Research & Search

zeno-zhu Bundle

用确定性命令操控网页版 ChatGPT（复用已登录会话）。适合需要外部第二意见、复杂决策、代码评审、预编程、Deep Research 或图片生成的场景：把文件 + 问题交给网页版 GPT，拿回技术指导、代码或产物。触发词：问问 ChatGPT、让 GPT 看看、把这份文件丢给 GPT、让 GPT Pro/Thinking 想想、让 GPT 出图、deep research、外部意见、第二意见、评审这个方案。

archmax-ai Bundle

Read, write and reorganise a shared knowledge base — a folder of plain notes, one per topic, each with a short labelled header and links to related notes, that people and software can both use. Read this before adding, editing, moving or deleting notes in a knowledge base that follows the Open Knowledge Format (OKF).

ilovefiniki Bundle

Download, inspect, and summarize Instagram Reels locally with zero personal account risk and built-in rate-limiting guards. Use whenever the user provides an Instagram Reel link or asks to inspect, summarize, or transcribe an Instagram Reel.

why20261 Bundle

通过怪奇信息查询和分析快手视频、达人、评论和品类机会研究。用户提到快手、KuaiShou或Kwai 数据分析、市场调研、选品、找品、爆品、趋势、市场容量、竞争结构等数据形成经营判断时使用，依据快手真实返回的数据形成分析结论。支持三大能力：(1) 关键词搜索视频，可按点赞数、发布时间、视频时长筛选排序；(2) 博主作品抓取，按主页链接获取公开作品列表；(3) 视频评论分析，按视频链接获取评论内容与互动数据。

andersonlimahw Bundle

Run an adversarial naming sprint to find a defensible brand name for a company or product. Use when the user says "naming sprint", "find a name", "name my company", "name this product", "rebrand", "brand name", "escolher nome", "nomear a empresa", or asks to validate a shortlist of candidate names. Generates a large longlist, funnels it down with an explicit scorecard, then tries to destroy every survivor with collision research across software, dev ecosystems, companies, app stores, domains and trademarks before recommending anything. Refuses to recommend a name that has not been researched.

why20261 Bundle

通过怪奇信息查询和分析抖音视频、达人、评论和品类机会研究。用户提到DouYin或抖音 数据分析、市场调研、选品、找品、爆品、趋势、市场容量、竞争结构等数据形成经营判断时使用，依据抖音真实返回的数据形成分析结论。支持四大能力：(1) 关键词搜索视频/图文，可按点赞数、发布时间、视频时长、内容类型筛选排序；(2) 实时热榜查询，获取抖音热搜词条与热度数据；(3) 博主作品抓取，按主页链接或 sec_uid 获取公开作品列表；(4) 视频评论分析，按视频链接或 aweme_id 获取评论内容与互动数据。

kewang0622 Skill

End-to-end MRI research assistant — take a project from idea to a published paper, and help write it. Use this WHENEVER the user wants to plan or run an MRI (or MRI + machine-learning) study and publish it: literature survey and finding the gap, forming a hypothesis/claim, designing experiments (datasets, baselines, metrics, ablations), running them, analyzing results, making figures/tables, and drafting + submitting a manuscript to a venue such as CVPR, MICCAI, NeurIPS, or Magnetic Resonance in Medicine (MRM). It orchestrates the whole flow and hands off to the specialized MRI expert agents. Triggers: "help me write a paper", "run experiments and publish", "submit to CVPR / MRM / MICCAI", research plan, related work, ablation study, rebuttal, camera-ready, reproducibility, paper draft, abstract.

andersonlimahw Skill

UX research methodologies and frameworks. Use for user journey mapping, persona creation, heuristic evaluation, usability testing plans, and competitive analysis.

aribajahan Skill

Reads across the dated reports the other scans produced and says what the pattern is, why it matters, and what's worth writing about. Conversational by default; say "write it" for something short in writing. Takes a window, such as "synthesis september" or "synthesis last two weeks". Use whenever you want to think out loud about a piece before drafting it, or want to know what the research turned up.

john-walks-slow Skill

需求调研设计工作流。进行中等以上规模需求开发、架构设计和重构前必须遵守此流程制定计划。

ainxin-1 Bundle

动手写代码前做一次对称决策预研 / Symmetric pre-flight research before writing code。钉死一句话需求 → 按「标准/协议 → 标准库 → OS 原生 → 项目已有代码 → SDK → 框架 → 第三方库 → 开源项目 → 自研」由便宜到贵的层级找现成方案并外部核实维护状态 → 实测基线并把「做」与「不做」两侧同口径摆出来 → 输出 复用/组合/改造/自研/不做/暂缓 六选一结论。当用户开新项目或新模块、问「有没有现成的库」「要不要自己造轮子」「这个功能值不值得加」「现在改还是先跑一段看」、做方案选型或可行性判断时使用；also use for build-vs-buy, tech stack selection, feasibility, "should I write this myself", dependency-adoption decisions；实现中途冒出技术风险（要引新依赖/改架构/动认证或网络）时也触发。纯改 bug、修报错、纯重构、用户已指定依赖或已定好实现方式时不要用。

ibk015 Bundle

Plan, run, cross-check and write up a Systematic Literature Review (SLR) using the Wolfswinkel et al. (2013) Grounded Theory method, PRISMA 2020 reporting, and Gioia-style coding. Use whenever the user mentions SLR, systematic literature review, systematic review, literature review for a thesis or paper, PRISMA flow diagram, search string, Scopus or Web of Science search, inclusion/exclusion criteria, title and abstract screening, dual reviewers or cross-checking a screening sheet, coding literature, concept matrix, or writing the methodology section of a review, even if they do not say "systematic".

