Get real-time stock quote with price, volume, change, market cap, and 52-week range for any ticker symbol. Use when user asks about current stock price, quote, or basic stock info.

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.

Decide which AI features to build, delay, shelve or kill, and whether each one gets better as models improve. Produces an AI Bet Memo (feature-by-feature verdicts, retest triggers, scaffolding ledger, moat and safety check) from a roadmap or idea list. Use for 'AI strategy', 'AI roadmap', 'what should we build with AI', 'will the next model make this obsolete', 'build vs wait for the model', 'will OpenAI/Anthropic build this', 'agent or chatbot', 'is this feature worth shipping'. Draws on 118 Lenny's Podcast guests incl. Nick Turley, Kevin Weil and Dianne Penn.

Upgrade any Pulumi provider to a newer version and reconcile the resulting diff. Use when users want to upgrade or update a provider (including editing package.json, requirements.txt, pyproject.toml, go.mod, or Pulumi.yaml to bump a provider SDK), check for breaking changes before or during an upgrade, fix resources that broke after a provider upgrade, or resolve unexpected replacements, creates, or deletes in a post-upgrade preview, including pulumi-gcp v10 errors such as a missing gcp.notebooks or gcp.iap.Brand type or a required secretDataWoVersion. Applies to all providers (aws, azure-native, gcp, kubernetes, aws-native, cloudflare, datadog, etc.) — not just Tier 1. Do NOT use for querying which stacks use what package versions; use skill `package-usage` for cross-stack audits. Do NOT use for general infrastructure tasks.

Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and CommunityToolkit components. Use when creating a brand new app, preparing a machine for WinUI, reviewing, refactoring, planning, troubleshooting, environment-checking, or setting up WinUI 3 XAML, controls, navigation, windowing, theming, accessibility, responsiveness, performance, deployment, or related Windows app design and development work.

Use when writing, debugging, or explaining Strudel live-coding music patterns — mini-notation syntax, pattern functions (fast/slow/every/off/stack), synth/sample selection, audio effects, scale/chord/voicing API, or EDM production recipes. Triggers: "write a Strudel pattern", "how do I make a bassline in Strudel", "what does .every() do", "strudel drum beat", "strudel chord voicing", any Strudel code question.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Answer questions about the GM Farcaster podcast archive (Farcaster, Base, and the wider crypto-social ecosystem) using the paid Warpee Knowledge API. Use this when the user asks what the GM Farcaster hosts or guests have said on a topic, wants an episode summary, asks about casts featured on the show, mentions of a person/project, or episode metadata (dates, hosts, guests). Each query is a paid x402 request (~$0.005 USDC on Base).

Add a note to the current recording or annotate a past meeting. Use whenever the user says "note that", "remember this", "mark this as important", "add a note about", "annotate the meeting", or wants to capture a thought during or after a recording. Plain text input — no markdown needed.

Fetch unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member. Use when asked to "find PRs I need to review", "show my review requests", "what needs my review", "fetch GitHub review requests", or "check team review queue".

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.

Use when estimating relative immune cell infiltration from a bulk expression matrix with a CIBERSORT-style nu-SVR deconvolution workflow based on an LM22 signature matrix, comparing one case group against one control group, and generating structured tables plus immune-fraction plots. NOT for single-cell RNA-seq, spatial data, clinical diagnosis, or workflows that require the original hosted CIBERSORT web service.

Use this skill when the user asks for online movie or TV reference metadata, Wikipedia/TMDB/TVDB lookups, person movie/TV credits, release years, summaries, external IDs, source URLs, or trailers after Plex is insufficient or when the question is not about local availability. This skill uses Wikipedia always and optional configured TMDB/TVDB APIs through bundled read-only scripts. Do not use this skill to claim that a title exists in Plex, scrape IMDb, stream or download video, aggregate reviews, or edit metadata.

Use when working with a local HashiCorp Vault instance that backs OpenClaw secrets: storing, retrieving, deleting, checking health, unsealing, managing a local service or container, or troubleshooting OpenClaw secret access.

Use this skill when the user asks whether movies, TV shows, seasons, or episodes are available in the configured Plex library; wants to search Plex video metadata; asks about watched state, years, editions, library locations, Plex GUIDs, or local movie/TV availability. This skill uses read-only Plex HTTP API requests through bundled scripts. Do not use this skill for online reference metadata, trailers, downloads, streaming playback control, metadata edits, library refreshes, or music library questions.

当用户要求 AI 直接操作他的 macOS 桌面时触发：打开某个 App、点击某个按钮、填写窗口里的表单、读取当前屏幕内容、自动化本地 GUI 流程。典型说法"帮我在访达里…"、"帮我在某 App 里点一下…"、"看看我屏幕上显示的是什么"。**仅在 OpenLoaf Desktop（macOS）中可用**；非桌面端会返回 desktop-only 错误，应改用 `BrowserAct` 或让用户自己操作。**不用于**：网页内交互（→ `browser-ops-skill`）、本地文件读写（→ `Read`/`Edit`/`Write`）。

Triggered when the user asks for page-level interaction with a specific webpage: login, form filling, button clicks, pagination scraping, screenshots, downloading page images, handling CAPTCHAs or anti-bot measures, accessing SPA dynamic content; also used as a fallback when WebFetch returns an empty shell or gets blocked. Typical phrasing: "log me into X then scrape Y", "take a screenshot". **Not for**: factual questions or "what is xx" (→ `WebSearch`), or simply reading static webpage text (try `WebFetch` first).

Triggers when the user wants to create, edit, improve, or debug an OpenLoaf custom Skill. Typical phrasings: "help me create a skill", "build a new skill", "turn what we just did into a skill", "write a skill that auto-XX", "tweak this skill", "why isn't this skill triggering", "edit my custom skill", "add a global skill", "add a skill to the current project". Any create / modify / tune request touching a `SKILL.md` under `.openloaf/skills/` should load this skill. Also applies when the user wants to understand the skill format, troubleshoot triggering issues, or solidify a conversation workflow into a reusable capability. Not for: modifying built-in skills (e.g. file-ops, email-ops) — those are read-only capabilities shipped with the platform.

Guides RESTful API endpoint design, resource naming, status code selection, pagination structure, versioning strategy, and error response schemas. Use when the user asks about designing APIs, defining HTTP endpoints, REST conventions, API versioning, request/response formats, URL structure, OpenAPI/Swagger specs, or reviewing an existing API contract for best practices.

Generate and validate shareable PowerShell or Bash command references from an explicitly supplied, non-sensitive command dump. Use when maintaining agent-readable command documentation, validating its JSON contract, or regenerating Markdown/JSON/YAML references without committing personal command histories, credentials, hostnames, or private filesystem paths.