By my-stacks
Headless responsive UI review across breakpoints, themes, a11y, Core Web Vitals, SEO, and visual regression. Built for Vercel preview deploys.
Just the accessibility audit. Runs axe-core and Pa11y at the configured breakpoints, including hover/focus/dark-mode states.
Bootstrap authentication for design QA. Copies the right Playwright auth setup template into the project, gitignores the storage-state directory, and prompts for credentials.
Just Core Web Vitals and Lighthouse. Mobile + desktop runs.
Just the breakpoint screenshot matrix without the full review. Useful for quick visual diffs.
Run a full headless design QA review against a URL. Sweeps breakpoints, runs axe + Lighthouse + SEO checks, optionally uploads to Argos, and produces a structured report.
Use when comparing the current page against a stored visual baseline. Uses Argos when an Argos token is configured, otherwise falls back to Playwright's built-in toHaveScreenshot.
Use when validating SEO basics, Open Graph, Twitter Card, JSON-LD, viewport meta, lang attribute, and heading hierarchy on a deployed page. Important for marketing sites and SEO-sensitive client work.
Use when running a WCAG 2.2 AA accessibility audit on a deployed web page. Combines axe-core and Pa11y, triggers hover/focus states (which axe misses by default), tests across light/dark themes, and outputs severity-ranked findings.
Use when measuring Lighthouse / Core Web Vitals (LCP, INP, CLS, TBT) on a deployed page. Runs both mobile and desktop profiles, reports actual measured numbers, and identifies top opportunities.
Use when capturing screenshots of a deployed web page across many viewport widths to find layout breaks. Specifically catches "grey area" widths (700, 900, 1180) where designs commonly fail between standard breakpoints. Sweeps 18 widths × light/dark/reduced-motion themes by default.
Requires secrets
Needs API keys or credentials to function
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.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
argosTokenArgos CI token for visual regression baselines. Get from argos-ci.com.
${user_config.argosToken}authStrategyHow the QA agent authenticates to protected app routes.
${user_config.authStrategy}browserDriverBrowser driver. 'playwright-mcp' (default) uses Microsoft Playwright MCP. 'agent-browser' uses Vercel agent-browser CLI for token-efficient runs and real Mobile Safari.
${user_config.browserDriver}breakpointPresetBreakpoint matrix to sweep. 'fast' = 5 widths. 'agency-default' = 18 widths covering grey areas. 'thorough' = 18 widths + ultra-wide + foldable outer + landscape.
${user_config.breakpointPreset}reviewerConfigPathPath (relative to project root) to the reviewer persona config. Defaults to .claude/design-qa/reviewer.json.
${user_config.reviewerConfigPath}vercelBypassSecretVercel Protection Bypass for Automation secret. Used as x-vercel-protection-bypass header to access protected preview deploys.
${user_config.vercelBypassSecret}argosUploadOnReviewAuto-upload screenshots to Argos at the end of /design-qa:review. Requires argosToken.
${user_config.argosUploadOnReview}Reusable components for Claude Code: skills, agents, commands, and more. Built for token efficiency, cross-model compatibility, and minimal friction.
| Component | Type | Version | What it does |
|---|---|---|---|
| linear | Skill | 0.5.1 | Linear project management with session continuity. Buffered writes, board management, ticket creation, structured handoffs persisted to Linear. Auto-maintains .latest-status.md. |
| handoff | Skill | 3.0.1 | Session continuity via .latest-status.md. Auto-updates during plan execution. Manual handoff, resume, and transfer commands. |
| vault-backup | Skill | 1.0 | Save research, project outputs, and knowledge artifacts from any Claude Code workspace into a shared Obsidian knowledge vault. |
| ai-router | Skill | 1.1 | Route tasks to optimal model tiers and ensemble responses across Claude, GPT, and Gemini APIs. Requires curl and jq. |
| pull-and-sync | Command | 1.0 | Sync working branch with latest from default branch using merge --no-ff. |
| commit | Command | 1.0 | Smart commit with conventional format, staged diffs, and hook compliance. |
| push | Command | 1.0 | Push with safety checks, branch protection, and tracking setup. |
| commit-push-pr | Command | 1.0 | Full pipeline: commit, push, and create a PR via gh CLI. |
| update-skills | Command | 1.0 | Check installed Stacklist components for available updates. |
Copy a component to your Claude Code config directory:
# Install a skill
cp -r .claude/skills/linear/ ~/.claude/skills/linear/
# Install an agent
cp .claude/agents/<name>.md ~/.claude/agents/
# Install a command
cp .claude/commands/commit.md ~/.claude/commands/
Then reference skills in your project's CLAUDE.md:
## Skills
Load skills from ~/.claude/skills/ as needed.
Each component has a version in its frontmatter. Compare against versions.yaml in this repo:
curl -s https://raw.githubusercontent.com/stacklist/claude-code-skills/main/versions.yaml
Or check locally if you've cloned the repo:
cat versions.yaml
claude-code-skills/
├── README.md
├── CLAUDE.md
├── versions.yaml
└── .claude/
├── skills/
│ ├── linear/
│ │ ├── SKILL.md
│ │ └── REFERENCE.md
│ ├── handoff/
│ │ └── SKILL.md
│ ├── vault-backup/
│ │ └── SKILL.md
│ ├── ai-router/
│ │ ├── SKILL.md
│ │ └── REFERENCE.md
├── agents/
│ └── .gitkeep
└── commands/
├── commit.md
├── push.md
├── commit-push-pr.md
├── pull-and-sync.md
├── update-skills.md
└── vault-backup.md
These components are built around a few constraints that shape every decision.
Token efficiency is a first-class concern. Every instruction competes for context window space. Templates and formats are as lean as possible without sacrificing clarity. If removing a line wouldn't cause the LLM to make a mistake, the line gets cut.
Cross-model compatibility. Components use standard markdown with YAML frontmatter. No model-specific syntax or features. They should work in Claude Code, Cursor, Windsurf, or any tool that reads markdown skill files.
Progressive disclosure. Not everything loads at once. Reference files are loaded on demand. The agent gets what it needs for the current command, not the entire knowledge base.
Fixes a frontmatter parsing bug in both skills. The ## Version Check section was placed before the YAML frontmatter, preventing the parser from reading trigger, description, and other metadata. This caused /linear update to run a version check instead of posting a project status update, and both skills to appear as "Version Check" in the skill list.
To upgrade:
cp -r .claude/skills/linear/ ~/.claude/skills/linear/
cp -r .claude/skills/handoff/ ~/.claude/skills/handoff/
The linear skill now auto-maintains .latest-status.md (the same file used by the handoff skill), eliminating the need to run /handoff separately when using Linear.
npx claudepluginhub my-stacks/claude-code-skills --plugin design-qaUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications