Research & Search

cabbage2000-lab Bundle

Paper 开题报告组装命令（多源汇聚组装器）。当用户要写开题报告、组装学位论文开题材料、按中文学位论文制度节点整理立项文档，或说"帮我组装开题报告""开题报告怎么写""开题要准备什么""选题依据怎么写""文献综述部分帮我整理""研究内容部分怎么填""学位论文开题"时使用——即使用户只说"我要开题了""开题报告草案""立项报告"也应使用。行为铁律：多源汇聚组装——从 topic（RQ 原话）+ literature（真实文献笔记五字段）+ method（研究设计参谋产物）提取可复用片段，按中文学位论文开题报告常见制度节点（选题依据/文献综述/研究内容/研究方法/技术路线/工作计划/参考文献/创新点）摆骨架；研究内容、工作计划、创新点等研究者自有内容标占位请用户填、绝不 AI 代写各节正文；锚点必指上游真实产物（文献不编、RQ 不改写、方法不凭记忆补）；产物如实披露组装来源；确认前零落盘。不替用户定研究内容、不编文献、不代写各节正文。"帮我写一份完整的开题报告""帮我编几条参考文献""帮我想几个创新点"走三段式转化。

danmcinerney Bundle

Develop a project endgoal through N bounded cycles of brainstorm and research, design, implementation, comparison testing and analysis.

krishagel Bundle

Organizational strategic planning for K-12 school districts using a research-backed 4-stage process

chrisliu298 Skill

Re-layer the previous response (or a named file) into a fast-to-skim form: answer first, a review-map or key-findings short version, action-changing blockers only, detail pulled on demand. Restructures for fast reading WITHOUT dropping substance. Use when a reply came out dense, or the user says "tl;dr", "too long", "wall of text", "make this skimmable", "digest that", or invokes "digest". Do NOT use to summarize-away detail, on already-short replies, or to clean code (use deslop).

alter123-zz Bundle

arXiv论文智能阅读助手。通过对话式交互阅读和分析学术论文。Keywords: 论文, arXiv, paper, academic research.

alter123-zz Bundle

引用管理。学术引用管理助手。文献导入整理、多种引用格式生成(APA/MLA/Chicago)、参考文献列表管理 Keywords: 引用管理, citation, 参考文献, 学术写作.

alter123-zz Bundle

市场调研自动化工具。从社交媒体挖掘用户痛点，分析竞品。Keywords: 市场调研, 竞品分析, market research.

tokenrhythm Skill

Use this meta-skill instead of answering directly when the user wants account research, lead qualification, company/person briefing, outreach prep, or a sales call brief that benefits from multi-skill orchestration across web research, browser/source review, CRM-style notes, and email drafting.

tokenrhythm Skill

Inspect the user's open GitHub PRs / failing CI / new issues via `gh`, summarize into 3 buckets (to-review / awaiting-me / CI-red), and persist follow-ups to memory.

lefant Bundle

Runs the portable QRSPI workflow (Question, Research, Structure, Plan, Implement), including Design, Worktree, and PR phases. Use when the user asks for QRSPI, names a /qrspi/ command, or requests its neutral-question research and staged design workflow. Not for the original RPI commands or generic planning requests.

stefanomartiradonna Skill

Overview

wang-q-l Bundle

产品经理市场调研与竞品分析技能。适用场景：(1) 需要做市场规模分析（TAM/SAM/SOM），(2) 进行竞品对比分析，(3) 分析行业趋势和机会，(4) 输出市场调研报告，(5) 用户说「做竞品分析」「分析市场」「市场调研」「竞争对手分析」时触发

artherahq Bundle

Evaluate whether a cross-sectional factor genuinely predicts returns. Trigger for "这个因子有效吗", "算一下IC", "动量因子在A股还有效吗", "帮我评估这个选股信号", "factor IC", "is this signal predictive", "compare momentum vs value factors", or whenever the user (1) proposes or computes a ranking/score across assets and asks if it works, (2) asks which factor explains recent moves, (3) wants factors screened/ranked before building a strategy, or (4) hands a signal to strategy construction. Fire even for informal phrasing ("这个指标选股靠谱吗"). Do NOT trigger for single-asset technical indicator questions (no cross-section) or for validating a finished strategy's returns (that is backtest-validation).

