Generate a single-file, self-contained HTML tracking panel for any project's progress — visual "waves" (phases/sprints/milestones) of work items (PRDs, workstreams, campaigns, whatever the project calls them) with dependency chips, per-item progress bars, a filterable/sortable task table with click-to-cycle status…
Adversarial QA evaluator. Validates that a sprint is ACTUALLY done before it's committed. Approves only when it can PROVE all criteria pass; rejects only on failures it observed and can reproduce. Uses playwright-cli to navigate the live app. Part of the Generator→Evaluator GAN loop. Triggered by: 'evaluate sprint'…
Screenshot-obsessed, fantasy-allergic QA specialist - Default to finding 3-5 issues, requires visual proof for everything. Screenshot-obsessed QA who won't approve anything without visual proof. Activar cuando se necesite un Evidence Collector en el equipo o pipeline.
Build an enterprise-grade executive sales/service proposal from a single Markdown source, exported to branded HTML+PDF and Word — matching the real pipeline that won the TRUTH → HITSS/Telmex deal (docs/sales/telmex in speechlytics). Markdown stays the single source of truth; a project-specific config.json (colors…
Consultant-grade AI specialist trained to think and communicate like a senior strategy consultant. Transforms complex business inputs into concise, actionable executive summaries using McKinsey SCQA, BCG Pyramid Principle, and Bain frameworks for C-suite decision-makers. Thinks like a McKinsey consultant, writes for…
Expert project manager specializing in experiment design, execution tracking, and data-driven decision making. Focused on managing A/B tests, feature experiments, and hypothesis validation through systematic experimentation and rigorous analysis. Designs experiments, tracks results, and lets the data decide. Activar…
Expert financial analyst and controller specializing in financial planning, budget management, and business performance analysis. Maintains financial health, optimizes cash flow, and provides strategic financial insights for business growth. Keeps the books clean, the cash flowing, and the forecasts honest. Activar…
Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animations, use…
Hand a piece of work to a DIFFERENT AI provider's CLI (Copilot, Codex, OpenCode, Gemini, Cursor, etc.) via Orca, using that provider's own subscription instead of burning Claude Code usage. Fires two ways — automatic (the orchestrator routes mechanical/low-risk work here without asking: documenter-type steps, Rigor…
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate harsh critic on each, compare blind against the bar, and loop until it wins. Works for builds, writing, code, research…
Expert growth strategist specializing in rapid user acquisition through data-driven experimentation. Develops viral loops, optimizes conversion funnels, and finds scalable growth channels for exponential business growth. Finds the growth channel nobody's exploited yet — then scales it. Activar cuando se necesite un…
Save progress, decisions, learnings, and next steps to persistent memory before a context compact (manual /compact or auto-compact) or at any natural session boundary — using ONE fixed template and a clear decision tree for where to write it, instead of improvising a different format every time. Trigger on…
Pre-commit code validator (GGA — Guardian Angel). Validates code against project cultural norms, skill definitions, and architectural rules before it's committed. AI-powered alternative to SonarQube — uses your own LLM, no external service. Works locally and in GitHub Actions CI/CD. Triggered by: 'validate code'…
Expert photography prompt engineer specializing in crafting detailed, evocative prompts for AI image generation. Masters the art of translating visual concepts into precise language that produces stunning, professional-quality photography through generative AI tools. Translates visual concepts into precise prompts…
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the…
Expert infrastructure specialist focused on system reliability, performance optimization, and technical operations management. Maintains robust, scalable infrastructure supporting business operations with security, performance, and cost efficiency. Keeps the lights on, the servers humming, and the alerts quiet.…
Expert Instagram marketing specialist focused on visual storytelling, community building, and multi-format content optimization. Masters aesthetic development and drives meaningful engagement. Masters the grid aesthetic and turns scrollers into an engaged community. Activar cuando se necesite un Instagram Curator en…
Generate a single-file, self-contained HTML "game map" of a product's user journey — a winding level path (one node per journey stage, per persona) colored by real build progress, plus a gap callout for stages nobody has built yet and a win-conditions checklist. Reads USER-JOURNEY.md (from the user-journey skill) as…
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM pitfalls. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria. Universal — applies to all agents and…
Expert LinkedIn content strategist focused on thought leadership, personal brand building, and high-engagement professional content. Masters LinkedIn's algorithm and culture to drive inbound opportunities for founders, job seekers, developers, and anyone building a professional presence. Turns professional expertise…
Convene a council of independent agents that answer a hard question separately, blind-review and rank each other's answers, then synthesize one vetted answer. Fights sycophancy and one-angle reasoning — use when the user wants a real answer instead of agreement. Two modes — default (5 Claude sub-agents) and…
Generate voiceover narration with Cartesia TTS and instrumental background music with Suno (via the Marcus/KIE gateway) — the audio sibling of marcus-images/cinematic-marcus, so a full video (voice + music + visuals) can be produced end-to-end without leaving the KIE/Marcus credential set. Triggers on "generate…
★not rated 3 6d agoA123 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: