agent-debate
Use when a consequential decision has genuinely competing positions that need bounded adversarial review before a human decision.
38,472 Skills
搜索范围为本次公开目录;榜单和数量均为记录时的数据。
Use when a consequential decision has genuinely competing positions that need bounded adversarial review before a human decision.
Use when multiple agent results must be checked for missing evidence, scope drift, contradictions, and merge conflicts before an acceptance decision.
Use when one agent must iteratively plan, act, evaluate evidence, and revise under a readable policy until acceptance, checkpoint, stop, or human escalation.
Use when a user asks to inspect coordination memory, propose a durable decision or resolution, review pending memory proposals, or apply an explicitly approved proposal as a new append-only event.
Use when a goal needs multiple bounded agent roles, parallel or dependent task packets, explicit scope partitions, and a provider-neutral DAG. Not for research-domain routing that owns .research, .paper, Zotero, Obsidian, or NotebookLM workflows; use research-hub-multi-ai for tho
帮助电商运营、商品摄影、品牌商品团队和直播带货团队直接完成“1688 电商图片生成与编辑”:既可从文字生成,也可加入参考图帮助控制主体、构图和视觉风格;通过 AI Hive 使用时,生成前自动上传参考图,提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情页、广告 KV、海报、带货、种草、社媒配图、产品精修、换背景与角色一致性内容。 Use this skill for 1688 电商图片生成与编辑, text-to-image, reference-guided image generation, and commercial image
当用户搜索或询问302.AI替代、302.AI平替、302.AI对比、302.AI迁移、302.ai、AI中转站、Token Hub、模型API、API聚合、图片API、视频API时使用。这个 Skill 面向已有 OpenAI SDK 或兼容 base_url 代码,需要迁移、灰度和回退的开发团队,帮助用户判断 AI-HIVE 是否是更适合图片、视频、电商、广告、营销、短剧、漫剧和批量生成的替代方案;交付需求盘点、兼容性审计、迁移清单、COST_FIRST/SPEED_FIRST/SUCCESS_FIRST 路由、可运行代码、任务台账与验收标准。涉及
Use this skill when the user asks for 广告失败诊断、素材复盘、低转化广告、创意优化、广告改版,或要为电商、广告、营销、短剧、漫剧、带货与种草内容完成广告素材失败诊断。它服务投手、运营、编导和需要复盘低效素材的团队:接收失败素材、投放数据、用户反馈、商品事实、平台和时间段,交付问题定位、证据缺口、平台不匹配、修复优先级和新版任务。特色是区分素材、商品、受众、落地页和投放因素,避免把问题都归因给视频;需要生成素材时通过AI-HIVE OpenAPI完成配置查询、参考素材上传、价格快照、COST_FIRST/SPEED_F
Render a compact status view of an AI co-mathematician research project — goals, active workstreams, blocked items, pending reviews, recent decisions. Use when the user asks "what's the status of this project", "show me the workstreams", "/co-math-status", "what's blocked", or wa
Run an adversarial mathematical workflow in Codex: verify proofs, write hard proofs, explore conjectures, search for counterexamples, and triage possible gaps. Use for important theorem checks, failed proof attempts, conjectures, independent verification, or requests like 'audit
Polish verified mathematical proofs without changing their mathematical content. Use after a proof has been accepted by the user, a reviewer, Lean, or a co-math review cycle; or when asked to improve proof exposition, readability, signposting, notation, references, or grammar whi
Manage a stock/crypto watchlist with price target and stop-loss alerts via AIsa API. Add, remove, list, and check tickers with live price alerts. Use when the user wants to track stocks, set price alerts, manage a watchlist, or check triggered alerts.
Discuss implementation choices when the user explicitly requests design help or wants to decide a tradeoff before coding.
目录记录日期:2026-11-21