Explorar skills

Use PROACTIVELY when the user invokes /clarify <slug> or when a spec has Open questions and the user wants to resolve them. Reads specs/<slug>/spec.md §6, asks targeted questions, integrates answers, bumps Status to `clarified`.

Use when an implementation plan should be reviewed by whichever supported backend is available, or when the backend should be chosen dynamically.

Um guia para projetar, construir e auditar ferramentas CLI para uso por agentes de IA. Ele fornece modelos iniciais, idiomatismos de implementação específicos da linguagem e um breve guia de introdução, complementando `anc` e `agentnative-spec`.

Install and operate a portable OpenAI Symphony + Linear orchestration setup in any Git repository. Use when the user wants a one-command local Symphony runner, a reusable WORKFLOW template, background launch scripts, or a Codex wrapper that restarts Symphony automatically when reopening the CLI.

Submission-grade Nature/high-impact journal figure workflow for Python or R. Use whenever the user asks to create, revise, audit, or polish manuscript figures, multi-panel scientific plots, figures4papers-style matplotlib plots, or journal-ready SVG/PDF/TIFF outputs, especially for Nature-family or other high-impact journals. Before plotting, define the figure's conclusion, evidence logic, export

Setup, configure, audit, and modernize Vitest testing in projects. Use when creating new test configs, auditing existing Vitest implementations for v4.0+ best practices, fixing deprecated patterns, migrating from Jest, or configuring test environments (Node.js, browser, monorepo). Checks for breaking changes, outdated configs, missing coverage settings, and performance issues. Covers browser mode,

深度阅读非技术素材，输出完整研究文章。四阶段流水线：捕获→精读→综合→撰写。素材类型：论文（arxiv、期刊）、书籍章节、新闻报道、长文、访谈记录、行业报告、政策文件。一个 skill 从头到尾完成，不依赖外部 skill。当用户想要：深度阅读论文、研究非技术主题、把多份素材综合成文章、对论文做深度解析、把报告整理成研究文章、综合分析多份素材、理解一篇论文的核心思想并写成文章、深度研究某个话题（社会现象、商业模式、理论框架等非代码主题）时，都应该触发。即使用户只说"分析这篇论文"或"帮我读一下这个"——只要素材不是代码或技术项目，就应该用 deep-read 而不是其他 skill。用户分享论文 PDF/URL、arxiv 链接、报告文件并要求分析时，一律触发。不触发：GitHub URL / 源码分析 / 技术框架深度解析 → source-dive；纯 URL 抓取不分析 → read

Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data, supplementary datasets, DataCite-style dataset references, FAIR metadata for acad

Use when checking whether a web app, localhost build, demo URL, landing page, AI-generated frontend, or GitHub project actually works in the browser before shipping. Trigger this whenever the user asks to test, verify, inspect, QA, launch, debug UI, check console errors, check mobile responsiveness, or validate a project in a real browser.

Use when users want to commit changes, improve a commit message, split mixed changes into logical commits, clean up recent local history, remove accidentally committed files, squash or reword recent local commits, or generally sort out a local Git mess before review or a PR.

Leave the current room without leaving the mesh. Host parts → room gist deleted, joiners reconnect into a new election. Joiner parts → host's gist stays open for others. Local identity preserved.

Set up a personal Slack bot — create the app, configure scopes, store the token, verify the connection.