deep-structural-analysis-skill
Opt-in DeepSeek Harness Skill-only bundle for the deep-structural-analysis multi-lens structural analysis skill.
10 results
Opt-in DeepSeek Harness Skill-only bundle for the deep-structural-analysis multi-lens structural analysis skill.
对抗式多视角代码审查插件:多透镜并行攻击式审查、确定性静态哨兵、跨视角合并去重、严重度定级、抑制规则与审查历史。支持 dsh(DeepSeek Harness)工具接入与独立 CLI 两种入口。
Adversarial pro/con debate with a neutral judge for DeepSeek Harness: /debate human command, subagent-driven rounds, verdict record, and a web debate card.
DeepSeek Harness plugin that bridges to external AI models (Codex, Claude, GPT, ...) for second-opinion code review, adversarial review, and task delegation.
Kestrel — adversarial deep-research engine for DeepSeek Harness. Mechanically-verified citations, independent-corroboration scoring that exposes syndication laundering, prosecutor/defender claim tribunal, and a compounding evidence graph.
Multi-agent orchestration for DeepSeek Harness: delegate, adversarial review, diverse explore, background runs + converge. One prompt. A team of agents.
怀疑驱动开发:每个非平凡决策在落地前接受新鲜上下文的对抗性审查(CLAIM→EXTRACT→DOUBT→RECONCILE→STOP)。受 addyosmani/agent-skills(88k★ MIT)启发。
DSH skill bundle: competition math (IMO/Putnam/USAMO/AIME) solved with a pure-reasoning pass, an adversarial verifier in a fresh subagent context attacking concrete failure modes, and calibrated confidence output (high / medium / honest "no confident solution"); optional LaTeX→PDF rendering.
Research lab for DeepSeek Harness: AutoSci-style wiki (experiments/literature/decisions), ASI-Bench-grade eval rigor ledger, arXiv digest, adversarial paper review, and academic writing checks.
Multi-Agent collaborative skill forging system for DeepSeek Harness — distill conversational experience into verifiable, reusable skills with evolutionary optimization.