Results for “big-bench-hard”

Read artifacts from the shared bench — the workspace where desks leave findings, verdicts, and work products for each other and the operator.

Multi-phase dialectical stress-test for HIGH-STAKES decisions only (architecture choices, irreversible product calls, strategic bets). Heavy-cost skill — do NOT use for routine questions, brainstorming, or simple tradeoffs. User must explicitly invoke or describe a decision they call "high-stakes", "irreversible", or "needs stress-testing". Triggers: "stress test this decision", "dialectic on", "challenge this thesis", "should I really".

Hard Negative Mixing for Contrastive Learning

Generates brutalist web prototypes with Swiss industrial-print aesthetics, using grotesque typography, oversized numbers, ASCII decorations, and hazard-red accents.

BALD EAGLE v3.0 — XYZ Alpha Hunter (Hardened). Focused on 6 high-liquidity XYZ assets: CL, BRENTOIL, GOLD, SILVER, SP500, XYZ100. Conviction-scaled leverage (5-10x based on score). Wider DSL for macro assets. Maker-only execution. Scanner calls create_position internally. v3.0: focused assets, conviction-scaled leverage, XYZ-tuned DSL, no thesis exit.

Generates a white magazine-style deck with rainbow bar, gradient text, macaron cards, and black pill for dual-use on Xiaohongshu and horizontal PPT.

Composite skill — one-pass cleanup of stale local branches, dead worktrees, merged branches, and abandoned remote PR branches. Chains `git fetch --prune` → `clean_gone` (kill [gone] branches) → worktree prune + offer-to-remove dead worktrees → list-and-delete branches merged to main and release → delete remote PR branches whose PRs merged >7 days ago. Use instead of running `clean_gone` alone — that only catches half the rot. Daily-friction composite; fires on "clean up branches", "branch hygiene", "stale worktrees", and on session start when local branch count > 30.

Matryoshka Representation Learning

Train large language models (7B-70B+) with RLHF using PPO, GRPO, DPO, and other algorithms, accelerated by Ray and vLLM for distributed multi-GPU setups.

BISON v2.0 — Conviction Holder (Hardened). Top 10 assets by volume. All signals are score contributors — no hard gates. Scanner enters via create_position internally (Wolverine pattern). RatchetStop exits. Thesis exit REMOVED. v2.0: every hard gate converted to score contributor, ensureExecutionAsTaker=false, conviction-scaled margin 25-37%.

Discover, bet on, track, and settle Hunch prediction markets in natural language with on-chain settlement on Base via x402.

Training Compute-Optimal Large Language Models

Structure a hard business decision — frame the choice, score options against weighted criteria, run a pre-mortem and stress-test, and produce a recommendation + decision record for any active brand

Put the user in the hot seat — one question at a time until their plan, decision, or idea actually holds up. Use whenever the user says "hot seat me", "grill me", "stress-test this", "poke holes in this", "am I missing anything", or drops a plan and wants it challenged before anyone acts on it — even if they never say the words. Also used as a sub-procedure by the whiteboard and connotation-cop skills.

Long Tasks

Creates a dramatic 'giant product' visual by compositing a product image into a scene where it appears building-sized next to a person, with an optional animation step.

Hard Call

Build serverless background jobs, event-driven workflows, and durable execution with Inngest, without managing queues or workers.

Specialist orchestrating codex exec / Antigravity CLI through dual paradigms — COMPETE (multi-variant comparison, select best) and COLLABORATE (decompose tasks across engines, integrate). Supports Solo/Team/Quick execution modes.

熊大（子供向）认知与表达框架（压缩蒸馏）：大哥责任、劝熊二、和光头强周旋… 触发：熊出没 等。安全喜剧