Update to AI DevKit

{
  "name": "brainstorm",
  "description": "AI DevKit · Use when the user asks to brainstorm, ideate, generate ideas, expand options, challenge ideas, pressure-test ideas, compare concepts, narrow choices, name something, plan content angles, explore strategy, evaluate product ideas, technical approaches, experiments, or decisions.",
  "included_files": [],
  "skill_md_contents": "---\nname: brainstorm\ndescription: AI DevKit · Use when the user asks to brainstorm, ideate, generate ideas, expand options, challenge ideas, pressure-test ideas, compare concepts, narrow choices, name something, plan content angles, explore strategy, evaluate product ideas, technical approaches, experiments, or decisions.\n---\n\n# Brainstorm\n\nRun a compact diverge-to-converge loop.\n\n## Workflow\n\n1. Frame: goal, constraints, audience, success criteria, assumptions.\n2. Baseline: state the simplest honest solution first. Every option must beat it; the baseline stays a candidate.\n3. Diverge: distinct options across practical, high-leverage, and unusual angles.\n4. Challenge: weak assumptions, failure modes, tradeoffs, rejections. Always: reject speculative generality (each abstraction, layer, flag, and data copy needs a current caller) and verify load-bearing \"needed\" claims in the consuming code, not doc assertions.\n5. Compare: only relevant criteria, plus deletion cost (how easily the option can be removed later). Ties go to the smaller option.\n6. Converge: strongest 3 picks with rationale and a next step. Self-review first: for each new constant, object, layer, and flag ask \"why do we need this?\" Cut answers that are only messaging or future-proofing.\n\n## Formats\n\nUse Quick by default. Use Deep only for ambiguous or high-stakes decisions. Ask at most one clarifying question only if missing context would materially change the brainstorm; otherwise state assumptions and proceed.\n\n- Quick: clusters, challenges, 3 picks.\n- Deep: assumptions, clusters, evaluation table, recommendation.\n- Naming: tone groups, fit, ambiguity, pronunciation.\n- Technical: approaches, tradeoffs, risks, validation.\n- Content: angles, hooks, audiences, outlines.\n\nAvoid filler, near-duplicates, generic best practices, premature recommendations, and scope without a current caller. If asked for more ideas, explore a new axis before listing variants.\n"
}