Research & Search

lyston11 Bundle

网络小说工具箱主入口。根据用户需求自动路由到对应 skill，并可启动本地 Dashboard 查看拆文库、写作项目和编辑文本。触发方式：/story、$story、/story dashboard、$story dashboard、/网文、「我想写小说」「打开工作台」「检查更新」。

lyston11 Bundle

基于文件系统初始化、继续和交付短剧或漫剧项目，并提供面向创作者的本地 Dashboard；也负责项目级制作形态、视觉方向和 Look Development 路由。用户提出“创建/继续短剧项目”“看进度/下一步”“做 Look Development”“打开 dashboard/短剧创作台”“导出制作资料”，或任务跨多个环节而需要判断负责技能时使用；明确的写作、资产、提示词、分镜或审查请求由对应子 skill 直接处理。

lyston11 Bundle

小说封面生成。根据书名、作者名自动分析题材风格，调用 GPT-Image-2 生成含标题和署名的专业级网文封面；Codex CLI 优先使用内置 ImageGen，无需单独 API Key。触发方式：/story-cover、/封面、「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」。

lyston11 Bundle

网文去AI味。检测并清除文本中的AI写作痕迹，让文字回归自然、非模板化。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。

lyston11 Bundle

逆向导入已有小说。将已写好的小说（半成品或完本）反向解析为标准项目目录结构，兼容 story-long-write / story-short-write 后续写作流程；内部复用 story-long-analyze / story-short-analyze 的拆解管道，按篇幅自动分流。触发方式：/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」。

lyston11 Bundle

多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。

lyston11 Bundle

从短剧剧本拆解并统筹角色/造型、场景/视图、道具/状态、可选的角色声音方向和跨场连续性。用户说‘拆角色/场景/道具’、‘做资产表/角色表/场景表/道具表’、‘判断复用还是新变体’、‘更新造型/道具状态’、‘给角色定声音/音色/绑定参考音频/做配音选角表’，或拿现成剧本直接做视觉资产准备时使用；本 skill 不写资产图提示词，不生成图片或视频，也不合成音频、不调用任何语音服务。

lyston11 Bundle

校验与审查文件系统短剧项目中的原著分析层、故事、剧本、资产、连续性、资产图片提示词、分镜、关键帧和视频提示词，并消费有界授权生产观察做当前项目校准。用户提出“审稿/检查剧本”“检查资产或连续性”“检查图片/视频提示词”“检查原著分析或分集候选”“审查或诊断模板感”“根据生产观察做项目校准”，或判断一集能否交付文本或 JSON 时使用；只发布审查问题、审查结论和修订要求，不代替负责人修改来源文件。

lyston11 Bundle

长篇网文扫榜。分析起点、番茄、晋江等平台排行榜数据，提炼市场趋势与热门题材。触发方式：/story-long-scan、/长篇扫榜、「长篇什么火」「起点排行」。

lyston11 Bundle

在创作者明确确认后，执行短剧项目的图片、视频、TTS/配音或时间线音乐生产任务，并把结果与精简运行记录落回项目。用户说“生成这张图/这段视频/这句配音/这段配乐”“开始跑图/跑视频/合成语音/生成音乐”“把已确认提示词送去生产”，或要求批量执行已确认媒体任务时使用；不负责创作提示词、镜头、台词、歌词或声音身份，也绝不把预览、继续、预算说明或既有接受状态当作本次付费生产确认。

lyston11 Bundle

长篇网文写作。从大纲到正文，辅助长篇网络小说的创作，包括世界观、人物、情节线管理。触发方式：/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。

lyston11 Bundle

短篇网文写作。辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控。触发方式：/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」。

lyston11 Bundle

长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。单一深度拆解管道：跑完黄金三章（Stage 1）后产出快速预览报告并询问是否继续全量拆解，确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告，全程产物落盘 拆文库/{书名}/。触发方式：/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」「深度拆解」「完整拆解」「系统拆解」或提供小说文本文件路径——全部进入同一管道。

lyston11 Bundle

把已接受的中文短剧剧本和资产转成原文落实表、有戏剧动机的镜头、连续性边界与冻结关键帧提示词；关键场次可先做场次视觉计划或 Coverage Audition 比较真正不同的导演方案。用户提出“拆分镜/设计镜头/做镜头表”“场次视觉计划/调度故事板”“比较导演方案/Coverage Audition”“写首帧/关键帧提示词”“检查轴线、站位、视线、持物连续性”，或需要在不生成媒体的前提下把竖屏短剧、漫剧的剧本内容转成可拍的画面时使用。

lyston11 Bundle

为已接受的短剧镜头和关键帧编写或修改可复制的通用视频提示词与运动规格，也负责跨镜时间线配乐/主题曲的 provider-neutral 音乐规格。用户提到视频提示词、文生视频、图生视频动作、人物表演过程、运镜、对白口型、环境运动、镜头时长、起止状态、把分镜转成视频提示词、写主题曲/配乐提示词或校验时间线音乐规格时直接使用；视频部分只描述单个已编镜头内的运动、表演、摄影与声音，音乐部分只投影已接受剧情/导演意图和创作者提供的歌词；不生成媒体，不调用供应商，不创作歌词，也不改写分镜边界。

nuanu-ai Bundle

Store, version, search, link, and deliver files and documents in Nuanu Flow — research outputs, reports, datasets; temp scratch vs committed storage, entity binding, downloads, and exact-version Process review.

91zgaoge Skill

StoryMoss 可推进的开放前沿——Context Rot 防御深化（长篇连载下记忆衰减量化与对抗）。何时加载：要规划研究、要评估长上下文记忆方向、要量化 Lost in the Middle、要扩展 ContextPrioritizer、或被问“下一步研究做什么/本项目的前沿在哪”时。

91zgaoge Skill

把直觉变成被接受结果的纪律（证据门槛、假设须先报数字、idea 生命周期、好想法来源）。何时加载：要做研究/实验、要提一个新机制/新阈值、要把实验 flag 转为默认或退役、或被问“怎么验证/怎么让这个想法被接受”时。

tamdogood Bundle

Analyze a software repository at the latest remote main commit and turn its implemented architecture into a citation-backed interactive isometric system map with a legend, selectable infrastructure buildings, dependency and payload flows, and plain-language learner explanations. For eligible public GitHub repositories, also contribute the verified map to tamdogood/CodeTerrain with a pull request. Use when a user provides a repository URL or asks to visualize, explore, learn, explain, or map a repo's architecture, infrastructure, runtime control flow, data flow, services, queues, stores, external systems, or deployment topology in an interactive UI.

tamdogood Bundle

Generate, refine, compare, and when needed validate distinctive names for startups, AI products, developer tools, protocols, open-source projects, apps, product families, local businesses, services, companies, nonprofits, and other organizations. Use when asked to name or rename a business, brand, product, venture, shop, studio, or organization; derive a name from an existing project or concept; create a company and product naming system; compare candidates; or check company, domain, package, repository, marketplace, or trademark conflicts. Default to a fast no-browse creative pass; use current validation when the user requests availability or research, or is choosing a final name. Do not claim legal clearance, purchase domains, or present stale or unverified availability as fact.

tronghieu Bundle

Coach structured brainstorming sessions on any topic: diverge on ideas together, then converge on priorities and next steps in a session document. Use whenever the user wants ideas or wants to think out loud, in any language ("brainstorm with me", "give me ideas for…", "help me come up with…", "let's explore options for…", "I'm stuck on the name / the features"; Vietnamese "brainstorm cùng tôi", "cho tôi ý tưởng", "nghĩ cùng tôi xem"), even when they never say "brainstorm". Also use when the user wants multiple perspectives or a devil's-advocate pass on their ideas ("give me different angles", "phản biện mấy ý tưởng này", "party mode"). Not for diagnosing why something is failing (problem-solver), user research (design-thinking), or company-level strategic bets (strategy-board).

tronghieu Bundle

Conduct rigorous, citation-backed desk market research: quick go/no-go market scans, market sizing (TAM/SAM/SOM), competitor analysis, customer demand signals, and trend/macro (PESTEL) analysis. Use this skill whenever the user wants to research, size, validate, or enter a market — "is there a market for…", "how big is the market for…", "who are the competitors of…", "should I build/launch/sell…", "validate this business idea", "market research for…", "market entry" — in any language and for any country's market (e.g. "nghiên cứu thị trường", "étude de marché", "市場調査", "análisis de mercado"), even when the user never says the words "market research". Also use it when another skill or workflow (strategy-board, design-thinking, a product brief) needs external market facts delivered into its fact base or research folder.

tsingyuai Bundle

Use this when the user wants research ideas, innovation points, or to find research gaps (找研究方向, 生成创新点). Generates 5 ideas from collected papers, identifies gaps, proposes novel methods with citations. Requires papers in workspace.

