skills

Build CoinFund-branded web presentations as self-contained HTML files. Supports static (print/PDF) and dynamic (keyboard nav, transitions) modes. Outputs a single versionable HTML file with optional PDF export via Puppeteer. Trigger on: 'web deck', 'web slides', 'html presentation', 'web presentation', or any request for a browser-based slide deck.

Compress a prompt while preserving semantic content. Use when user says "compress this prompt", "make this shorter", "reduce token count", or "shorten these instructions". Supports lossy (default, 30-50% reduction) and lossless (--lossless, 100% retention) modes.

Collaboratively improve an article or bullet points section-by-section. Use when user says "improve this article", "make this better", "edit my draft", or "help me revise this piece". Surfaces non-obvious insights, applies a target style, and pauses for user input at every step.

Surface the top 3 mental models from contemporary thinking that best illuminate a given problem or situation. Use when user says "what mental models apply here?", "help me think about this", "what framework should I use?", or "reframe this problem". Applied analysis showing how each model reframes or clarifies the issue.

Optimize a prompt through a critique-compress pipeline with semantic equivalence verification at each stage. Use when user says "optimize this prompt", "make this prompt better and shorter", or "improve and compress". Applies think-critically to improve the prompt, then compress-prompt to reduce it, validating that behavior is preserved after each transformation.

Take any user output — prompt, story, procedure, analysis — and make it maximally effective through iterative intent extraction and focused questioning. Use when user says "sharpen this", "make this more effective", "help me clarify this", or "refine my writing".

Adversarially test a thesis or take for differentiation, robustness, and blind spots. Use when user says "stress test this", "is this take good?", "what am I missing?", "poke holes in this", or "challenge this thesis". Prevents publishing consensus as contrarian and surfaces what would change your mind.

Extract falsifiable ideas from input, deep-research each one, and return evidence for or against with strength ratings. Use when user says "find evidence for this", "is this true?", "back this up with data", or "fact-check these claims". Honest about when evidence contradicts the idea.

Take data, observations, or notes and surface non-obvious insights that click into place. Use when user says "what does this mean?", "connect the dots", "what's the insight here?", "analyze these notes", or provides bullet points and asks for meaning. Finds connections, dynamics, and structural truths hiding in the data.

Rigorously evaluate whether a prompt or document will produce the expected output when processed by an LLM. Use when user says "evaluate this prompt", "review my prompt", "will this work?", "critique this", or "check my instructions". Adversarial analysis with expectations scorecard and actionable recommendations.

Transform song lyrics into vivid visual scene descriptions and image generation prompts. Use when user says "visualize these lyrics", "turn this song into images", "create visuals for this track", or provides song lyrics and asks for imagery. Filters for concrete imagery and renders each distinct scene as a numbered canvas.

Write accessible, engaging op-ed-style articles in the Brukhman voice. Use when user says "write an op-ed", "write an article", "draft a blog post", or wants a long-form opinion piece. Authoritative but conversational, technically grounded, with progressive narrative structure.

Write punchy, conviction-driven thread essays in the Brukhman voice. Use when user says "write a thread essay", "write a post about", "draft a thread", or wants a conviction-driven insider-audience piece. First-person, insider-to-insider, with contrarian framing and enumerated arguments.

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 comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer