Refinement-time test planning: reads a Linear issue's acceptance criteria and the repo's test conventions, then drafts a layer-aware test plan — per-AC scenarios tagged with a test layer and an expected result, plus auth roles, fixtures, visual states, and regression watch areas — and after your approval attaches it to the ticket as <issue-id>-test-plan.md for the qa skill to execute against.
A curated collection of plugins, skills, and agents for Claude Code.
Requires Claude Code v1.0.33 or later.
Add the marketplace:
/plugin marketplace add mvdmakesthings/skills
Browse available plugins:
/plugin
Then navigate to the Discover tab and install what you need.
You can also install plugins directly:
/plugin install <plugin-name>@mvdmakesthings
| Plugin | Command | What it does | Requires |
|---|---|---|---|
qa | /qa [issue-id] | Reviews your current changes against a Linear issue: maps acceptance criteria to coverage, runs every test layer it finds, and screenshots the UI against design attachments. | Linear MCP, Playwright MCP |
plan-design | /plan-design <issue-id> | Turns a Linear issue into design mockups. Interviews you on each UI surface, generates three layout options with OpenAI image generation, then builds the HTML/CSS for the one you pick and attaches it to the ticket. | Linear MCP, OpenAI API key |
grill-with-docs | /grill-with-docs | Interrogates a plan against your CONTEXT.md and ADRs one question at a time, then writes the resolved decisions back into those docs. | CONTEXT.md / ADRs |
to-issues | /to-issues | Slices a plan, spec, or PRD into Linear issues you can pick up independently. Each one is a thin end-to-end cut with its own acceptance criteria. | Linear MCP |
to-prd | /to-prd | Synthesizes the current conversation into a PRD and publishes it to Linear. | Linear MCP |
writer | /writer:human [prompt] | Rewrites prose so it reads like a person wrote it, stripping the vocabulary and sentence patterns that flag text as AI-generated. | none |
storyteller-guidance | auto-triggers on pitch / talk / memo phrasing | A storytelling coach. Picks from a 54-card tactic deck to draft or coach you through pitches, talks, and memos. | none |
track | /track:start <client> | Billable-hours timer backed by a git-versioned plaintext ledger under ~/.time-tracker/. Rounded out by stop, pause, resume, status, and report. | jq, git |
"Requires" lists what each plugin reaches for beyond Claude Code itself. MCP servers (Linear, Playwright) are configured in your Claude Code settings; plan-design reads the OpenAI key from your environment for image generation.
Each plugin lives in its own directory under skills/. Here's the structure:
skills/
└── your-plugin/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest (required)
├── skills/ # Skills (optional)
│ └── your-skill/
│ └── SKILL.md
├── agents/ # Agents (optional)
│ └── your-agent.md
├── commands/ # Slash commands (optional)
│ └── your-command.md
└── hooks/ # Hooks (optional)
mkdir -p skills/your-plugin/.claude-plugin
Create skills/your-plugin/.claude-plugin/plugin.json:
{
"name": "your-plugin",
"description": "What your plugin does",
"version": "1.0.0"
}
Add skills, agents, commands, or hooks to their respective directories. See the Claude Code plugin docs for details on each component type.
Add an entry to .claude-plugin/marketplace.json:
{
"plugins": [
{
"name": "your-plugin",
"source": "./skills/your-plugin",
"description": "What your plugin does"
}
]
}
claude plugin validate .
/plugin marketplace add ./path/to/skills
/plugin install your-plugin@mvdmakesthings
skills/.claude-plugin/marketplace.jsonclaude plugin validate .Please keep plugins focused: one clear purpose per plugin.
MIT
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.
npx claudepluginhub mvdmakesthings/skillsDomain-expert personas that drop into any project and work with its conventions: a Postgres-first DBA (/dba) for health audits, schema design, index/bloat cleanup, slow-query diagnosis, and live incident investigation.
Linear-driven planning→QA flow: PRDs, issue breakdown, plan grilling, design mockups, test planning, QA execution, and post-incident reports. Bundles the to-prd, to-issues, grill-with-docs, plan-design, plan-qa, qa, and pir skills.
Console-native billable hours tracker with git-versioned plaintext ledger.
Writing toolkit: humanize AI-sounding prose (/writing:human) and a storytelling coach for pitches, talks, and memos. Bundles the human-voice-writer and storyteller-guidance skills.
Skills that improve other skills — session reflection, friction logging, and HITL-gated SKILL.md evolution.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
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
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
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses