Research plugins

분야·기간(날짜)·키워드·venue에 '○○ 관련 논문만' 주제 조건을 걸어 논문을 찾고, 공개 PDF를 '논문제목(venue).pdf'로 references에 받거나 DOI 표로 정리한다. ICAIF·Journal of Forecasting 포함.

1 skill

Source-tier classification + independent-verification rubric for any external signal before you act on it. Tier gating, corroboration math, paywall discipline. Not investment advice.

1 skill

A canonical 7-part investment thesis structure (claim, mechanism, fit, invalidation, sizing, asymmetry, conviction levers) that renders at three depths: reference file, memo, chat. Not investment advice.

1 skill

Run omics and spatial-omics analyses with full provenance, build a self-contained HTML report, then Ask, Edit, Review and Translate it in the page with the same Claude Code session.

1 skill

Grade any pundit's annual predictions at three bars against the year's public evidence, with receipts.

1 skill

对任意主题做深度、多来源、经交叉核查的调研,产出带引用、按置信度分级的报告。五阶段流水线:把问题分解成 4-8 个子问题 → 跨渠道(web/github/news/academic)并行 fan-out 调研 → 对每个发现做对抗式核查(证伪而非确认,发现者≠核查者)→ 交叉验证+圆桌综合、标注分歧 → 输出 HIGH/MEDIUM/LOW/CONTESTED 分级的引用报告。Provider-agnostic:同一份 skill 在 Claude Code、Kimi(kimi -p)、Codex(codex exec)三端都成立;fan-out 与核查阶段可跨模型互查(claude 的发现让 codex/kimi 证伪,反之亦然),对方模型作独立第二视角。当用户想「深度调研 / deep research / 全面调研 / 多角度调研 / research roundtable / 帮我把某主题查透并给带引用的报告」时使用。调用前:若问题欠具体(如「买什么车」却无预算/用途/地区),先问 2-3 个澄清问题收窄范围,再把澄清结果织进 args。

1 skill

Saves YouTube transcripts, video details and comments, and news and blog articles, to a local library Claude can search, and checks your topics every night, so Claude can summarize, fact-check and spot trends across them.

1 skill

Kitap ve belgeleri (PDF, EPUB, DOCX, HTML, Markdown, TXT, RTF, MOBI/AZW) aşamalı açılan yapılandırılmış ajan becerilerine dönüştürür: çerçeveler, zihinsel modeller, ilkeler, teknikler, bölüm özetleri, sözlük ve karar kartı. Kaynak: virgiliojr94/book-to-skill (MIT).

1 skill

네이버 블로그 검색·본문 읽기·상위노출 분석·이미지 받기 (Claude Code · Claude 앱 Cowork)

1 skill

Build calibrated, multi-lens, uncertainty-adjusted views on any topic via first-principles lens enumeration, a persistent lens library, and parallel per-lens research agents.

1 skill

論文1本を、本文に書かれた事実だけを根拠に深く読み解き、日本語のレポート（HTML）にまとめるスキル

1 skill

軽い知識の質問に、形と深さをそろえた答えを返し、数字・年・固有名詞を出典の本文と照合するスキル

1 skill

Survey the products that already exist in a category, extract each one's complete feature inventory, and write it up as a build spec with feasibility marks and a recommended build order.

1 skill

Estimate what a stock is worth by writing down what has to be true for today's price to make sense. Picks between sum-of-the-parts, normalized earnings times one multiple, and finite-life NPV, then reports a bear/base/bull range with falsifiable checkpoints.

1 skill

Agent skill for Nabu, a local, read-only library of ancient-text corpora: install, the 14 MCP tools, license-class etiquette, honest limits.

1 skill

Map the literature of a research field or thesis niche: fan-out theme searches over arXiv / INSPIRE-HEP / Semantic Scholar / CiNii / J-STAGE build a persistent local corpus (stdlib-only fetch script, no pip installs); an LLM subagent fan-out classifies every paper into a corpus-derived taxonomy with a 0–3 relevance score; deliverables are a temporal/topical map figure, a curated reading-list CSV, a markdown briefing, and a final answer grouping the top papers by how they connect to the user's own work. INSPIRE-HEP supplies citation counts natively (no OpenAlex key needed for physics).

1 skill

面向日常学习、知识获取与好内容拆解沉淀的通用技能：支持「通道 A 主动求知（问题/概念 -> 快速多维检索四要素）」与「通道 B 素材拆解（视频总结/脚本/文章/URL -> 知识卡 + 制作技巧）」双通道输入，统一以「极简 TL;DR + 核心痛点问答（3–5 问）+ 立即可用清单 + 可选脚本/表达技巧拆解」直击痛点，并分类沉淀到 ~/Development/Personal/knowledge-vault/。

1 skill

Ouroboros V2 saddle-point escape benchmark and publication package for Genesis Conductor by @invariantx. Fixed-seed reproducible 20D Ackley+saddle tests with p-bit solvers (Chiral p-bit, ER=EPR Hypersphere, HITL Spatial), Barnes-Hut PCA heuristic, full falsifiability contract, committed results, manuscript PDF, and automated Zenodo/ORCID publishing. Validates topological/thermodynamic reasoning claims with deterministic outputs and explicit rejection criteria. Integrates with seismic-log S-ToT verification and broader Genesis Conductor research artifacts.

Research, search, and analysis specialists - market research, competitive analysis, trend forecasting

Research, search, and analysis specialists - market research, competitive analysis, trend forecasting

Company research using Exa search. Finds company info, competitors, news, tweets, financials, LinkedIn profiles, builds company lists.

Research, search, and analysis specialists - market research, competitive analysis, trend forecasting

Research, search, and analysis specialists - market research, competitive analysis, trend forecasting, and idea validation

Research, search, and analysis specialists - market research, competitive analysis, trend forecasting, and idea validation

Research, search, and analysis specialists - market research, competitive analysis, trend forecasting, and idea validation. (VoltAgent, 25.3K★, MIT, fijado al commit auditado 82b7382 — mismas condiciones que voltagent-core-dev.)

Generated distribution of the Wildcat Promise Machine skills runtime. Every file is rebuilt hourly from wildcat-finance/skills; nothing here is authored.

Generated distribution of the Wildcat Promise Machine skills runtime. Every file is rebuilt hourly from wildcat-finance/skills; nothing here is authored.

Generated distribution of the Wildcat Promise Machine skills runtime. Every file is rebuilt hourly from wildcat-finance/skills; nothing here is authored.