Claude Skills by justsima

Parallel divergent ideation for coding agents. Spawns N isolated branches under different cognitive frames (regulator, biology, speedrunner, 10 year old, $0 budget), scores, prunes traps, and deepens the top survivors. The isolated parallel branches and the separated generator/critic phases are load-bearing. Costs about 10 LLM/Agent calls per run (5 to 10x a single answer) so invocation is gated. UNCONDITIONAL TRIGGER. When the user types "/adhd" or explicitly asks for "ADHD mode", "use the ...

Generate tailored answers for job application questions based on your own profile. Use when the user shares a job description or application questions and needs help crafting responses. Supports all question types including behavioral, motivational, technical, and short-answer application form questions. Generates natural, human-sounding responses that are professional yet friendly.

Run a question, plan, decision, code review, or PR through a 5-advisor LLM Council with anonymized peer review and chairman synthesis. Each advisor uses a distinct REASONING METHOD (inversion, decomposition, analogy, naive questioning, dependency graphing) — not just a different persona. Based on Andrej Karpathy's LLM Council + DMAD research (ICLR 2025). MANDATORY TRIGGERS: 'council this', 'run the council', 'pressure-test this', 'stress-test this', 'war room this', 'debate this', 'convene th...

Advanced product/market research — find "the best X on the market" in any category (best laptop, best phone, best 5G router, best headphones, best monitor, etc.) across major retailers (Amazon, Best Buy, Walmart, Newegg, B&H, Target, manufacturer). Runs a multi-agent pipeline: expert-review consensus + contrarian/owner-complaint mining + live cross-retailer pricing + spec verification, then a DETERMINISTIC weighted decision-matrix scoring engine, adversarial red-team verification, and a wiki-...