mercury-agent-skills

Generate a 15-30 second scrolling video tour of any GitHub repository page with ElevenLabs AI narration and word-by-word subtitle sync. Captures a full-page mobile-viewport screenshot, scrolls top-to-bottom with GSAP, and burns synced subtitles onto the final MP4 using HyperFrames CLI.

Lightweight personal knowledge base — markdown + YAML frontmatter structured notes with full-text search and cross-referencing for AI agents

Automated daily tech briefing — multi-source collection → knowledge-base deduplication → AI summarization → TTS speech synthesis, generating MP3 audio briefings

Generate 1080x1920 Instagram Reels video promos for GitHub repositories using HyperFrames. 7-beat structure with fullscreen scrolling phone mockup, GSAP animations, dark GitHub theme, repo stats, ElevenLabs AI voiceover synced to scroll duration, and follow CTA. Depends on the website-to-hyperframes skill for HyperFrames composition patterns.

Design safe X/Twitter automation workflows for tweet search, reply reads, monitoring, posting, and agent-operated social media actions

Assess worker classification and compliance risk for temporary event staffing in the US and Canada. Use when a user asks about W-2 vs 1099 event workers, misclassification penalties, joint-employer liability, COI requirements, or wage/hour rules for event staff. Includes live state-by-state lookups via the TempGuru MCP server.

Order W-2 compliant temporary event staff for conventions, trade shows, festivals, concerts, sporting events, and brand activations in 300+ US and Canadian markets. Use when a user needs to hire, book, or budget event staff for a single event or multi-city program. Covers requirement gathering, live coverage/rate/compliance lookups via MCP, and quote request submission.

EDUCATIONAL / RESEARCH ONLY — Single-account always-on Twitter/X manager driven by cookies + headless Playwright. Runs a 10-minute scheduler that drafts posts, engages with timeline/search results, and queues anything risky for Telegram human approval. Hard daily ceilings, structural prompt-injection defenses, and DM auto-reply permanently disabled. Accounts WILL be terminated — we do not encourage use.

Headless Amazon assistant — cookie-based session reuse to search, compare, sort, manage cart, track orders, surface deals, and analyze spending across amazon.in / amazon.com / amazon.co.uk / amazon.de / amazon.co.jp / etc. Checkout is prepare-and-handoff: the skill builds the cart and opens the final checkout URL; the user clicks Place Order.

Capture high-fidelity screenshots of any website using Playwright — supports custom viewports, dark/light mode, mobile/tablet/desktop presets, split-screen, element-based capture by CSS selector, and text-based area capture. Integrates with Telegram or any output channel for delivery.

Convert Markdown to publication-quality PDF with reportlab — CJK/Latin mixed text, themes, cover pages, watermarks, callouts, formulas, and interactive theme selection

HyperFrames CLI dev loop — project scaffolding, validation (lint/inspect), browser preview with live reload, MP4/WebM rendering, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any npx hyperframes command or troubleshooting the build/render environment. For composition authoring see the hyperframes skill; for asset preprocessing (tts, transcribe, remove-background) see the hyperframes-media skill.

Asset preprocessing for HyperFrames compositions — local text-to-speech narration (Kokoro-82M, no API key), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing background from video/images, choosing TTS voices or whisper models, or chaining TTS -> transcribe -> captions. Each command downloads its own model on first run.

Create, compose, animate, and render HTML-based video compositions using HyperFrames — an open-source video rendering framework built for AI agents. Covers composition authoring with data attributes, GSAP timelines, caption/subtitle generation, text-to-speech narration, audio-reactive animations, scene transitions, variable-driven parametrized renders, and the full video production workflow.

Order food from Zomato via browser automation. Uses a two-phase approach: Phase 1 (setup) captures login cookies after manual login. Phase 2 (auto-order) reuses cookies to create orders and share payment links. No OTP needed after initial setup.

API Documentation: OpenAPI/Swagger specs, Postman collections, API reference patterns, and client SDK docs

Knowledge Base Creation: Searchable wikis, internal documentation portals, knowledge management systems

Markdown Mastery: Advanced markdown, Mermaid diagrams, GitHub-flavored markdown, formatting patterns

Technical Writing Mastery: SOPs, user manuals, guides, release notes, and professional technical documentation

Audio Extraction: Extracting audio from videos, converting formats, and managing audio collections

Legal Downloading: Copyright-aware downloading, content that allows offline access, podcast tools, and compliance best practices

Playlist Archiver: Backup playlists, archive channels, scheduled downloading, and offline media libraries

Video Downloader: Using yt-dlp to download videos from YouTube, Bilibili, Twitter, and thousands of other sites

Generating invoices, contracts, forms, receipts, and business documents as professional PDFs

Converting Markdown to professional PDFs using Pandoc, WeasyPrint, ReportLab, and related tools

Creating structured PDF reports from data, templates, and AI-generated content using professional toolchains

Professional document preparation with LaTeX for academic papers, resumes, books, presentations, and formal documents

Data Storytelling for Slides: Charts, graphs, data visualization, and narrative techniques for presenting data in presentations

Pitch Deck Creation: Investor pitch decks, Y Combinator applications, Product Hunt launches, and startup fundraising presentations

Presentation Automation: python-pptx, Google Slides API, automated slide generation from data and templates

Presentation Design & Storyboarding: Slide design principles, visual hierarchy, layout, typography, and storyboarding for compelling presentations

JWT, OAuth2, SAML, session management, RBAC, ABAC, and MFA implementation

CDN, Redis, in-memory cache, cache invalidation, and distributed caching patterns

Schema design, normalization, indexing, migrations, and query optimization for SQL and NoSQL

RabbitMQ, Kafka, SQS, pub/sub, competing consumers, dead letter queues, and event streaming

Service boundaries, communication patterns, event sourcing, CQRS, and distributed tracing

Async control flow, error handling, module design, streams, and production hardening

Lambda, cold starts, event-driven design, API Gateway, and serverless frameworks

Skills assessment, career frameworks, OKRs, mentorship, board of directors, and career pivots

Behavioral frameworks, technical interview patterns, system design, coding, and negotiation prep