artherahq Bundle

Turn a natural-language trading idea into a disciplined, testable strategy spec and implementation. Trigger for "帮我生成一个动量策略", "写一个BTC均值 回归策略", "设计多因子选股", "做一个ETF轮动", "generate a momentum strategy", "build me a trading strategy", "turn this idea into code", or whenever the user (1) describes a trading idea and wants it made concrete, (2) asks for strategy code, (3) wants strategy variants compared, or (4) asks to improve an existing strategy. Fire even for vague asks ("有什么好策略推荐吗" — the answer is a disciplined spec, not a tip). Do NOT trigger for validating an already-backtested result (backtest-validation) or for pure factor evaluation (factor-research).

backspace-shmackspace Skill

Research and create a technical blueprint for a new feature.

backspace-shmackspace Skill

Search, retrieve, and summarize past journal entries. Use when the user says "what did I", "recall", "look up", "find in journal", "journal search", "last week", "weekly review", "what happened on", "summarize my week", "what have I been working on", "review my journal", or asks about past work, decisions, meetings, or notes.

atman-33 Bundle

Rebuild and maintain an Obsidian vault's permanent knowledge base for work knowledge and learning notes. Use when asked to reorganize permanent, design hub/leaf/MOC structure, standardize frontmatter (especially required summary), define tag taxonomy, generate a safe restructure plan (dry-run), and apply non-destructive moves/renames while preserving links.

latifox Skill

Research a market and generate 7-10 scored idea candidates matched to your background

latifox Skill

Research a market before committing to an idea - trends, competitors, size and how people actually acquire users

sswym Skill

运行有来源支持的技术研究并将发现转换为就绪实现的指导。

fabio-baumgartner Skill

Bereitet auf einen Verkaufs- oder Kennenlern-Call vor. Nimmt Name, Firma oder LinkedIn-Profil entgegen, recherchiert öffentliche Quellen und liefert ein Kurzprofil mit Gesprächsaufhängern, wahrscheinlichen Einwänden und guten Fragen, alles auf einer Seite. Nutze diesen Skill, wenn der User sagt "bereite mich auf den Call vor", "Call-Vorbereitung", "wer ist mein nächster Termin", "Recherche zu [Firma] vor dem Gespräch", "Meeting-Vorbereitung", "prep me for this call", "sales call prep", "research this company before my meeting".

light0305 Bundle

Verify scholarly references and claim-citation support for Light stage 10. Use when auditing a manuscript, claim map, bibliography, DOI/arXiv/PMID/ISBN/URL, BibTeX/CSL, citekeys, chimeric or fabricated citations, retraction/correction alerts, or preparing a canonical citation registry for typesetting. Builds provenance-preserving inventories, confirms metadata with independent authoritative sources, distinguishes CONFIRMED/CONFIRMED-MISSING/UNAVAILABLE/UNRESOLVED, records Crossref update direction, and emits the citation gate plus delivery artifacts.

light0305 Bundle

Light 科研主线第 8 步·论文写作：围绕「如何让审稿人相信值得发表」组织，初稿→审稿人视角循环打磨； 每个 claim 都有证据、措辞强度匹配证据强度、绝不过度宣称。何时用：实验+分析做完要写论文 / 写/改摘要·引言· 贡献句·结论 / 担心「claim 无证据 或 措辞夸大」/ 要让贡献三处(摘要·引言·结论)一致 / 引言四段式(痛点→不足→ 洞察→贡献) / 要当审稿人自己挑一遍 / 论文初稿润色去 AI 腔/被动/语法。 触发词：写论文 / 论文写作 / 写摘要 abstract / 写引言 introduction / 贡献句 contribution / 写结论 / 润色 polish / 改写 / 措辞 / 过度宣称 overclaim / claim 无证据 / 审稿人视角 / 自我审稿 / 贡献一致 / hedge / 学术腔 / AI 腔 / 被动语态 / paper writing / draft。 核心纪律：**claim 无证据 = critical 诚信门**（spec §4.2，STAGE_GATES[8]=[claim_evidence,overclaim]）； 过度宣称 / 贡献三处不一致 = warn（critical 措辞红线在 research-ethics 交付门）；**措辞强度必须匹配证据强度**、 不显著只能报「未见显著差异」、绝不过度宣称；机检措辞有边界，逻辑/创新/论证终判仍需人/审稿人。 本技能是 **8→7（claim 无证据→result-analysis）/ 8→6（实现缺口→experiment-coding）回炉发起方**。

