Ryuya Matsunawa
Community@ryuya-matsunawa · Japan, Tokyo
Ryuya Matsunawa publishes 20 skills covering disciplined software development practices—TDD, debugging, code review, git worktrees—plus natural Japanese business writing.
Agent Skills by Ryuya Matsunawa
Showing 19 vetted skills indexed across 1 GitHub repositories.
using-git-worktrees
Creates isolated git worktree workspaces with baseline test verification before feature implementation.
test-driven-development
Enforces red-green-refactor test-driven development workflow before writing implementation code.
systematic-debugging
Diagnose bugs through a four-phase root cause investigation process before proposing fixes.
using-superpowers
Enforces skill discovery and invocation before any AI agent response across platforms.
dispatching-parallel-agents
Dispatches multiple subagents concurrently to investigate independent failures across separate problem domains.
find-skills
Searches and installs agent skills from the open skills ecosystem using the Skills CLI.
executing-plans
Executes written implementation plans task-by-task with verification checkpoints and review gates.
finishing-a-development-branch
Guides completion of development branches through structured merge, pull request, or cleanup options.
herdr
Control Herdr terminal multiplexer workspaces, panes, and coding agents via CLI.
brainstorming
Guides collaborative design dialogue to turn ideas into approved specs before implementation.
natural-japanese
Write, revise, and score natural Japanese business documents using deterministic lint detection.
interview-dev
Runs a full development loop with pre-implementation interviews and independent post-implementation code reviews.
writing-plans
Generate detailed multi-task implementation plans with TDD steps from feature specifications.
requesting-code-review
Dispatches a code reviewer subagent to evaluate git changes against requirements before merging.
receiving-code-review
Guides verification and implementation of code review feedback with technical rigor.
verification-before-completion
Enforces running verification commands before claiming work is complete or passing.
grill-me
Interviews the user question-by-question to stress-test plans and design decisions.
grilling
Interviews users in structured question rounds to stress-test plans and decisions.
subagent-driven-development
Executes implementation plans by dispatching fresh implementer and reviewer subagents per task.
Frequently Asked Questions About Ryuya Matsunawa
FAQPage SchemaWhat tasks can I accomplish with ryuya-matsunawa's skills?▼
You can run disciplined development cycles: test-driven development, systematic debugging, writing and executing implementation plans, requesting and receiving code reviews, verifying work before completion, and managing isolated git worktree branches. A separate natural-japanese skill writes, rewrites, and scores Japanese business documents.
Who are these skills designed for?▼
Software engineers who want enforced rigor—TDD before implementation, evidence before success claims, structured code review—and teams running parallel or subagent-driven development sessions. The natural-japanese skill targets professionals drafting minutes, reports, proposals, emails, and blog articles in Japanese.
How do the development-process skills work in practice?▼
Skills trigger on context: interview-dev runs a pre-implementation interview and post-implementation self-review loop; writing-plans precedes coding; executing-plans runs plans with review checkpoints; verification-before-completion requires running verification commands before claiming work is done.
Are these skills open source, and what do they cost?▼
The natural-japanese skill is explicitly MIT-licensed and free to use. Other skills in the manifest do not state a license, so users should check each skill folder in the repository before redistribution or commercial use.
What prerequisites or dependencies do these skills require?▼
Most skills are process guidelines requiring no external dependencies. The herdr skill is the exception: it controls the Herdr terminal multiplexer for panes, tabs, and workspaces, and requires the HERDR_ENV=1 environment variable to be set before use.