yamadashy

Who yamadashy (Kazuki Yamada) is — a compact profile card to load when an agent needs to know the author's identity, background, or work. Triggers on: 'who is yamadashy', 'who am I', 'about the author/maintainer', 'introduce yamadashy', or when a task needs the user's bio, main products, or links.

Use this skill to delegate tasks to OpenAI Codex CLI as a sub-agent, including image generation/editing with GPT-Image-2. Triggers on: 'ask codex', 'run it with codex', 'codex exec', 'generate an image with codex', or when the user explicitly wants to use the Codex CLI for a task.

Propose the tasks on a repository that only a frontier-tier model can execute — the work the model one tier below or a routine engineer would fail at or do shallowly. The deliverable is a numbered pitch list ('I can do this here, and nothing cheaper can') for the human to greenlight. Triggers on: 'what could only you do in this repo', 'only-you', 'find frontier-worthy tasks', 'what work is worth handing to you', or when the user wants to know what to give the most capable model available.

Safely batch-merge Renovate's dependency-update PRs in the current repo. Lists open Renovate PRs and runs each through fixed safety gates — author is the Renovate bot with GitHub-verified (signed) commits, the update is non-major, the diff is confined to dependency files and clears a supply-chain scan, the new release is not brand-new (cooldown), CI is green, and the PR is mergeable — then auto-approves and merges only the PRs that clear every gate, holding the rest for manual review. Triggers on: 'merge the renovate PRs', 'merge dependency updates', 'handle renovate PRs', 'process renovate', 'update dependencies via renovate'.

日本語の文章を人間が読みやすいリズムに整えるスキル。黙読時に脳内で文を「声に乗せて」処理する仕組み（内在的韻律・サブボーカライゼーション）を前提に、音韻の紛らわしさ・韻律と統語の整合・文の単調さを点検して直す。日本語の文章を書く・推敲する・レビューするとき、あるいは「読みにくい」「リズムが悪い」「硬い」「読点の打ち方」「文末が単調」といった指摘や要望があったときは、明示的に「リズムを直して」と言われていなくても積極的に使うこと。コード・表・箇条書きが主体のドキュメントには使わない。

Vet a GitHub pull request and its author for supply-chain risk before reviewing or merging. Treats all PR/author text as untrusted to resist prompt-injection of the reviewing agent, investigates the author's account reputation, scans the PR diff for malicious patterns (obfuscation, install hooks, native-build/binding.gyp exec, credential harvesting, Trojan Source, hidden network egress, guard removal), and checks the change against current supply-chain attack techniques. Triggers on: 'vet this PR', 'vet this contributor', 'check this PR author', 'is this PR safe', 'supply chain risk', 'can we trust this PR', or before merging a fork PR from an unfamiliar author.

Iterative Claude review-and-fix loop

Drive a pull request to a mergeable state — address review feedback AND fix failing CI checks end to end. Fetch review comments and CI status, apply code fixes, verify locally, commit, push, watch CI back to green, then reply to and resolve threads. Triggers on: 'address PR feedback', 'fix the PR', 'fix CI', 'CI is red', 'resolve review comments', or pointing at a PR with failing checks or unresolved comments.

Fetches an arXiv paper — metadata (title, authors, abstract) via WebFetch on the abs page, plus the full PDF via curl on arxiv.org/pdf and structured extraction by pdfvision. Use when the URL is in the form arxiv.org/abs/{paper_id}.

Reads GitHub via the gh CLI — repo metadata / README / file tree, issues with comments and timeline, pull requests (diff, files, inline comments, GraphQL review threads with isResolved / isOutdated), discussions (GraphQL), code (file contents and code search), and releases (with tarball / zipball fallback). Routes by URL shape into references/{topic}.md so only the relevant command sheet is loaded. Use when the URL is on github.com.

Fetches MDN Web Docs as raw Markdown by mapping the developer.mozilla.org URL to its source file in mdn/content (en-US) or mdn/translated-content (other locales) on GitHub and curl-ing the raw blob. Cleaner and more compact than rendering the SPA page; falls back to WebFetch on the original URL when the path mapping 404s. Use when the URL is on developer.mozilla.org.

