agent-skills

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

Create App Store and Google Play screenshots with exact platform specs. Covers iOS/Android dimensions, gallery ordering, device mockups, captions, preview videos, localization, and A/B testing. Use when: app store screenshots, ASO, app preview, store listing, app mockup.

Multidisciplinary idea and project evaluator. Dispatches 3-6 specialist evaluators in parallel (market, technical, risk, impact, resources, innovation), synthesizes their outputs into a unified assessment with scores, Value Matrix, and actionable next steps. Use when: evaluate idea, assess project, is this worth building, analyze opportunity, score my idea, project evaluation, should I build this, business viability, feasibility study, startup idea.

Audit code against architecture documentation. Detects drift between what was designed and what was built. Compares ARCHITECTURE.md, ADRs, and README technical sections against actual code structure, imports, and dependencies. Use when: architecture, drift, review architecture, code vs design, structural audit, architecture compliance, design doc.

Analyze C/C++ code for Rust migration planning. Classifies functions by migration difficulty (easy/medium/hard), identifies unsafe patterns, pointer complexity, and macro usage. Use when: analyze C code, migration planning, C to Rust, assess migration difficulty, code complexity analysis.

Complete C/C++ to Rust migration pipeline. Analyzes code difficulty, converts to idiomatic safe Rust, and validates the result. Covers memory management, pointer translation, error handling, unsafe minimization, and differential testing. Use when: migrate C to Rust, rewrite in Rust, C to Rust conversion, Rust migration, convert C code, C2Rust, unsafe Rust reduction.

Life advisory council with 8 parallel specialist advisors and synthesis. Dispatches domain-specific advisors (life coach, finance, health, career, learning, systems, relationships, creative) in parallel, synthesizes their outputs into a unified action plan with prioritized next steps. Use when: life planning, goal setting, periodic review, career decision, financial planning, health optimization, relationship advice, productivity systems, creative projects, life direction, organize my life, what should I focus on, I need advice about, quarterly review.

Record automated demos for mobile and web apps. Converts natural language demo scripts into Maestro flows (mobile) or webreel configs (web), executes them to capture screenshots and video, and generates a QA report. Use when: record demo, demo recording, record app demo, grab demo, automated demo.

Generate and run E2E tests for mobile and web apps. Discovers screens, states, and flows via static analysis, generates Maestro test flows with assertions, executes them, and reports pass/fail results. Use when: run e2e, test flows, e2e tests, generate tests, automated testing.

End-to-end product builder with founder mindset. Orchestrates 9 phases: idea evaluation → architecture → TDD → implementation → E2E → verification → analysis → GTM. Produces a launched product with README, pitch, tweet thread, and Product Hunt draft. Use when: build product, founder mode, full lifecycle, idea to launch, end to end, build from scratch, MVP, product builder, launch kit, vibe coding with quality.

Complete strategic and personal evaluation of any idea, project, or life decision. Runs architect (6 business evaluators) and council (8 life advisors) in parallel, cross-references their outputs, and generates a PDF report. Use when: full evaluation, complete assessment, should I do this, evaluate everything, life decision, career move, startup decision.

Simulate a real hackathon jury evaluating your project. Researches actual jury members via web search, builds personalized juror personas, dispatches parallel evaluations, and synthesizes a deliberation with scores, feedback, and pitch coaching. Use when: hackathon, jury, evaluate my project, hackathon submission, judge my project, prepare for hackathon, hackathon feedback, hackathon prep.

Automated idea laboratory — generates multiple diverse ideas from a context, pre-screens them, evaluates the best with multi-agent scoring via /architect, and ranks the winners. Configurable idea count, diversity axes, score thresholds, and dimension filters. Composes with /founder-mode to build the winning idea. Use when: brainstorm ideas, generate ideas, hackathon ideas, idea lab, idea factory, compare ideas, evaluate multiple ideas, which idea should I build, batch evaluation, ideation.

Redesign mobile app UI to feel unmistakably iOS-native with modern Apple-like glass materials (translucency, blur, depth). Use when: iOS design, glass UI, translucent UI, Apple-style, iOS material system, glassmorphism, blur effects, iOS-native interface, mobile app redesign, SF Pro typography.

