ワンクリックで
rileys-skills
rileys-skills には rbrown101010 から収集した 25 個の skills があり、リポジトリ単位の職業カバレッジとサイト内 skill 詳細ページを表示します。
このリポジトリの skills
Find paid promotion, sponsorship, brand deal, influencer campaign, creator partnership, affiliate, and paid collaboration opportunities in Riley's Gmail or email exports; research each brand/client; dedupe follow-ups; prioritize fit; and produce a Markdown table, document, or spreadsheet of brand leads with notes. Use when the user asks to scan recent email for brand deals, paid promo offers, sponsorship pitches, creator partnerships, or to turn those leads into a table/spreadsheet/doc.
Use Buffer's GraphQL API to inspect Buffer accounts, organizations, channels, queues, posts, daily limits, and to create Buffer Ideas, drafts, scheduled posts, queued posts, or media posts. Use when the user asks to draft, schedule, queue, publish, edit, delete, review, list, or manage social posts through Buffer, or asks what is connected in their Buffer account.
Build, sign, and install iOS apps on real devices using the Vibecode signing service. Use when the user wants to build an iOS app from source, sign an iOS app, install on their iPhone, register a device, set up Apple Developer auth, or work with the iOS build/sign/distribute pipeline. Also triggers for "test on device", "put this on my phone", "ship it to my iPhone", or any request to get a Swift/iOS app running on a real device.
Create polished Excalidraw diagrams from text descriptions. Use when the user asks for a diagram, flowchart, architecture diagram, decision tree, process flow, data flow, system overview, or similar visual explanation, or says "draw this", "diagram this", "visualize this", or "make a chart". Produces styled `.excalidraw` files with consistent colors and can export a shareable excalidraw.com URL.
Use when working with Firebase from the terminal: repairing or installing the Firebase CLI, authenticating, selecting projects, creating or managing Cloud Firestore databases, creating or querying Realtime Database instances, registering Firebase apps, or printing SDK config. Prefer this skill when the user asks to add Firebase to an app, create a Firebase database, inspect Firebase project resources, or run Firebase CLI commands safely.
Use when Codex needs to find images on the public internet and save them into a local directory, especially for brand assets, moodboards, research boards, reference pulls, or site-specific image collection. Supports SerpAPI Google Images search for query-driven discovery and Firecrawl scrape/map workflows for extracting images from specific pages or whole sites.
Build, prototype, deploy, preview, sign, and install mobile apps. Use when the user wants to make a mobile app, React Native app, iOS app, phone UI prototype, iPhone install, or mobile build using Vibecode. Covers Vibecode CLI mobile projects, local mobile design prototypes, and bundled iOS build/sign/install tooling.
Create or refine mobile app UI as a real, clickable local prototype, usually inside an iPhone-scaled frame with reusable tokens, primitives, and screen components. Use when the user wants mobile-first product design, a polished app concept, a browser preview they can click through locally, screen-to-screen flow exploration, or visual iteration on sizing, spacing, typography, and hierarchy for phones.
Use when work requires direct, full Notion API access outside the bundled Notion connector, including searching pages and databases, inspecting schemas, querying database rows, creating or updating pages, appending blocks, and sending raw Notion API requests with a locally configured integration token.
Use when editing an open Paper board through the local Paper MCP server at http://127.0.0.1:29979/mcp. Prefer this over Computer Use for Paper canvas reads/writes, image placement, HTML writes, node inspection, screenshots, and exports.
Generate, inspect, and vectorize SVG assets with the QuiverAI API. Use when Codex needs to create SVG logos, icons, illustrations, diagrams, or other vector graphics from text prompts, convert raster images such as PNG/JPEG/WebP into SVG, list Quiver models, or troubleshoot QuiverAI API requests using QUIVERAI_API_KEY.
Use when a user wants to search, export, organize, or automate Readwise or Reader data from Codex or another terminal agent, especially when browser auth should be avoided and an access token is available.
Connect Codex to the Remodex iPhone app. Use when the user wants to access Codex from their phone, pair or re-pair Remodex, bring the bridge up on macOS, inspect bridge status, reset pairing, resume the last mobile thread on desktop, or manage the local Remodex bridge lifecycle.
Use when creating or modifying Remotion videos that need HTML-in-canvas effects, the HtmlInCanvas component, Canvas 2D/WebGL/WebGPU post-processing, custom HTML-in-canvas transitions, or @remotion/web-renderer HTML-in-canvas rendering.
Remove backgrounds from images with remove.bg and save the cutout result locally. Use when Codex needs to cut out a subject from a local image file or image URL, produce a transparent PNG or WebP, export a flat JPG, or verify remove.bg account access before running image background removal.
Create, repair, validate, preview, and package Codex-compatible animated character spritesheets from character art, screenshots, generated images, or visual references. Use when a user wants to turn a reference image or concept into an animated sprite character, hatch a Codex pet, create a custom animated pet, or build an 8x9 atlas with transparent unused cells, row-by-row animation prompts, QA contact sheets, preview videos, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.
Use when the user says /todo, asks to update the shared todo list, or wants any project to track current work in Riley's shared todo document.
Fully control Typefully from Codex. Use this skill when asked to inspect or manage Typefully social sets, drafts, tags, queue, analytics, media uploads, or to call arbitrary Typefully API endpoints directly.
How to use the vibecode-cli command-line tool to manage vibecode.dev cloud projects, sandboxes, deployments, and AI coding agents. Use this skill whenever the user wants to create a web app, mobile app, or any cloud project. Also use it when the user mentions vibecode, vibecode-cli, vibecode.dev, cloud sandboxes, deploying to vibecode.run, sending prompts to a coding agent on a sandbox, or any project/sandbox/deployment management task. Trigger this skill when the user says things like 'build me an app', 'deploy my project', 'create a webapp', 'make a mobile app', 'spin up a sandbox', 'send this to the agent', 'ship it', or wants to manage anything on the vibecode.dev platform, even if they don't explicitly mention vibecode.
Use when the user wants a local video analyzed with the Gemini API, especially for transcript, summary, key visuals, timestamped scene notes, creator/content critique, or fast visual breakdowns from .mp4, .mov, .m4v, or .webm files. The skill uses a bundled helper that chooses inline upload for small videos and Gemini Files API for larger videos.
Write directly to Riley's local Neon-backed notebook app. Use when the user asks to save, add, append, update, or inspect notebook notes without using the UI.
Summarize the latest videos from a YouTube channel using available transcript and metadata tooling.
Use when the user wants YouTube research at speed: finding relevant videos in a niche, scanning channels, pulling transcripts, comparing competitors, or gathering source material from YouTube before summarizing trends, hooks, topics, or positioning. This skill uses a local helper script wired to SerpApi for YouTube search and Supadata for fast transcripts and channel data.
Generate YouTube thumbnail options from high-performing YouTube style references, a target person's images, and optional relevant logos/assets. Uses the local youtube-researcher SerpApi workflow to find/pull YouTube thumbnails, internet-image-puller to gather logos/images when needed, and OpenAI image generation/editing to create final 16:9 thumbnails. Defaults to 5 options when the user does not specify a count.
Create animated SVG-to-GIF diagrams for Google Docs and similar document workflows. Use when Codex needs to make animated flowcharts, process charts, timelines, decision trees, context maps, explainer diagrams, or doc-ready GIFs from editable SVG source, especially when the user wants clean slide-like charts embedded in a native Google Doc.