | Drive an issue through the full lifecycle end-to-end |
/ralph-hero:team | Multi-agent team with parallel analyst, builder, and integrator workers |
/ralph-hero:ralph-triage | Assess backlog issues -- close duplicates, split large tickets, route to research |
/ralph-hero:ralph-research | Investigate an issue, create a research document, update issue state |
/ralph-hero:ralph-plan | Create an implementation plan from research findings |
/ralph-hero:ralph-review | Review and critique plans (interactive or automated) |
/ralph-hero:ralph-impl | Implement one phase of an approved plan in an isolated worktree |
/ralph-hero:ralph-val | Validate implementation against plan requirements |
/ralph-hero:ralph-pr | Push branch and create a pull request |
/ralph-hero:ralph-merge | Merge an approved PR, clean up worktree, move issues to Done |
/ralph-hero:ralph-split | Decompose M/L/XL issues into XS/S sub-issues |
Human-in-the-loop skills for collaborative development:
| Skill | Description |
|---|---|
/ralph-hero:draft | Quickly capture an idea for later refinement |
/ralph-hero:form | Crystallize draft ideas into structured GitHub issues |
/ralph-hero:research | Interactive codebase research with parallel sub-agents |
/ralph-hero:plan | Create implementation plans through collaborative exploration |
/ralph-hero:iterate | Refine or extend an existing plan |
/ralph-hero:impl | Implement an approved plan phase-by-phase with manual verification |
| Skill | Description |
|---|---|
/ralph-hero:hello | Session briefing -- pipeline status, hygiene warnings, actionable insights |
/ralph-hero:status | Pipeline dashboard with health indicators and WIP violations |
/ralph-hero:report | Generate and post a project status report to GitHub |
/ralph-hero:ralph-hygiene | Identify archive candidates, stale items, and board health issues |
/ralph-hero:setup | One-time project board setup with required fields |
/ralph-hero:setup-repos | Bootstrap multi-repo portfolio management |
/ralph-hero:idea-hunt | Scout GitHub for interesting ideas, trends, and inspiration |
/ralph-hero:record-demo | Record an annotated product demo and attach to an issue |
The plugin bundles an MCP server (ralph-hero-mcp-server) that provides GitHub Projects V2 tools to Claude Code via the Model Context Protocol.
npx claudepluginhub cdubiel08/ralph-hero --plugin ralph-playwrightGenerate sprint demo videos from structured JSON input using Remotion. Reusable scene templates, pluggable themes, and export presets for 16:9, 1:1, and 9:16 formats.
Knowledge graph for ralph-hero: semantic search, relationship traversal, and document indexing across thoughts/ documents. Optional companion to ralph-hero.
AI test generation with Ralph-loop quality gate: coder → reviewer → iterate
Production-grade Playwright testing toolkit. Generate tests from specs, fix flaky failures, migrate from Cypress/Selenium, sync with TestRail, run on BrowserStack. 55+ ready-to-use templates, 3 specialized agents, smart reporting that plugs into your existing workflow.
10 coordinated QA agents for Claude Code: chains diff analysis, AC compliance, test scenarios, browser validation, bug reports, and automation code generation.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Comprehensive SEO analysis plugin for Claude Code. 25 sub-skills (21 core + 1 orchestrator + 1 framework + 2 extension mirrors) and 18 sub-agents cover technical SEO, content quality, schema, sitemaps, Core Web Vitals, local SEO, backlinks, AI/GEO, ecommerce, hreflang, SXO, clustering, drift monitoring, and Google APIs. Includes optional MCP extensions, SPA-aware rendering, portability, and hardened SSRF/DNS-rebinding safe fetchers.
Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more