hamzafarooq/multi-agent-course

hamzafarooq/multi-agent-course

Skill Claude Code

Write unit tests for any function — happy path, edge cases, and error cases. Use when the user asks for tests, wants to add test coverage, or is practicing TDD.

hamzafarooq/multi-agent-course

Skill Claude Code

Research emerging trends in a market or technology space. Returns signal vs noise breakdown with evidence. Use when the user asks what's changing in a market, what trends to watch, or what's coming next.

hamzafarooq/multi-agent-course

Skill Claude Code

UI/UX design intelligence. 67 styles, 96 palettes, 57 font pairings, 25 charts, 13 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing…

hamzafarooq/multi-agent-course

Skill Claude Code

Converts feature ideas or rough bullets into user stories with acceptance criteria. Use when asked to write user stories or break down a feature.

hamzafarooq/multi-agent-course

Skill Claude Code

End-of-session code review — checks for unused imports, console.logs, missing error handling, hardcoded values, and edge cases before committing. Use when the user is done coding and wants a final pass before committing or shipping.

hamzafarooq/multi-agent-course

Skill Claude Code

Analyze writing samples and extract the patterns that define the user's voice. Use when the user wants to capture their writing style, train Claude on how they write, or make future writing sound like them.

hamzafarooq/multi-agent-course

Skill Claude Code

Run a quick 15-minute pre-class review that recaps the previous module and previews the upcoming one. Use when the learner says they have class soon, wants to prepare, asks for a refresher or warm-up, or asks "what did we cover" / "what's next" right before a session.

hamzafarooq/multi-agent-course

Skill Claude Code

Takes one or more YouTube video URLs, visits each page using Brave MCP, extracts chapters/timestamps, key moments, and top comments, and produces a structured highlight report. Use when the user wants to find the best parts of a video without watching the whole thing.

hamzafarooq/multi-agent-course

Skill Claude Code

Uses Brave MCP to search YouTube and find relevant videos on a topic. Use when asked to find, research, or recommend YouTube videos about a subject.

hamzafarooq/multi-agent-course

Skill Claude Code

Generate a Product Evaluation report (.md, optionally PDF) for the FDE Assignment 1 Live Translate product. Runs the automated rubric + benchmark, then does a real live-website test (e.g. homedepot.com), and writes PRODUCTEVAL.md. Use when the student wants to evaluate their translation product, produce their…

hamzafarooq/multi-agent-course

Skill Claude Code

Generate a Product Evaluation report (.md, optionally PDF) for FDE Assignment 3 — Moment Search at Scale. Runs the automated rubric + benchmark (incl. --resilience), then does a real cross-source test (ingest a video + a research paper + a deck the student doesn't control and verify one query cites all three)…

hamzafarooq/multi-agent-course

Skill Claude CodeCodex

You are a competitor-research assistant. Follow this procedure for every research request, regardless of domain.

hamzafarooq/multi-agent-course

Skill Claude Code

Run the six LUMINA gates against a deployed (or local) gateway and write the report.json that the provided UI renders at /evals. Use when the student says they are ready to submit, wants to run the eval, asks for their score, or says "eval my LUMINA".

hamzafarooq/multi-agent-course

Skill Claude Code

Break a one-line problem or product idea ("build a Perplexity clone", "a voice receptionist for a clinic") into a complete specification pack a coding agent can build from and be graded against - declared thresholds in JSON, a contract, an exhaustive SPEC.md, AGENTS.md, TECHNICAL.md, a short PRD.md with no numbers…