AI Agent Workflow Collection

Add notes and learnings to Tim's work knowledge base at Spotify from any Claude Code…

Analyzes brands, products, apps, and digital presences for positioning, narrative, emotional framing, identity signals, and cultural meaning—not feature lists alone. Use when the user asks for brand analysis, positioning or narrative analysis, perception study, tone-of-voice audit, framing review, or deep analysis of a named brand, product, company, app, or website URL.

Design API contracts, data models, and UI/UX specifications. Use for API design, data modeling, UI wireframes, and design systems.

You are an implementer of GitHub issues. You are an Agent who has been assigned an issue to work on.

Uses GitHub for project management in the current repository via gh CLI — issues, labels, milestones, projects, and pull requests. Use when planning work, decomposing tasks, creating or updating issues, managing milestones, or operating GitHub Projects.

Universal project workflow — brainstorming, documentation, task planning, and implementation. Works with GitHub and GitLab. Use when starting a new project, discussing a feature, updating project docs, decomposing work into issues, or implementing tasks from a backlog. Triggers on "project workflow", "start project", "update docs", "create issues", "implement task", "take issue", "work on feature", or when the user wants end-to-end project support at any stage.

Interacts with Vikunja (self-hosted or cloud) via its REST API to manage tasks, projects, labels, and related resources. Uses VIKUNJABASEURL and VIKUNJATOKEN from the process environment; fetches /api/v1/docs.json only when the conversation lacks enough API detail for the request. On failed requests, diagnoses missing config and points to persistent (global) env setup. Use when the user mentions Vikunja, wants task/project CRUD, imports, or API operations against their Vikunja instance.

Audits a public website for search crawlability, structured data, sitemaps, robots.txt, optional llms.txt, and major AI crawler policies; produces an evidence-backed report and only applies vendor-confirmed remediation guidance. Use when the user wants an AI/search discoverability audit, llms.txt review, robots.txt for GPTBot/OAI-SearchBot/Claude/Perplexity, sitemap quality, or “make my site work well with AI search + Google/Bing”.

Fetches a YouTube video transcript and returns the text to the user by default. Present the answer like a simple UI — short and substantive; avoid flags, paths, and stack talk unless something breaks or the user asks. Use when the user provides a YouTube link or video ID and wants the transcript; optional save-to-file or Add Knowledge. Triggers on "get transcript", "download transcript", "YouTube transcript", or a YouTube URL plus transcript intent.