By hanamizuki
Core skills: plan review, code review loops, backlog management, and thinking partners.
PR orchestration planner. Reads a task file, discusses PR splitting strategy with the user, produces plan + spec files, and either dispatches a worktree subagent in the current session (single PR, run now) or schedules execution via cron (multi-PR, or single-PR scheduled). Use when the user wants a task implemented, reviewed, and merged automatically — whether the scope fits in one PR or needs to be split. Triggers: "autopilot", "orchestrate", "batch implement", "split into PRs and run", or when the user provides a todo/spec and wants unattended PR execution.
Automated PR review loop that keeps running until the PR is clean. Triggers external reviewers (Codex bot, Codex CLI, Gemini), processes feedback, fixes issues, and re-triggers — repeating until no new suggestions remain. Supports `/greenlight external` to skip internal review and go straight to external reviewers, and `/greenlight external gemini` to specify a starting reviewer. Use when the user says "greenlight", "run reviews until clean", "get this PR approved", or wants automated review cycling on an open PR. Also auto-detects uncommitted mode: when on main branch with uncommitted changes and no PR, runs Codex CLI `--uncommitted` review loop only, fixes in-place without committing, until codex reports clean. Also supports post-commit mode (explicit `/greenlight post-commit <SHA>` or `<SHA1>..<SHA2>`): Phase 1 subagents + Codex CLI + Gemini in parallel, fixes as new commits on top (no amend, no new PR), pushes after each round.
Generate a self-contained handoff context document for the current work, printed inline as markdown so the user can copy it and paste into any other agent — a fresh Claude Code session, Codex, ChatGPT, or an agent on another machine. Use when the user says /handoff, "write context for the next session", "package this for handoff", "hand off to another agent", or wants to capture the current session's state in a portable form. Output is printed inline AND written to `/tmp/handoff/<YYYY-MM-DD>_<slug>.md`. No worktree is created (use worktree-handoff if a git worktree is needed).
Merge an open PR for the current branch. Refuses to merge when the worktree has uncommitted changes, consolidates the branch's plan file (renaming the latest Handoff Context section to Final Progress and moving the file to done/ in state-machine mode), merges via GitHub CLI, and reports status. Also cleans up stale merged-but-not-removed worktrees from prior sessions on every run. Use when the user says "merge", "merge PR", "merge this", or wants to land the current branch.
Meta-orchestrator for going from a product idea to a demo-able MVP fast. Drives the full flow: brainstorming → PRD visual confirmation (user gate) → template lookup → MVP-flavored plan → single-subagent execution. Optimized for **time-to-first-demo**, not production quality — no TDD, no per-task review loops, no hardening. Use INSTEAD OF superpowers:brainstorming when the user is starting a new product from scratch — this skill calls brainstorming internally, then chains in a PRD confirmation phase, template discovery, plan writing, and execution. Triggers: "/mvp", "我要做 app", "想做產品", "想做一個 app", "做個 MVP", "build a product", "build an app from scratch", "MVP from scratch", "start a new app", "new product".
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.
solopreneur is a family of Claude Code plugins that gives solo founders the workflows of a full engineering org: plan review, code review loops, automated PR cycles, marketing, design, and platform-specific experts. Install à la carte.
claude plugin marketplace add hanamizuki/solopreneur
claude plugin install solopreneur@solopreneur
Then add whichever roles you need (marketer, designer, ios-dev,
android-dev, ai-engineer, neo4j-dev). See the full install guide
for details and role-based recommendations.
| Plugin | What you get |
|---|---|
solopreneur | 16 in-house skills (review, pipelines, thinking partners, automation) |
marketer | marketer agent + 7 in-house skills (GTM, naming, writing, X/LinkedIn growth, slide design) |
designer | designer agent + 10 vendored design skills (taste-* family + impeccable) |
ios-dev | ios-dev agent + ios-patterns + ios-app-templates (reference apps) + 23 vendored skills (asc-* + iphone-apps) |
android-dev | android-dev agent + android-patterns + 39 vendored skills (Compose + gplay-* + Android official) |
ai-engineer | ai-engineer agent + langgraph + ai-app-templates + 1 vendored skill (senior-prompt-engineer) |
neo4j-dev | neo4j-dev agent + 4 vendored Neo4j skills |
Installing any sub-plugin auto-pulls solopreneur. Requires Claude Code
≥ v2.1.110 for plugin dependency resolution.
