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.
Write prose that sounds authentically human rather than AI-generated. Use this skill whenever writing long-form content, emails, articles, reports, documentation, blog posts, creative writing, social media copy, proposals, memos, or any text where sounding like a real person matters. Triggers on requests like "write this naturally," "make it sound human," "don't sound like AI," "write like a real person," or any writing task where the user has indicated they want authentic, non-robotic prose. Also use when editing existing text to remove AI-sounding patterns.
Help the user craft presentations, pitches, talks, demos, launch announcements, all-hands updates, sales decks, fundraising pitches, conference talks, memos, narratives, blog posts, founder updates, internal announcements, layoff communications, post-mortems, kickoffs, town halls, and any other communication intended to persuade, inspire, inform, or move an audience. Use this skill whenever the user is preparing to present, pitch, announce, launch, kick off, give a talk, write a memo, share news, or otherwise tell a story to other humans — even when they don't use the word "story." It walks a structured diagnostic and applies tactics from a 54-card storytelling system (Concept, Explore, Character, Function, Structure, Style, Organise) plus seven recipes that combine tactics for common goals.
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 curated set of Claude Code plugins that add structured workflows to your AI sessions — from Linear planning and QA, to billable hour tracking, to prose rewriting. Each plugin bundles several related skills you install once and use across every project.
Requires Claude Code v1.0.33 or later.
Some plugins reach outside Claude Code itself. Check what you need before installing:
| Plugin | External dependencies |
|---|---|
delivery | Linear MCP (all skills); Playwright MCP (/qa visual verification); OPENAI_API_KEY env var (/plan-design image generation) |
meta | None — runs entirely inside Claude Code |
track | jq, git (both must be on your PATH) |
writing | None |
If you already know which plugin you want:
/plugin install delivery@mvdmakesthings
/plugin install writing@mvdmakesthings
/plugin install track@mvdmakesthings
/plugin install meta@mvdmakesthings
Add the marketplace first, then explore from the Discover tab:
/plugin marketplace add mvdmakesthings/skills
Then open the plugin browser:
/plugin
Navigate to the Discover tab and install what you need.
| Plugin | What it does |
|---|---|
delivery | Linear-driven planning → QA flow: PRDs, issue slicing, plan grilling, design mockups, test planning, and QA execution |
writing | Humanize AI-sounding prose; storytelling coach for pitches, talks, and memos |
track | Billable hours timer backed by a git-versioned plaintext ledger |
meta | Improve your own skills: capture session friction, then evolve SKILL.md files with your approval |
delivery/plugin install delivery@mvdmakesthings
A full planning-to-QA pipeline built around Linear. Skills chain together — /to-prd → /to-issues → /plan-design + /plan-qa → /qa — but each one works independently.
| Command | What it does | Requires |
|---|---|---|
/to-prd | Synthesizes the current conversation into a PRD and publishes it to Linear | Linear MCP |
/to-issues | Slices a plan, spec, or PRD into independently-grabbable Linear issues — each a thin vertical slice with its own acceptance criteria | Linear MCP |
/grill-with-docs | Challenges a plan against your CONTEXT.md and ADRs one question at a time, resolves terminology conflicts, and writes decisions back into those docs inline | CONTEXT.md / ADRs |
/plan-design <issue-id> | Reads a Linear issue, interviews you per UI surface, generates three layout mockups via OpenAI image generation, builds HTML/CSS for the one you pick, and attaches it to the ticket | Linear MCP, OPENAI_API_KEY |
/plan-qa <issue-id> | Drafts a layer-aware test plan from a ticket's acceptance criteria and attaches it as <issue-id>-test-plan.md for /qa to execute | Linear MCP |
/qa [issue-id] | Maps acceptance criteria to coverage, runs every test layer, executes the attached test plan, and screenshots the UI against design attachments | Linear MCP, Playwright MCP |
writing/plugin install writing@mvdmakesthings
| Command | What it does | Requires |
|---|---|---|
/writing:human [prompt] | Rewrites prose so it reads like a person wrote it — strips the vocabulary and sentence patterns that flag text as AI-generated | None |
storyteller-guidance | A storytelling coach for pitches, talks, and memos. Auto-triggers on pitch / talk / memo phrasing. Draws from a 54-card tactic deck | None |
track/plugin install track@mvdmakesthings
| Command | What it does |
|---|---|
/track:start <client> | Start a billable timer for a named client |
/track:stop [note] | Stop the active timer with an optional session note |
/track:pause | Pause the active timer |
/track:resume | Resume a paused timer |
/track:status | Show the active timer and today's totals per client |
/track:report | Print an invoice-ready rollup with hours and dollar totals |
Sessions are recorded to a git-versioned JSONL ledger under ~/.time-tracker/. Requires jq and git on your PATH.
meta/plugin install meta@mvdmakesthings
Two skills that form a continuous improvement loop for any skill in this marketplace:
Any project Skills repo
─────────── ───────────
Run a skill
↓
/skill-reflect ──── logs ───→ ~/.claude/skill-sessions/
↓
/skill-improve ──→ SKILL.md updated
↓
HITL approval gate
npx claudepluginhub mvdmakesthings/skills --plugin writingRefinement-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.
Domain-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.
Skills that improve other skills — session reflection, friction logging, and HITL-gated SKILL.md evolution.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.