yamadashy

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.

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.

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.

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。

Extract text, metadata, per-page density signals, structural layout, image bounding boxes, optional OCR, and rendered page PNGs from a PDF using the pdfvision CLI. Use when the input is a `.pdf` URL, a local PDF path, or another agent skill produced a PDF that still needs structured extraction. 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) shared by AI agents and humans. Use whenever the conversation involves saving, recalling, or organizing notes across sessions — including IMPLICIT cues like the user describing a tricky fix worth not redoing, asking 'what did we decide about X', handing off a mid-task state to be picked up later, or wanting to set something aside and forget it for now. Use PROACTIVELY (without being asked) whenever you discover something a future agent (or future-you) would otherwise have to re-derive from scratch — a non-obvious library gotcha, a fix that took real effort to find, a rejected design alternative that would otherwise be re-proposed, an in-progress state worth resuming. When in doubt, prefer a brief note over losing context: unused notes expire automatically.