← all publishers

wkentaro

@wkentaro source repo

16 published skills

  1. Core · wkentaro
    Provides non-interactive git-hunk mechanics for inspecting, splitting, committing, or explicitly discarding working-tree changes by Hunk ID or exact Repository path. Use when an agent needs hunk-level staging or commits without an interactive prompt.
    0
    installs
  2. Logical Commits · wkentaro
    Decides how to group, order, and describe working-tree changes as focused commits. Use when splitting mixed changes in a project with no commit conventions of its own.
    0
    installs
  3. Recommit · wkentaro bundle
    Reshape the commits a branch carries on top of its target branch into a clean, logical sequence without changing the final committed tree, then stop before any push. Use when a branch needs presentable history before review or merge, when iterative work left fixups, WIP commits, or interleaved refactors, when another skill needs clean commits, or when the user says "recommit" or asks to tidy the git history.
    0
    installs
  4. Hear Me · wkentaro bundle
    Checks voice-dictated requests with a readback and stays active in the current conversation until disabled.
    0
    installs
  5. Review Fix · wkentaro bundle
    Run configurable review-and-fix rounds on a working change until clean. Use for review-fix requests on uncommitted work, a branch, PR, or MR; use the Default Review Policy when no brief is supplied, accept an optional target or custom review brief, and leave supported fixes uncommitted.
    0
    installs
  6. Where Am I · wkentaro
    Render the open decision points of a task as an ASCII tree so the user can see where they are and what to answer next. Use when a task has branched into several pending choices, when the user asks "where am I?" / "what do I need to decide?" / "what's left to decide", or invokes /where-am-i. About task decisions, not git branch or working directory. Pure presentation; reads state from the conversation, persists nothing.
    0
    installs
  7. Clean Branch · wkentaro bundle
    Extract the essential feature changes from mixed committed and working-tree work into a new branch. Use when the user asks for a clean branch or a minimal feature branch; use recommit instead when only the commit history should change.
    0
    installs
  8. Ask Exemplar · wkentaro bundle
    Consult the accepted standard and strongest supported exemplars for a decision, plan, design, completed artifact, or diff, then return a source-grounded recommendation or evaluation.
    0
    installs
  9. Writing Code · wkentaro bundle
    Write or audit code against the house coding conventions. Use while writing code to settle a style call, or when auditing a change against the conventions.
    0
    installs
  10. Ask Me Again · wkentaro bundle
    Re-ask the assistant's pending questions as native interactive choices.
    0
    installs
  11. Harvest Sessions · wkentaro bundle
    Sweep recent Claude Code and Codex sessions into one reviewed secondbrain pull request.
    0
    installs
  12. Telegram Daily Log · wkentaro bundle
    Summarize today's verified accomplishments as a Telegram daily log and copy it to the clipboard.
    0
    installs
  13. Setup Github Labels · wkentaro bundle
    Apply and document the canonical GitHub issue and pull-request label set in a repository.
    0
    installs
  14. Sending Pull Request · wkentaro bundle
    Prepare a conventional branch, write or review a pull/merge request title and body, then push and create or update the GitHub PR. Use when work is ready for review or PR/MR copy needs drafting or review.
    0
    installs
  15. Writing Social Posts · wkentaro bundle
    Draft, sequence, and refine social posts — X threads and one-offs, Show HN submissions, LinkedIn posts. Covers launches, progress updates, technical notes, opinions, and amplifying someone else's work. Use when the user asks to write or refine a post, order a thread's posts and media, or check copy before it goes out.
    0
    installs
  16. Competitive Advantage · wkentaro bundle
    Moat analysis for products, companies, open-source projects, careers, and communities. Use when asking why something wins, whether an edge survives imitation or substitution (including AI commoditization), which advantages form a coherent strategy stack, or when another skill needs competitive-advantage vocabulary.
    0
    installs