light0305 Bundle

Light 科研主线第 5 步·研究方案与实验设计：把 idea-critique 放行的 idea 与 data feasibility 拆成**能真执行、能写进论文、 能复现**的 question/estimand、实验矩阵与预注册包。何时用：idea 已通过审查要落地 / 要设计实验·消融·对比·敏感性· 泛化·鲁棒性 / 写研究方案 PROJECT_PLAN / 锁 primary outcome、排除/停止规则或 preregistration / 规划样本量、种子与统计功效 / 算实验算力预算 / 复现已有论文 / 担心 baseline 放水或假设推不翻。触发词：研究方案 / 实验设计 / 实验矩阵 / 假设 / 对照 baseline / 消融 ablation / 公平比较 / 可证伪 / 统计功效 power / 多少种子 / 复现 / reproducibility / research plan / experiment design / 可复现。核心纪律：**对照不公平(baseline 放水)/不可证伪 = critical 一票否决** （spec §4.2，STAGE_GATES[5]=[fair_baseline,falsifiable]）；消融不隔离/欠功效 = warn；功效是计划阶段反推非结果检验； lint 是启发式有边界，公平/可证伪终判仍需人/领域判断，绝不吹"证明了对照绝对公平"。

light0305 Bundle

Light 科研主线第 3 步·提 idea:从模糊方向/数据/文献**结构化发散**(激发算子系统生成,不是泛泛头脑风暴) → 产**值得做且做得成的分层候选 idea**(moonshot 冲刺/solid 稳妥/safe 保底),每个必答**为什么值得做·创新点· 比现有强在哪·解决什么具体问题·能投什么层次**,且**提出时就自带撞车前置自查**(最像的前作+delta,吃上游 literature-search 领域地图)。何时用:用户问"这个方向/数据能做什么" / 要创新点·研究思路·选题·突破口 / 帮我想 idea / brainstorm research ideas / 这 idea 行不行(先生成再送 idea-critique 严审)。触发词:提 idea / 想 idea / 创新点 / 研究思路 / 选题 / 突破口 / 差异化 / 这个方向能做什么 / 有什么可做的 / brainstorm / research idea / ideation / 新点子 / 立项。核心纪律:**不下 novel/无创新的最终判决**(那是 idea-critique 的 critical 门,生成端只产撞车 warn 信号);用**证据根→机制/假设 delta→信息增益→最小判别实验**谱系约束候选； 过 **innovation_engine 反拼接门**，把原创来源分型(新问题/新机制/新测量/新数据/新理论/跨域迁移/工程增量)与 claim 强度绑定； 数量/七角度只作 advisory，机制多样性才是硬门。

light0305 Bundle

Light 科研诚信与伦理全生命周期常驻红线门:在研究分诊、审批、采集、变更、分析、投稿、发布与出版后检查 学术不端/数据造假/统计自洽/结论夸大/幻觉与撤稿 引用/自我抄袭/隐私/版权/署名与 AI 披露/软著专利权属/论文工厂洗稿等风险,把"别造假别夸大"从口头建议 落成**可机检、可阻断、可被总控 run_checkpoint 聚合的机读门**(产 light.findings.v1,Critical fail → exit 1)。 何时用:投稿/camera-ready 前、数据或代码发布前、软著提交前、涉人或涉动物实验设计时——这些是硬闸门; 以及任意写作/分析/引用任务的后台诚信扫描。触发词:伦理 / 诚信 / 学术不端 / 造假 / p-hacking / 夸大 / SOTA / 撤稿 / 查重 / 抄袭 / 隐私 / IRB / 知情同意 / 署名 / AI 披露 / 论文工厂 / 软著权属。核心纪律:**信号≠定罪**, AI 不能自评 → 一律"机读门 + 人工复核";查不到写"待核查/UNRESOLVED",绝不编造;全程在线核实、零本地知识库、零付费 key。

