Claude Skills by sasamuku

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use...

Triage PR review comments and CI failures. Default mode categorizes and presents findings for user decision; --auto mode autonomously fixes, commits, pushes, replies, re-kicks Devin Review (/devin review) after pushing fixes when Devin is reviewing the PR, and self-starts a 5-minute recurring loop (/loop 5m /babysit --auto) until the PR is mergeable or merged.

Interactive coaching skill for polishing technical articles, tech blogs, and personal engineering essays. Starts from the user's rough draft and guides the article through meta-review, rewrites toward natural human-sounding prose, removal of clickbait/over-claims, title and description redesign, footnote curation, and commit granularity management. MUST trigger whenever the user mentions writing or editing a technical article in mdx/md, asks to review a draft, complains the writing feels AI-g...

Commit changes, push to remote, and create a draft pull request

Commit changes and push to remote repository

Creates logical, well-structured git commits following Conventional Commits. Use when user mentions commit, committing, saving changes, or asks to organize changes into commits.

Compress, reduce, optimize, or shrink documentation files. Use when docs are verbose, redundant, or need consolidation for clarity.

Copies `claude -r <session-id> --fork-session` for the current session to the clipboard. Use when the user wants to fork the current session into a new branch from another terminal, or asks to copy the fork command, session id, or `/fork` command.

General guidelines for creating GitHub issues

Review the local diff with flat-perspective sub-agents, fix findings in a loop, then create a PR via the create-pr skill once the review is clean

Create a GitHub pull request using gh CLI, following the repository's own PR template and language conventions. After creation, autonomously fixes CI failures until green, then presents review-comment triage for user decision (HITL)

.claude/rules/ 配下のルールファイル (*.md) を新規作成・編集するときに、適切なメカニズム選択と paths スコープを保証する。ルールを書く前・書いた後に必ず適用する。

Create a new Claude Code skill with best practices. Use when user wants to create a skill, add a SKILL.md, or extend Claude's capabilities.

Create a sub-issue linked to a parent GitHub issue, honoring repository-specific issue conventions

Delegate a task to a worktree-worker agent running in an isolated git worktree. Use this skill when you want a sub-agent to implement code changes, fix bugs, or investigate errors in a separate worktree — keeping the main session clean. Trigger on phrases like "delegate this to a worker", "fix this in a worktree", "have a worker handle this", or when the user wants code changes done in isolation.

Generic thinking protocol for deriving optimal solutions through iterative self-checking. Invoke BEFORE searching within the given problem space whenever the user asks for advice, judgment, evaluation, or choice. Reframes the problem, generates options, evaluates trade-offs, runs a self-answer check (does this answer the user's actual question at the right granularity, reach upstream, match expectations, offer non-obvious value?), and loops back to upstream tracing or same-level reframing if ...

地頭のよい知的好奇心が旺盛な 10 歳向けの図解説明。/eli10 <topic>、または「シンプルだが幼稚すぎない」説明 (本物の仕組み・正しい用語) を求められたときに使う。

Fetch and execute mizchi's empirical-prompt-tuning skill at runtime. Use when evaluating or iteratively refining an agent-facing prompt (skill / slash command / task prompt / CLAUDE.md section / code-gen prompt) by dispatching an unbiased subagent, then improving until metrics plateau. Trigger right after creating or heavily revising such a prompt, or when agent misbehavior is suspected to stem from ambiguity in the instruction.

Switch the current session into an existing git worktree (e.g. one created by /delegate-worker or `wt add`). Use when the user wants to enter, cd into, or follow a worktree — trigger on phrases like "enter the worktree", "worktree に入って", "ワーカーの worktree に移動して".

Exit the current worktree session and return to the original working directory. Use when the user wants to leave a worktree entered via /enter-worktree or /delegate-worker — trigger on phrases like "exit the worktree", "worktree から出て", "元のディレクトリに戻って".

Fetches a GitHub issue, implements the fix, and verifies it. Use when user wants to fix an issue, implement issue changes, or resolve a bug.

Creates a fixup commit and performs autosquash rebase

計画や設計について、ユーザーを徹底的に問い詰めて一緒に詰める。実装・着手の前に計画をストレステストしたいとき、または「詰めて」「グリルして」「問い詰めて」「ツッコんで」「設計レビューして」「ほんとうにこれでいい?」などのトリガー表現が出たときに必ず使う。

Generate a HANDOVER.md file summarizing the current session's work. Use at the end of a session to preserve context for the next session.

Fully automated pipeline from an approved plan to a green PR. Delegates implementation to a worktree-worker, creates the PR, then hands off to /babysit --auto until CI is green and the PR is mergeable.

Merges a branch into current branch with conflict resolution. Use when user wants to merge, combine branches, or integrate changes.

Orchestrate Epic issue as team leader. Delegate sub-issues to member agents in isolated worktrees. Members run in background and communicate via SendMessage.

Create or update the execution plan for a GitHub issue and always sync it to the issue comment. Reads the issue deeply (epic/siblings/PRs) on first run; reflects conversation decisions and sub-issue progress on updates.

ドキュメントやコードコメントから、読者にとって価値の無い記述を取り除いて最終状態だけにする。作業の過程・暫定の注記・自明な説明が残っているときに使う。

Pulls latest changes from remote with conflict resolution. Use when user wants to pull, fetch changes, or update from remote.

Pushes commits to remote repository. Use when user wants to push, upload commits, or send changes to remote.

Fetch a GitHub issue with its sub-issues, walk up to the parent Epic, list sibling issues under that Epic, fetch the body of each sibling issue, attach the implementing PR for each closed sibling with body and diff summary, gather related code, and present as a Japanese summary so the reader can grasp the whole task context including the actual contents of siblings and their PRs

Rebases current branch onto target with conflict resolution. Use when user wants to rebase, update branch base, or linearize history.

Review local code changes against main branch

Run the review-pr workflow on Codex instead of Claude — hand the PR number and the review-pr procedure to Codex via the codex:rescue subagent, then surface Codex's integrated review summary. Use when the user wants a PR reviewed by Codex / GPT, or asks to "review this PR with Codex".

Comprehensive PR review with parallel multi-agent analysis, optional inline comment posting

Review and merge renovate PRs with automerge configuration updates

Investigate Sentry issues by URL. Use when user provides a Sentry issue URL and wants to understand the error cause, analyze stack traces, and find the root cause in the codebase.

Review all changes (commits and working changes) and organize into appropriate commit granularity

Stash changes, rebase onto latest main, and reapply stash

Summarize GitHub Epic issue with sub-issues and related PRs. Use when reviewing epic progress or getting implementation overview.

Understand current work status and project context. Use when starting work, resuming a session, or checking git state (modified files, staged changes, current branch).

Updates the user's global Claude Code instructions file (~/.claude/CLAUDE.md, which is a symlink into the dotfiles repo). Use ONLY when the user explicitly asks to update, edit, add to, or remove from the global CLAUDE.md / global rules / global Claude instructions — typically while working in a different project where ~/.claude/CLAUDE.md isn't the primary editing target. Do NOT trigger for project-local CLAUDE.md files.

Create a new git worktree via `wt add` (firing .wt_hook.sh) and move the current session into it so the MAIN agent works there directly — no sub-agent. Use when the session started on main/master and the user wants to do the task themselves in an isolated worktree. Trigger on phrases like "worktree を作ってそこで作業して", "このセッションで worktree に入って直接やって", "work in a worktree yourself". For delegating to a background sub-agent instead, use /delegate-worker.