Persistent error memory — analyzes failures, extracts root-cause lessons, and prevents the same mistake twice. Triggers on test failures, build errors, runtime crashes, and command failures. Use when: error, fail, bug, mistake, crash, learn, lesson, debug memory, remember error, same mistake.

Maestro mobile E2E testing patterns for React Native/Expo apps: YAML test flows, testID selectors, adaptive auth state, optimistic update verification, GraalJS scripting, cross-platform stability, CI/CD integration, Maestro Cloud, and MCP server integration. Use when: write Maestro test, flaky mobile test, test my app, automate mobile testing, mobile E2E, debug test failure, Maestro setup.

Safety verification checklist for C-to-Rust migrations. Validates compilation, unsafe block minimization, memory safety, API compatibility, and idiomatic Rust patterns. Use when: validate migration, check Rust safety, verify converted code, migration QA.

Comprehensive mobile UI/UX design system covering React Native components, touch interactions, gesture patterns, accessibility, app navigation, and visual design principles. Use when building mobile apps, designing mobile screens, implementing React Native UI, reviewing mobile UX, or following iOS/Android platform conventions. Triggers: mobile UI, React Native, app design, mobile UX, touch targets, mobile patterns, app screen design.

Development conventions for the Noricum C-to-Rust migration agent. Architecture decisions, crate structure, coding standards, and contribution guidelines. Use when: contributing to Noricum, noricum development, noricum architecture.

Evaluate if your project is ready for open source. 5 specialist agents audit in parallel — licensing, documentation, security, community readiness, API surface — then synthesize a unified readiness score with prioritized fixes. Use when: open source my project, ready for open source, prepare for public release, open source checklist, publish my code, should I open source this.

Generate professional PDF reports and presentations from structured content. Converts evaluations, proposals, and assessments into polished PDFs with tables, score visualizations, and styled sections. Use when: generate PDF, create report, export to PDF, make presentation, create proposal document, export evaluation.

Record browser interactions as video using Playwright. Capture demo videos, app walkthroughs, and UI flows. Includes cursor highlighting, click ripple effects, cookie banner dismissal, and window scaling patterns. Use when: record demo, capture browser video, screen recording, walkthrough footage.

Automatic post-mortem analysis — parses logs, compares with history, identifies recurring patterns, proposes fixes, updates memory. Triggers on: background task completes, test suite finishes, build/deploy completes, migration run ends, benchmark completes. Use when: analyze, post-mortem, what happened, evaluate results, what went wrong, compare runs, run history, run report.

C/C++ to idiomatic Rust conversion patterns and pipeline. Covers pointer translation, memory management, error handling, string conversion, struct patterns, and quality gates. Use when: convert C to Rust, migrate to Rust, C to Rust patterns, Rust migration, rewrite in Rust.

Iterative UI/UX polishing workflow for web applications. Achieve Stripe-level visual polish through multiple passes — each iteration adds incremental improvements that compound dramatically. Use when: polish UI, improve UX, make it look better, Stripe-level, world-class design, desktop and mobile optimization, visual polish.

Simulate a VC investment panel evaluating your startup. Researches real investors in your sector via web search, builds personas from their investment thesis, portfolio, and known preferences, then each investor evaluates independently. Synthesizes a partner meeting deliberation with funding verdict and specific feedback. Use when: VC feedback, investor pitch, fundraising prep, would VCs fund this, pitch evaluation, startup funding, series A prep.

Create and record scripted browser demo videos with webreel. Generates MP4, GIF, or WebM recordings with cursor animation, keystroke overlays, and sound effects from a JSON config. Use when: record a demo, create a browser video, edit a webreel config, generate a screen recording, preview a demo, product video, marketing video, record website, work with webreel in any way.

Create developer YouTube content, technical screencasts, and video tutorials. Covers tutorial structure, screen recording setup, live coding, shorts vs long-form, thumbnails, and SEO for technical content. Use when: YouTube, developer video, screencast, video tutorial, live coding, YouTube for developers, tech YouTube, YouTube thumbnails.