hamzafarooq/multi-agent-course

hamzafarooq/multi-agent-course

Skill Claude Code

Write a LinkedIn post from a topic, idea, or article URL. Matches the user's voice with a strong hook, punchy body, and clear CTA. Use when the user wants to post on LinkedIn or turn something into a LinkedIn post.

hamzafarooq/multi-agent-course

Skill Claude Code

Estimate TAM, SAM, and SOM for any market from a product description. Use when the user asks about market size, opportunity sizing, or how big a market is.

hamzafarooq/multi-agent-course

Skill Claude Code

Convert any markdown file to a clean PDF. Use when asked to make a PDF from a .md file, export a document, or convert markdown to PDF.

hamzafarooq/multi-agent-course

Skill Claude Code

Extract action items, decisions, risks, and open questions from raw meeting notes or transcripts. Use when the user pastes meeting notes or asks what came out of a meeting.

hamzafarooq/multi-agent-course

Skill Claude Code

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

hamzafarooq/multi-agent-course

Skill Claude Code

Generate 5–7 unique angles for a newsletter issue using SCAMPER and contrarian frameworks. Use when the user wants newsletter topic ideas, doesn't know what to write about, or wants fresh angles on a subject.

hamzafarooq/multi-agent-course

Skill Claude Code

Turn a goal statement into well-formed OKRs — 3 Objectives each with 3 measurable Key Results. Use when the user wants to write OKRs, quarterly goals, or structured targets for their team.

hamzafarooq/multi-agent-course

Skill Claude Code

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

hamzafarooq/multi-agent-course

Skill Claude Code

Generates a structured PRD from a feature description or brief. Use when asked to write, draft, or create a PRD.

hamzafarooq/multi-agent-course

Skill Claude Code

Write a structured client or internal proposal from a brief. Covers problem, solution, timeline, investment, and next steps. Use when the user needs to send a proposal, pitch a project, or document a plan for approval.

hamzafarooq/multi-agent-course

Skill Claude Code

Test the learner's understanding of a module or topic and track weak spots. Use when the learner asks to be quizzed, tested, checked, or wants to know if they're ready to move on. Never reveals answers before the learner attempts them.

hamzafarooq/multi-agent-course

Skill Claude Code

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

hamzafarooq/multi-agent-course

Skill Claude Code

Generate a sprint retrospective document from raw notes or observations. Returns what worked, what didn't, and 3 concrete action items with owners. Use when the user wants to run or document a sprint retro.

hamzafarooq/multi-agent-course

Skill Claude Code

Analyze a draft or URL for SEO gaps, then rewrite the title, meta description, and headers to improve search visibility without killing the voice. Use when the user wants to optimize content for search.

hamzafarooq/multi-agent-course

Skill Claude Code

Evaluate any Skill by scoring its output against ground truth. Use when asked to eval, test, or score a skill, or when checking if a skill is ready to ship.

hamzafarooq/multi-agent-course

Skill Claude Code

Turn an Anthropic Agent Skill into a runnable standalone Python app built on the Anthropic SDK. Use this whenever the user wants to "publish", "export", "package", or "turn into an app" a skill, or asks for the "SDK version" / "API version" / "standalone version" of a skill, or wants a script that loads a SKILL.md and…

hamzafarooq/multi-agent-course

Skill Claude Code

Generate a complete HTML slide deck from a topic, bullet list, or document. McKinsey-style — one insight per slide, no filler. Use when the user wants to build a presentation, pitch deck, or teaching slide deck.

hamzafarooq/multi-agent-course

Skill Claude Code

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

hamzafarooq/multi-agent-course

Skill Claude Code

Turn a list of user stories or backlog items into a prioritized 2-week sprint plan with effort estimates and capacity check. Use when the user wants to plan a sprint, prioritize stories, or figure out what fits in two weeks.

hamzafarooq/multi-agent-course

Skill Claude Code

Write a concise weekly or monthly stakeholder update from raw notes. Covers progress, blockers, decisions needed, and next steps. Use when the user needs to write an update for their manager, leadership, or cross-functional partners.

hamzafarooq/multi-agent-course

Skill Claude Code

Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

hamzafarooq/multi-agent-course

Skill Claude Code

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

hamzafarooq/multi-agent-course

Skill Claude Code

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

hamzafarooq/multi-agent-course

Skill Claude Code

Run an interactive lesson for one course module. Use when the learner asks to learn, start, study, or be taught a module or topic, or to continue where they left off. Walks through the module's lesson.md one concept at a time with comprehension checks.