Research & Search

aryaniyaps Bundle

Plan and synthesize evidence-grounded product research. Use when deciding what evidence is needed, designing actor walkthroughs, grounding claims in a repository or live product, analyzing user-provided references, modeling users and tasks, or communicating findings without inventing data. Use lamina-evaluation instead to judge a built product, and lamina-ux to design interaction behavior.

aryaniyaps Bundle

Judge product usability and evidence quality. Use when running Persona-based walkthroughs on a built product, planning an expert heuristic review, defining evidence-backed success metrics, or checking quantitative claims without inventing measurements. Use lamina-research to plan or synthesize evidence collection and lamina-ux to design interaction behavior.

babyracoonbbq Bundle

Create or update a source-grounded Obsidian review of a researcher after at least ten of their papers have complete literature notes. Use when evaluating a potential supervisor, collaborator, or researcher; synthesizing research themes, trajectory, recent directions, representative works, collaborators, author roles, student-era first-author work, methods, impact, industry fit, and open questions; or building a supervisor hub note with verified bidirectional links. Enforce a local-first reading manifest and an audited per-paper evidence ledger before any web research or synthesis. If fewer than ten analyzed notes exist, stop and recommend $survey-researcher-papers first.

roadofriot Skill

Perform reliable current technical research using authoritative sources.

quantumbfs Skill

Use when the user asks to review a research-paper draft (typically LaTeX) or a related text (reply-to-referee, thesis chapter, technical note). Walks a fixed checklist of common issues — notation, figures, citations, structure, equations, style, reproducibility — and inserts inline author-comment reminders at locations that fail each check. Triggers on phrases like "review my paper", "check my draft", "apply the checklist", "review as a PRB reviewer".

raxxid-ux Skill

Turns raw UX research (interview notes, survey answers, observations) into simple user insights and pain points. Use when you have research data and don't know what to do with it, or when you're new to research synthesis and need a clear step-by-step method with examples instead of a blank page.

raxxid-ux Skill

Synthesizes UX research into insights with rigor — weighting evidence strength, spotting contradictions, and stress-testing conclusions before they drive design decisions. Use when you already know the basic affinity-mapping method and need to go deeper — validating insights, resolving conflicting data, or defending research findings to stakeholders.

raxxid-ux Skill

Breaks a UI/UX or branding project into simple weekly phases (research, design, identity, application, guidelines) so the work feels organized instead of overwhelming. Use when starting a new design project and don't know how to structure your time, or when a project feels chaotic and you need a clear plan to follow.

fengmo11 Bundle

Automatically route natural-language paper research requests to the right module in a complete publication workflow for computer science, engineering, mechanical, and general academic manuscripts. Use for requests about topics, literature, citations, figures, palettes, language polishing, AI-voice cleanup, reviewer simulation, revision, response letters, re-review, and submission gates without requiring the user to name a specific module.

edonadei Bundle

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

m1nga Skill

Conclude the last N rounds of the CURRENT conversation, in Chinese by default, AND hand back 5 evidence-based insights for working more efficiently with Claude Code. Read back over the recent exchanges — both the user's questions AND the assistant's answers, including code written, decisions made, and progress — then give a tight conclusion (what was asked, what was actually done and verified vs merely proposed, current state, open decisions) followed by 5 concrete Claude-Code-usage insights drawn from patterns in those rounds. N defaults to 4 and is read from what the user says (前4轮 / past 3 / 前面5个来回 / 前面两个问题). This is an IN-conversation recap, read-only — it never changes files, and it is NOT a cross-session daily digest. Run whenever the user says 总结前面N轮 / 总结一下前面 / 小结一下 / 结论一下 / 回顾前面几轮 / 前4轮 / 这几轮做了啥 / conclude the last N rounds / recap the last few rounds / summarize what we just did / catch me up on this thread — even without naming the skill. Works identically in Claude Code and Codex.

netclaw-dev Bundle

REQUIRED when the user asks you to search, look up, verify, buy, shop, compare, price-check, find current info, or check facts online. Contains citation format rules for web_search and web_fetch.

alephic-ai Skill

Review a pull request for correctness and style, then summarize the findings. Use when the user asks for a PR review, mentions reviewing a diff, or wants feedback on changes before merging.

jinjie0703 Bundle

Act as a strict Knowledge Editor to extract high-value, reusable, and timeless engineering knowledge from conversation transcripts into structured notes. Use when asked to extract insights, curate technical decisions, or summarize engineering trade-offs from chat logs.

jonny-1812 Skill

Get a complete customer profile by aggregating contact details, conversation history, notes, and relevant knowledge base articles into a single unified view. Use when the user wants to see everything about a customer, look up a contact's full history, or prepare for a customer call.

mikiagent Bundle

Manage large or noisy working context for repository research, long documents, logs, datasets, multi-file investigations, and long-running coding tasks. Use when the task risks context overload, requires evidence from many locations, or would benefit from probing/searching/filtering external sources before reading them deeply. Build a bounded working set by probing structure, narrowing candidates, admitting only relevant evidence, delegating separable scopes when useful, synthesizing results, and validating evidence coverage. Prefer simple direct reads for small localized tasks and do not add recursive scaffolding unless it earns its complexity.

catch-the-wave Bundle

TRIZ-powered product architecture and design decisions. Use when facing product trade-offs ("more features vs simplicity"), choosing between design approaches, resolving UX contradictions, making architecture decisions, or when the user says "TRIZ", "trade-off", "contradiction", "can we have both", "approach A vs B", or asks you to evaluate competing design directions. NOT for generic engineering — this is for product craft.

catch-the-wave Skill

Advanced Jobs To Be Done methodology knowledge base. Use when analyzing products, markets, customer segments, or making product decisions. Provides access to complete AJTBD framework and expert prompts.

