Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Structured data research: search sources, extract structured data, archive raw sources, maintain canonical tracker pages, deduplicate. Parameterized via YAML recipes for investor updates, donations, company updates, or any email-to-structured-data pipeline.
Pick hot articles from GeekNews (news.hada.io) and write a TIL document for each. Select top articles by points and only process articles that do not duplicate existing documents.
Ingest links, articles, tweets, and ideas into the brain. Fetch content, save to brain with analysis, create author people page, and cross-link. Use when the user shares a link or says "read this", "save this", "think about this".
Brain-augmented web research. Sends brain context about a topic to Perplexity, which searches the web with citations and returns what is NEW vs what the brain already knows. Use for entity enrichment, current-state checks, deal monitoring, and freshness deltas. NOT for simple URL fetches (use web_fetch) or brain-only queries (use inbrain query).
把用户输入的任意词汇、概念、具体物品、器物、情绪、标题、人设、产品名、社会现象或抽象问题，返回它的父概念、实体父亲、上位概念、维基第一链接式上翻路径、哲学父亲和更深层来源。用户说“z-father-concept”“父亲.skills”“父亲 skill”“父概念”“父 xx”“这个词的父亲是谁”“上位概念”“给这个概念找爸爸”“任意词帮我找父概念”“维基第一链接”“一路翻到哲学”“更有趣更深刻地解释这个词”时必须使用。遇到具体物品时，优先给出具体物品层面的父亲或器物祖先，再像维基百科哲学现象那样逐层上翻到功能、欲望、文明问题和哲学母题。默认用中文输出，兼具分类学、器物谱系、隐喻、哲学联想和传播感。
Analyze a project's architecture end to end — extract domain language, map the tech stack, document frontend and backend patterns. Use when onboarding a new codebase or refreshing the architecture baseline.
On-demand pattern extraction from a specific GitHub codebase, given a focused query — "how does shadcn/ui implement the design system", "how does opencode use effect-ts", "how does base-ui handle composition" — when no pre-distilled static rule pack exists yet. Distills the generic pattern-extraction moves — classify the query before grepping (component / composition / state / effect / error / build / routing), grep before reading whole files, treat tests and examples/ as canonical intent, follow imports outward for the public surface, follow usages inward for variants, filter boilerplate / legacy / test scaffolding to surface load-bearing code, and capture findings to /knowledge/libraries/ for reuse. Dynamic light sibling of static code-atlas skills (opencode-ts, openai-codex-rust-patterns, nextjs-ppr-patterns). Triggers on "show me how <library> implements X", "find the <pattern> in <repo>", "distill <library>", and ad-hoc /distill-<library>-style invocations.
Library-documentation lookup methodology — API behavior, version-specific changes, idiomatic usage, or why production diverges from docs — independent of which library. Distills the generic navigation moves shared across libraries — classify the question before searching (changelog vs API reference vs idiom vs known-bug), check llms.txt before scraping HTML, pin to the user's version before reading reference pages, read changelog first for "did X change" questions, treat examples/ dirs as truth for idioms, and fall back to GitHub issues / status page / Discord when docs match but reality doesn't. Per-library topography lives in the shared /knowledge/libraries/ graph as thin reference data, alongside code-distill's section. Triggers on "where in <library> docs", "look this up in <library>", "did <library> change X", "docs say X but code does Y", and any prompt where the next move is to consult a library's official documentation.
Search and inspect local iOS 26 SDK documentation and Swift interfaces, especially SwiftUI and SwiftUICore. Use when Codex needs current iOS 26 SwiftUI APIs, Liquid Glass components, view modifiers, availability, signatures, deprecations, symbol docs, or SDK-only facts and should not rely on memory or public web docs being available.
Search and inspect local macOS 26 SDK documentation and Swift interfaces, especially SwiftUI, SwiftUICore, and AppKit. Use when Codex needs current macOS 26 APIs, Liquid Glass components, window, scene, menu, toolbar, AppKit bridging, availability, signatures, deprecations, symbol docs, or SDK-only facts and should not rely on memory or public web docs being available.