Extracts text (with original line breaks), metadata, per-page character / image density, and optional rendered PNGs from a PDF using pdfvision. Falls back to --render on pages whose density Overview shows low text coverage so multimodal models can read raster slides. Use when the URL ends in .pdf, the user supplies a local PDF path, or another readable-* skill produced a PDF that still needs structured extraction.

Fetches a SpeakerDeck slide deck by extracting the public PDF URL from the slide page (WebFetch), downloading it via curl, and running pdfvision — typically with --render on image-heavy pages so the slides can be read visually. Use when the URL is in the form speakerdeck.com/{user}/{slug}.

Reads web platform specifications via WebFetch — uses the multipage HTML variant for the WHATWG HTML spec, anchor-targeted section reads for W3C TR documents and TC39 / ECMAScript. Returns the relevant section rather than the whole spec, since these documents are too large for a single fetch. Use when the URL is on *.spec.whatwg.org, w3.org/TR/, or tc39.es.

Fetches a Stack Overflow question body and its answers via the Stack Exchange API (api.stackexchange.com/2.3 with the withbody filter, gzip-compressed). Anonymous quota is 300 req/day per IP; honor the response backoff field. Surface the question URL when displaying content (CC BY-SA attribution). Use when the URL is in the form stackoverflow.com/questions/{id}/...

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Analyze or explore a codebase (remote or local repository) by packing it with the Repomix CLI, then reading and searching the generated output. Use when the user wants a high-level understanding of an unfamiliar or large repo, not a targeted edit. Trigger for: - Structure/overview: "analyze this repo", "what's the structure", "explain this codebase", "what's in vercel/next.js" - Pattern discovery across many files: "find all auth code", "where are the API endpoints", "show me all React components" - Metrics: "how many files/tokens", "largest files", "TypeScript vs JavaScript ratio" - Remote repos: any github.com URL or "owner/repo" the user wants explored DO NOT trigger for: - Editing, refactoring, or writing code in the current project - Reading or searching a known file/path in the local project (use Read or grep directly) - Single-symbol lookups in the local project answerable with one grep - Git operations, running tests, builds, or installs

Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.

Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.

Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.

Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

Use this skill when working on the Repomix documentation website in `website/` directory, including VitePress configuration, multi-language content, or translation workflows.

arXiv 論文の内容を取得・要約するスキル。URL が arxiv.org/abs/{論文ID} 形式の場合に使用。PDF をダウンロードして Read ツールで読み取る。

GitHub リポジトリの情報を取得・要約するスキル。URL が github.com/{owner}/{repo} 形式の場合に使用。gh コマンドと DeepWiki MCP を活用してリポジトリの詳細情報を取得する。

SpeakerDeck スライドの内容を取得・要約するスキル。URL が speakerdeck.com/{user}/{slug} 形式の場合に使用。PDF をダウンロードして Read ツールで読み取る。

Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'clean up memories'. Also use proactively when discovering valuable findings worth preserving.

Use this skill when the user wants to analyze or explore a codebase (remote repository or local repository) using Repomix. Triggers on: 'analyze this repo', 'explore codebase', 'what's the structure', 'find patterns in repo', 'how many files/tokens'. Runs repomix CLI to pack repositories, then analyzes the output.

Extract text, metadata, per-page density signals, layout, image boxes, OCR, and page PNGs from a PDF via the pdfvision CLI. Use when the input is a `.pdf` URL, a local PDF path, or a PDF another agent skill produced. Triggers on: 'read this pdf', 'extract from <file>.pdf', '.pdf', 'scan / slide / paper / form contents'.

Persistent file-based notebook (.carnet/<category>/<slug>.md, auto-expiring after 30 days of disuse) for AI agents and humans. Use whenever saving, recalling, or organizing notes across sessions — IMPLICIT cues include the user recapping a tricky fix worth not redoing, asking 'what did we decide about X', handing off mid-task state, or setting something aside for now. Use PROACTIVELY when you discover something a future agent would otherwise re-derive from scratch — a non-obvious library gotcha, a hard-won fix, a rejected design alternative likely to be re-proposed, an in-progress state worth resuming. SKIP for: time-bound TODOs that need to nag (TodoWrite/Issues surface back, carnet does not), credentials/secrets (don't put them on disk), context already in a commit/PR/ADR (no double-bookkeeping). When in doubt, prefer a brief note over losing context: unused notes expire automatically.