light0305 Bundle

Light 科研主线第 1 步·文献调研:在线多源检索(OpenAlex/arXiv/Crossref/Europe PMC/DOAJ,全程免 key)→ 产出**不是论文列表,是可直接喂 idea 的"领域地图"**:近三年前沿 + 经典奠基 + 跨领域方法移植**三层分别 检索分别排序**,合成研究脉络 + 方法谱系 + 未解问题地图,揪出**最像你设想的那一篇**→喂 idea-critique 撞车预警,诚实标检索覆盖度。何时用:调研某方向 / 找综述 / 了解某领域有哪些工作 / 提 idea 前摸清前作 / 收集中英文论文·专利·标准·数据集·开源·竞赛方案·行业报告。触发词:文献调研 / 文献综述 / 调研方向 / 领域地图 / 研究现状 / 有哪些工作 / 相关工作 / related work / literature review / survey / 前沿 / 综述 / 找论文 / 撞车 / 新颖性摸底 / 跨领域 / 检索式。核心纪律:不臆造 DOI/被引(查不到写 unknown);三层分别排序 不一锅 relevance;撞车只产**信号**不下 novel 判决(归 idea-critique);覆盖度按真实 HTTP 码诚实标。

lytics Skill

Research-driven authoring of Lytics webhook templates -- fetches destination docs, drafts and tests the transform, and emits a ready-to-go webhook job blueprint. Use when the user wants to send Lytics audience triggers or enrichment requests to a custom webhook destination (e.g., Qualtrics, Slack, custom CRM).

manutej Bundle

Systematic analysis patterns for categorical AI papers (Gavranović, de Wynter, Bradley, Zhang). Use when analyzing academic papers on categorical deep learning, extracting categorical structures from AI research, mapping meta-prompting concepts to category theory, or building comprehensive literature reviews on categorical approaches to AI.

marketingskills Skill

Produce a focused refresh brief for a declining page. Use when Codex needs to research SERP intent, competitor content, entity coverage, and internal link opportunities to create an actionable page refresh plan.

fw1201 Bundle

將學術研究資料（文獻關係、研究架構、概念框架、資料流程、統計結果） 視覺化為精確的學術圖表，優先調用 Excalidraw MCP 生成手繪風格圖， 或生成可嵌入論文的 SVG/PNG 圖表。 當使用者提及「研究架構圖」「概念框架」「文獻關係圖」「理論模型」 「研究流程圖」「資料視覺化」「畫圖」「論文圖表」「研究地圖」 「系統性文獻回顧」「SLR 流程」「PRISMA」時觸發。 適用情境：碩博士論文、期刊論文、研討會論文、研究計畫書。

fw1201 Bundle

嚴格查核學術文獻的準確性與引用格式，透過 WebSearch、Consensus MCP 進行 多源交叉驗證，逐一確認作者/年份/標題/期刊/頁碼，並驗證目標引用格式 (APA 7th / MLA 9th / 臺灣學位論文 / Chicago) 是否正確。 查核不到的文獻直接標示「查無」，格式錯誤直接指出哪裡錯。 當使用者提及「查文獻」「驗證引用」「確認參考資料」「文獻格式對嗎」 「APA格式」「MLA格式」「引用正確嗎」「幫我查一下這個文獻」 「格式查驗」「文獻清單」「參考書目」「bibliography」「references」時觸發。

larrysequino Skill

Turn raw key=value application logs into a table an on-call engineer can sort during an incident, then summarize what changed in the minutes before the page fired. Use when someone pastes a wall of log lines and asks what happened. NOT for setting up log shipping or retention (use observability-setup for that), and NOT for writing the postmortem afterward.

opensealai Bundle

Use this skill when the user requests a multi-stage content plan or production programme combining research, videos, carousels, and editor handoff. Coordinate only the requested creative deliverables.

policyengine Skill

Find and cite PolicyEngine's published blog posts and research articles as evidence or proof points — for talks, pitches, grant narratives, and "has PolicyEngine written about X?" Triggers: "find a blog post", "PolicyEngine research on", "published analysis", "proof point", "has PolicyEngine written about", "cite our work on", "which post covers", "blog post about".

rlaope Skill

Feature validation gate — research, define purpose, stress-test from real user perspective before building