jiangeplus Bundle

Equity research orchestrator. Routes stock research requests to the right module and enforces analyst discipline: PM seven questions, variant perception, data traceability, rating with target price, and disclaimers. TRIGGER when: the user asks to research/analyze a stock, write an initiation or earnings note, value a company, build an investment pitch or memo, size a position, track a thesis, or screen for ideas. DO NOT TRIGGER for: general financial news summarization with no stock-specific conclusion, personal portfolio hand-holding, or requests for price predictions without analysis. 触发词：股票研究、个股分析、首次覆盖、估值、投资论点、评级、目标价、研报、持仓跟踪、选股。

bolaflame1 Bundle

Use this skill for "add a card", "create a card for this paper", "card for DOI", "card for PMID", "retrieve this paper", "add this paper to the cards", "update the card", "verify the card", "check the BibTeX", "make a card", "pull this paper", "download this paper to cards", or when the user mentions card.md, source.md, meta.json, card slug, key_papers.bib, or asks to add a paper to a project's reference library.

bolaflame1 Skill

OpenCite Skill

bolaflame1 Bundle

Use this skill for "new manuscript", "start a paper", "scaffold a manuscript", "create build_doc", "new project manuscript", "set up manuscript builder", "create manuscript template", or when the user wants to start writing a new academic paper and needs the build_doc.py infrastructure.

bolaflame1 Bundle

EndnoteLink Skill

jcaraballo113 Bundle

Read-only overview of review comment status on the current branch's open PR. Groups comments into addressed / pending / in-discussion / deferred-or-dismissed so you can see where things stand before acting. Use when the user says "show PR review status", "where are we on the review", "what's left to address", "summarize review progress", or comes back to a long-running PR and needs context. For active triage, fixes, and posting replies, use `triage-pr-comments` instead.

kitze Skill

ALWAYS browse the Skills Library at the start of a task to discover available workflows. Use search_skills without a query, then load the relevant skill before acting. Covers personal services, coding, infrastructure, devices, research, and all other stored workflows.

wundercorp Bundle

Search arXiv papers by keyword, author, category, or ID.

nwave-ai Bundle

Canonical AT completeness gate — research-anchored 7-category taxonomy (C1-C7) + 15-item mechanical checklist. Paradigm-neutral. Drives acceptance-designer reviewer verdict deterministically.

wundercorp Skill

Hybrid local search over notes, docs, and transcripts.

cellebrite-labs Bundle

Reverse engineering assistant powered by Ghidra. Use for binary analysis, decompilation, vulnerability research, auditing compiled code, renaming symbols, annotating disassembly, cross-references, or any RE task - even without explicit mention of Ghidra.

wundercorp Bundle

Read RSS, Atom, JSON feeds; discover feeds behind a page.

wundercorp Skill

Scrape sites with stealth browsing and Cloudflare bypass.

wundercorp Bundle

Ground answers and documents in cited, verifiable sources.

wundercorp Skill

Query and edit a SiYuan knowledge base via its API.

wundercorp Bundle

Free keyless web, news, and image search via ddgs.

wundercorp Bundle

Serve an interactive codebase knowledge graph web UI.

wundercorp Bundle

Follow the money via public records and sanctions data.

wundercorp Skill

Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.

wundercorp Bundle

Passive recon of subdomains, SSL certs, WHOIS, and DNS.

inno3dtony-rg Skill

치과·구강 스캐너 시장의 **숫자와 출처가 있는 조사 결과**를 산출하는 스킬. 담당: 시장 규모, CAGR, 점유율, 경쟁사(3Shape·Medit·iTero·Dentsply) 스펙·가격 비교표, 국가별 인허가 규제 현황, DSO 동향, 임상 논문 수치 해석. 모든 수치에 출처와 조사시점을 붙이고, 미확인 값은 [확인 필요]로 표기한다. 넘길 곳: 여러 출처를 훑는 장문 리서치 보고서 작성은 `deep-research`(이 스킬은 치과 도메인 수치 해석 담당), 조사 수치를 넣어 만드는 영업 문서는 `dental-sales-strategy`, 특정 국가 진입 실행 계획은 `dental-business-development`.

wundercorp Bundle

Write ML papers for NeurIPS/ICML/ICLR: design→submit.

wundercorp Skill

Gateway to 400+ genomics and computational biology skills.

wundercorp Bundle

Free keyless meta-search aggregating 70+ engines.