// Creative problem-solving techniques for breaking through stuck points - includes collision-zone thinking, inversion, pattern recognition, and simplification
| name | problem-solving |
| description | Creative problem-solving techniques for breaking through stuck points - includes collision-zone thinking, inversion, pattern recognition, and simplification |
| when_to_use | when stuck on a problem, need innovation beyond conventional approaches, or want to find elegant solutions |
| version | 1.0.0 |
A collection of techniques for breaking through stuck points and finding elegant solutions.
Location: when-stuck/SKILL.md
Start here when stuck. Matches your stuck-type to the right technique. Quick dispatch table for routing to the appropriate sub-skill.
Location: collision-zone-thinking/SKILL.md
Force unrelated concepts together to discover emergent properties. "What if we treated X like Y?" Revolutionary insights come from deliberate metaphor-mixing.
Location: inversion-exercise/SKILL.md
Flip every assumption and see what still works. "What if the opposite were true?" Exposes hidden constraints and alternative approaches.
Location: meta-pattern-recognition/SKILL.md
Spot patterns appearing in 3+ domains to find universal principles. Extract abstract forms that apply across domains.
Location: scale-game/SKILL.md
Test at extremes (1000x bigger/smaller) to expose fundamental truths. What breaks? What survives? Extremes reveal what normal scales hide.
Location: simplification-cascades/SKILL.md
Find one insight that eliminates multiple components. "If this is true, we don't need X, Y, or Z." Look for unifying principles.
| How You're Stuck | Use This |
|---|---|
| Don't know which technique | when-stuck |
| Need breakthrough innovation | collision-zone-thinking |
| Forced by assumptions | inversion-exercise |
| Same issue in different places | meta-pattern-recognition |
| Unsure about production scale | scale-game |
| Complexity spiraling | simplification-cascades |
Conventional solutions inadequate? → collision-zone-thinking
"This must be done this way"? → inversion-exercise
Same pattern 3+ places? → meta-pattern-recognition
Will it work at scale? → scale-game
Same thing implemented 5+ ways? → simplification-cascades
"One powerful abstraction > ten clever hacks"
These techniques help you find the elegant solution that makes complexity unnecessary, rather than managing complexity through brute force.
Integrate Bunny.net services (CDN, Storage, Stream, DNS, Edge Scripting, Shield, Magic Containers, Optimizer, Database). Use when building with Bunny.net APIs, deploying to Bunny CDN, uploading files to Edge Storage, managing video streaming, configuring DNS zones, writing edge scripts, setting up WAF/DDoS protection, deploying containers, or optimizing images. Triggers on "bunny", "bunnycdn", "b-cdn", "pull zone", "edge storage", "bunny stream".
Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.
Build 3D web apps with Three.js (WebGL/WebGPU). Use for 3D scenes, animations, custom shaders, PBR materials, VR/XR experiences, games, data visualizations, product configurators.
Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.
Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.
Deploy to Cloudflare (Workers, R2, D1), Docker, GCP (Cloud Run, GKE), Kubernetes (kubectl, Helm). Use for serverless, containers, CI/CD, GitOps, security audit.