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…
Query, manage, and automate Google NotebookLM from your AI agent. Add sources, generate slide decks with your brand colors, run research, and keep auth alive automatically.
Extract a brand's design from any reference the user provides (site URL, screenshot, or existing assets) and generate a full design system reference page AND a 1-page A4 brand book PDF. Triggers on "design system", "brand book", "make design assets", "extract design", "brand page", "one page brand".
Generate cinematic motion graphics videos using ByteDance Seedance 2.0 via Fal AI. Covers image-to-video, reference-to-video, text-to-video, liquid glass prompting, App Store screenshot scraping, and the full pipeline from screenshot to finished promo clip. Triggers on seedance, cdance, motion graphics, liquid glass…
Claude Code instructions for robonuggets/hyperframes-helper, covering claude.md — hyperframes helper kit, quick start for claude code, what's in the skill and behavior rules.
Produce HTML output instead of markdown for any agent task. Four levels — Static Doc, Visual Artifact, Two-Way Interactive, Throwaway Tool. Based on Thariq Shihipar's "Unreasonable Effectiveness of HTML" framework. Triggers on "/html-it", "html-it", "html this", "render as html", "build me an html", "make an html…
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's "Signs of AI writing" guide plus newer 2025-era tells. 30 patterns across content, language, style, communication, and filler categories. Severity-tiered (dead…
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Two Claude Code hooks that fix the most common Telegram plugin failures — stale bot processes holding the bot token (409 Conflict on next session) and silently dropped replies (agent forgets to call the reply tool). Triggers on "telegram hook fix", "telegram 409", "telegram bot conflict", "telegram reply guard", "fix…