Kentaro Wada
Community@wkentaro · Tokyo
Building intelligence to automate more.
Agent Skills by Kentaro Wada
Showing 14 vetted skills indexed across 1 GitHub repositories.
wkentarosetup-github-labels
Apply and document a canonical GitHub issue and pull-request label set in a repository.
wkentarosending-pull-request
Prepare branches, write PR titles and bodies, and publish GitHub pull requests with verified evidence.
wkentarowriting-code
Write and audit code against house coding conventions with rule-cited findings.
wkentaroreview-fix
Runs configurable review-and-fix rounds on a change until reviewers report clean.
wkentarocompetitive-advantage
Analyzes and stress-tests competitive advantages using a structured moat evaluation framework.
wkentarowhere-am-i
Render open task decisions as an ASCII tree with markers and ordered open questions.
wkentaroharvest-sessions
Sweep recent Claude Code and Codex session transcripts into a reviewed secondbrain pull request.
wkentaroask-exemplar
Evaluate decisions and completed artifacts against researched standards and exemplars.
wkentarotelegram-daily-log
Summarize verified daily accomplishments from git, GitHub, and shell history into a Telegram post.
wkentarowriting-social-posts
Draft, sequence, and refine social posts for X threads, Show HN, and LinkedIn.
wkentaroclean-branch
Extract essential feature changes from mixed commits and working-tree state into a fresh branch.
wkentarorecommit
Rewrites unmerged branch commits into a clean logical sequence while preserving the final tree.
wkentarohear-me
Validates voice-dictated requests with readback checks and resolves ambiguous terms before execution.
wkentaroask-me-again
Re-asks pending assistant questions as native interactive structured choices.
Frequently Asked Questions About Kentaro Wada
FAQPage SchemaWhat tasks can I accomplish with wkentaro's skills?▼
You can apply canonical GitHub label sets, draft and push pull requests, audit code against house conventions, run review-and-fix rounds, clean up branch history with recommit and clean-branch, render pending decisions as ASCII trees, and draft X threads, Show HN, and LinkedIn posts.
Who are these skills designed for?▼
Software developers and open-source maintainers who manage Git branches, prepare pull requests for review, enforce coding conventions, and publish technical updates. Strategy-focused users also get moat analysis and exemplar-grounded recommendations for decisions, designs, and diffs.
What are the prerequisites and dependencies?▼
Most skills run inside a Claude Code or Codex conversation. harvest-sessions additionally requires local Claude Code or Codex transcripts, Python 3, Git, GitHub CLI access, and a wkentaro/secondbrain checkout. ask-exemplar needs a web search or page retrieval capability, otherwise it reports Evidence Gaps.
How do the Git history skills differ from each other?▼
recommit reshapes the commits a branch carries into a clean logical sequence without changing the final tree, while clean-branch extracts essential feature changes from mixed committed and working-tree work into a new branch. Use recommit for history polish and clean-branch for isolating a minimal feature.
Are these skills free to use?▼
The skills are published publicly on wkentaro's GitHub profile, which hosts 374 public repositories. No licensing fee or paid tier is indicated in the manifest; several skills are marked disable-model-invocation, meaning they run as deterministic local operations rather than model calls.