Migrating from a previous version? See MIGRATION.md. For per-release, per-plugin notes, see CHANGELOG.md.
Each plugin section describes the bundled skills (in-house and vendored) plus its Requirements: external CLIs, plugins, MCPs, or GitHub apps the plugin's skills and agent integrate with. Hard requirements are called out explicitly; everything else is recommended and degrades gracefully if absent.
solopreneur (core)The foundation. Every other plugin depends on this one. No agent, just 16 skills that wrap the lifecycle around your work.
| Skill | What it does |
|---|---|
/mvp | PM. Drives the full new-product flow end-to-end: brainstorming → PRD visual confirmation → template lookup (auto-discovers *-app-templates in installed plugins) → plan → execution. Use when starting from scratch |
/second-opinion | Advisor. Challenges your plan across 5 dimensions (completeness, consistency, clarity, scope, feasibility) using an independent reviewer |
/tech-vetting | Tech Lead. Vets your technical plan against the latest official docs and platform-specific best practices before you write a single line of code |
/worktree-handoff | Coworker. Creates an isolated git worktree with a CONTEXT.md so the next session picks up exactly where you left off |
/handoff | Scribe. Packages the current session into a self-contained markdown context doc, printed inline so you can copy and paste it into any other agent (Codex, ChatGPT, a fresh Claude session, an agent on another machine). No worktree, no file save |
/preview | Presenter. Turns any proposal / plan / idea into an interactive HTML page, deploys it to Vercel for a protected-by-default review URL (or a public bucket when explicitly requested), with an in-page comment overlay so reviewers can highlight text and leave in-context feedback you can act on directly |
/specialist-review | Code Reviewer. Detects your tech stack, dispatches matching expert agents, and reviews against best-practice skill indices |
/post-mortem | SRE. Traces a bug through git history, finds the root cause commit, produces a structured post-mortem report |
/session-retro | Coach. Reviews the current conversation for mistakes, traces root causes, proposes durable process improvements |
/perspective | Thinking Partner. Switch between thinker perspectives (Musk, Feynman, Munger, Naval, Jobs, Taleb, …) to analyze problems from a different angle |
This repo dogfoods the backlog workflow with public task files under
todos/.
npx claudepluginhub p/hanamizuki-solopreneur-plugins-solopreneurUI/UX design expertise. Ships the designer agent and 10 vendored third-party design skills (taste-* archetype family + impeccable).
Android/Kotlin expertise. Ships the android-dev agent, android-patterns, and 39 vendored third-party skills (Compose / architecture / Gradle + 18 gplay-* Google Play Console CLI + 6 official Android team skills).
Neo4j graph database expertise. Ships the neo4j-dev agent and 4 vendored third-party skills (cypher / cypher-guide / migration / cli-tools).
AI / LLM application engineering expertise. Ships the ai-engineer agent plus in-house skills (langgraph, ai-app-templates) and 1 vendored skill (senior-prompt-engineer) for production LLM systems, RAG, agents, and prompt design.
Marketing / brand / writing expertise. Ships the marketer agent plus GTM strategy, naming, X/Twitter & LinkedIn growth, AI-pattern removal, and brand-aware slide design.
UI/UX design expertise. Ships the designer agent and 10 vendored third-party design skills (taste-* archetype family + impeccable).
Agent-first PM toolkit with 9 specialist agents and 18 skills for solo developers and small teams
Toolkit for solo developers to build, manage, and grow their business - customer profiling, brand guidelines, design system, SEO strategy, X/Twitter growth strategy, and more
Your own path. Multiple stacks. Ship everything. 30 skills, 3 agents, code intelligence MCP — from shower thought to deployed product.
A comprehensive collection of custom skills for Claude Code covering engineering, product management, design, content, trading, database, QA, and educational domains
An operator-grade AI skill stack for builders. Elite, domain-tested skills and structured /commands for every stage of the product lifecycle: strategy, design, engineering, marketing, sales, and ops. Cross-tool: Claude Code, Cursor, Codex, opencode.