productivity▌

Generate structured, AI-optimized specification documents with standardized templates and machine-readable formatting. \n \n Creates specification files in /spec/ directory following naming convention spec-[purpose]-[type].md with YAML front matter for metadata \n Enforces structured markdown with 11 standard sections covering purpose, requirements, interfaces, acceptance criteria, and validation \n Includes explicit guidelines for unambiguous language, acronym definitions, and self-contained do

Web search and content extraction via Tavily and Exa APIs through inference.sh CLI. \n \n Five search and extraction apps: Tavily Search Assistant (AI-powered answers with sources), Tavily Extract (multi-URL content extraction), Exa Search (smart web search), Exa Answer (direct factual responses), and Exa Extract (web page analysis) \n Designed for research workflows, RAG pipelines, fact-checking, and content aggregation with LLM integration examples \n Requires inference.sh CLI ( infsh ) instal

Design or improve onboarding flows that get users to their \"aha moment\" quickly and successfully. \n \n Assess onboarding needs by identifying user challenges, experience level, and the key action you want them to take, then define measurable success metrics \n Follow core principles: show don't tell, make it optional, prioritize time to value, teach contextually, and respect user intelligence \n Design for multiple contexts: initial product onboarding (welcome, setup, core concepts, first suc

Analyze and redesign features to match your design system standards and ensure consistency. \n \n Requires upfront design system discovery—searches for documentation, UI guidelines, and design tokens before making changes; asks clarifying questions rather than guessing at principles \n Systematically normalizes typography, color, spacing, components, motion, responsive behavior, and accessibility across eight key dimensions \n Prioritizes UX consistency and usability over visual polish; replaces

Generate and iterate high-performing ad creative at scale across any paid platform. \n \n Supports Google Ads RSAs, Meta, LinkedIn, TikTok, and Twitter/X with built-in character limits and format validation for each platform \n Two core modes: generate from scratch using audience and product context, or iterate from performance data by analyzing top/bottom performers and building on winning patterns \n Provides structured angle-based generation (pain point, outcome, social proof, urgency, identi

Sales collateral and playbooks that help reps close deals faster. \n \n Covers pitch decks, one-pagers, objection handling docs, demo scripts, ROI calculators, case study briefs, proposals, and sales playbooks tailored to specific buyer personas and deal stages \n Emphasizes rep-centric design: scannable formats, rep language, and situation-specific customization rather than generic templates \n Includes frameworks for discovery-driven demos, objection response strategies organized by category,

Deterministic browser automation for AI agents with snapshot-based element references and multi-session support. \n \n Interact with web pages using stable element refs (@e1, @e2, etc.) generated from snapshots, enabling reliable automation across DOM changes \n Core commands cover navigation, form filling, clicking, waiting, screenshots, PDFs, and visual regression testing via baseline comparison \n Supports parallel isolated sessions, network-aware waits (networkidle), and selector-based targe

Fast, optimized image generation with Pruna's P-Image models via inference.sh CLI. \n \n Four model variants: P-Image for text-to-image, P-Image-LoRA with 11 preset styles, P-Image-Edit for image editing, and P-Image-Edit-LoRA for stylized edits \n Supports multiple aspect ratios (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, custom) and multi-image compositing for collages and combinations \n Requires inference.sh CLI ( infsh ) and login; run models via infsh app run pruna/[model-name] with JSON input p

Comprehensive implementation plans for multi-step tasks, breaking down specs into bite-sized, testable steps. \n \n Decomposes requirements into focused tasks (2–5 minutes each) following TDD: write failing test, verify failure, implement, verify pass, commit \n Maps file structure upfront with clear boundaries and responsibilities, ensuring each file has one purpose and files that change together stay together \n Includes exact file paths, complete code samples, and specific commands with expec

Use this skill for the tzst command-line interface. Default to execution when the user clearly wants a real archive action and the required paths or archive names are already known.