tsingyuai Bundle

Use this when the user wants to write a literature review, survey paper, or thesis chapter from existing papers. Guides reading strategy, note-taking, synthesis, and academic writing. NOT for searching new papers (/research-collect) or generating ideas (/idea-generation).

tychohq Skill

Research the architecture of a codebase or system. Reads source code, finds external context, explains design decisions, and produces ELK diagrams. Use when asked to understand, explain, or diagram how a repo/system is built.

ukgovernmentbeis Skill

Crawl repository PRs, issues, and review comments to distill institutional knowledge into a shared knowledge base. Run periodically by "context agents" to maintain agent_artefacts/repo_context/REPO_CONTEXT.md. Trigger only on specific request.

undefined-ui Skill

Draft from the vault: outline from concept pages, keep citations to the user's own sources, and surface where their material disagrees. Use this skill when the user wants to write an article, post, essay or newsletter based on what they have collected, or asks what they could write about a topic. Do NOT use for research reports, for writing with no grounding in the vault, or for editing text the user wrote themselves unless asked.

fedec65 Skill

Swiss legal document drafter — creates contracts (OR), court submissions (ZPO), and legal opinions (Gutachten) in DE/FR/IT/EN with correct Swiss citations and Gutachtenstil. Trigger when: a user asks to draft, write, or create a legal document. Uses swiss-citation-formats for citation verification and swiss-legal-research for jurisdiction resolution. Do NOT trigger for: document analysis (swiss-document-analysis), research (swiss-legal-research), or citation formatting only.

fedec65 Skill

Swiss legal research and jurisdiction resolution — searches BGE/ATF/DTF precedents, interprets federal and cantonal statutes, resolves federal vs. cantonal jurisdiction, and produces verified multi-lingual legal analysis. Trigger when: a user asks what the law says, requests precedents, needs statute interpretation, or asks which jurisdiction applies. Do NOT trigger for: citation formatting only (swiss-citation-formats), query clarification (legal-intake), drafting (swiss-legal-drafting), or translation (swiss-legal-translation).

fedec65 Skill

Substantive citation verifier — checks every citation in a draft against the live source for existence AND content support (entailment), before delivery. Status per citation: MATCH / PARTIAL / MISMATCH / UNVERIFIED. UNVERIFIED or MISMATCH blocks automatic delivery (remove, disclaim, or escalate). Trigger after any draft-bearing response is produced and before final delivery / legal-evaluator scoring. Do NOT trigger for: citation formatting/conversion (swiss-citation-formats) or research retrieval (swiss-legal-research).

fedec65 Skill

Swiss legal document analyzer — structured analysis of contracts, court decisions, statutes, submissions. Includes NDA triage (GREEN/YELLOW/RED) and playbook-aware contract review. Trigger when: user uploads a document for review, requests NDA triage, or mentions 'playbook' or 'posizioni standard'. Uses swiss-caselaw, entscheidsuche, legal-citations, fedlex-sparql MCPs. Do NOT trigger for: drafting (swiss-legal-drafting), citation formatting only (swiss-citation-formats), or research without a document (swiss-legal-research).

fedec65 Skill

Swiss legal translator — translates Swiss legal texts (contracts, submissions, statutes, opinions) between DE, FR, IT, and EN with correct terminology and register. Trigger when: a user asks to translate a Swiss legal document or term, or a document must be prepared in a different national language. Uses fedlex-sparql for statute text verification. Delegates citation conversion to swiss-citation-formats. Do NOT trigger for: citation formatting without translation (use swiss-citation-formats), document drafting (use swiss-legal-drafting), or general non-legal translation.

fl-sean03 Skill

Search, retrieve, compare, and export INTERFACE Force Field (IFF) parameters for molecular dynamics simulations. Use BEFORE searching literature for force field parameters — IFF covers metals, minerals, oxides, clays, and organic interfaces with validated, citation-ready values.

fl-sean03 Skill

Synthesize scientific theories from literature corpora using ASTA Theorizer. Use when asked to generate hypotheses, find research gaps, synthesize knowledge across many papers, or create literature-grounded theories for computational testing.

fl-sean03 Skill

Search and retrieve scientific literature. Use when asked to find papers, research a topic, find citations, get paper abstracts, or conduct literature reviews. Accesses Semantic Scholar, arXiv, and other academic databases.

guhcostan Skill

Use when facing 2+ independent research, analysis, or investigation tasks that can run concurrently without shared state