qoli Bundle

Locate, inspect, and safely summarize local Codex conversation logs by UUID. Use when a user provides a Codex conversation/thread UUID and asks to read, explain, recover, continue, hand off, 查看、接續、恢復、回看、理解 prior Codex Desktop/CLI thread context without exposing raw private transcripts.

qoli Bundle

Broad local Codex session search and safe activity summarization with distill. Use when the user asks what they did today, yesterday, recently, this week, or during a time range; asks to summarize Codex work history without providing a UUID; says things like "看看昨天做什麼", "今天做了什麼", "最近我在忙什麼", "整理一下這幾天的 Codex 對話"; or wants a dominant workstream summary across many local Codex Desktop/CLI sessions. For exact UUID recovery, hand off to codex-conversation-lookup instead.

tradecatlabs Bundle

严格自然语言数学证明。用于证明或审查 theorem/lemma/proposition、补齐证明草稿、构建证明义务与依赖图、寻找反例、检查量词/常数/边界情况，或判断命题是否必须削弱。

tradecatlabs Bundle

Math Derivation

tradecatlabs Bundle

可重跑的数学计算与反例实验。用于 SymPy 精确代数/微积分/方程/矩阵、NumPy/SciPy 数值方法、mpmath 高精度交叉检查、OEIS 序列识别、有限范围反例搜索和计算证据记录。

tradecatlabs Bundle

数学形式化与 proof-assistant 验证。用户要求 Lean 4/Mathlib、formal proof、kernel check、无 sorry 编译，或需要把自然语言定理切成可形式化定义和引理时使用。缺少 Lean 工具链时必须 fail-closed。

tradecatlabs Bundle

数学研究任务路由器。用户提出找问题、查文献、推公式、做计算、写证明或形式化验证，但当前瓶颈尚未明确时使用；每次只选择一个主 skill。

tiangong-ai Bundle

Adapt a managed Tiangong Auto Research workflow to a native WorkBuddy or CodeBuddy producer running in Default Permission mode, especially when independent review needs the explicit sandbox-bridge transport. Use only as a thin router to the project-installed tiangong-auto-research Skill; do not use for unrelated WorkBuddy tasks or standalone searches.

mangowhoiscloud Skill

Research process for exploring related patterns across 4 frontier harnesses (Claude Code, Codex, OpenClaw, autoresearch) and performing GAP analysis before feature implementation. Triggered by "research" ("리서치"), "gap", "frontier", "harness", "case study" ("사례 조사"), "pattern exploration" ("패턴 탐색"), "comparative analysis" ("비교 분석") keywords.

arcasilesgroup Bundle

External evidence with citations via a 4-tier escalation (local → free MCPs → web/Exa → NotebookLM autonomous deep research, launched first / harvested last). Every claim sourced [N] or marked [unsourced]; output ends with 3 cited recommended directions. Trigger for 'what does the state of the art say about', 'compare options for', 'find sources on', 'investigate this question', 'research this'. Use for questions whose answer lives OUTSIDE the codebase. Not for codebase exploration; use /ai-explore instead. Not for refactors; use /ai-simplify instead. Not for business-logic debugging; use /ai-debug instead.

stiron92-byte Bundle

관심 분야의 데이터를 자동 수집 → 분석 → 트렌드 리서치 보고서 생성. "~트렌드 알려줘", "~시장 분석해줘", "~뭐가 뜨고 있어?", "~리서치해줘", "데이터 수집해줘", "시장 조사", "경쟁사 분석", "투자 리서치", "트렌드 분석", "요즘 뭐가 핫해?", "~분야 어때?", "~시장 현황", "~동향 파악", 화장품 트렌드, 주식 분석, IT 트렌드, 식품 트렌드, 부동산 시장, 게임 트렌드, beauty trend, market research, competitor analysis, investment research, 데이터 자동 수집, 자동 분석, 리서치 보고서, 시장 브리핑, 산업 분석. content-research 스킬과 다른 점: 이 스킬은 "데이터 기반 분석 보고서"를 생성하며, 과거 동향 → 현재 트렌드 → 미래 예측 구조의 심층 리서치를 제공한다. 자동화 요청 시 GitHub Actions + 수집 파이프라인 코드도 생성 가능.

stiron92-byte Bundle

Use when the user wants content ideas, topic suggestions, trend research, or news collection. 트렌드 찾기, 콘텐츠 리서치, 유튜브 주제 선정, 유튜브 영상 주제 추천, 유튜브 컨텐츠 뭐 만들지, 어떤 컨텐츠가 좋을지, 영상 주제 뽑아줘, 블로그 기획, 블로그 글감, 뉴스레터 발행, 뉴스레터 소재, 뉴스 자동 수집, 뉴스 정리, 관심 분야 뉴스, 트렌드 분석, 요즘 뜨는, 이번 주 트렌드, 콘텐츠 아이디어, 콘텐츠 캘린더, 컨텐츠 추천, 컨텐츠 기획, 요약 브리핑, 식품 트렌드, 시장 브리핑, 핫한 여행지, 주목할 제품, RSS 수집, YouTube topics, content research, trending topics, content calendar, what content to make, blog planning, newsletter.

soyonaoc Skill

Use when looking up astronomy or physics papers by bibcode, arXiv ID, DOI, title, author, abstract, citation metadata, or when repairing BibTeX/reference entries with ADS/SciX or arXiv records.

theworstprogrammerever Bundle

Create, inspect, and update durable filesystem notes for Codex continuity across sessions. Use when the user asks Codex to remember, persist, record, save for later, create a durable note, update a local memory/todo store, summarize setup state, maintain a runbook, or standardize notes that future agents should read after context loss.

tyrantlucifer Bundle

Use when the user wants to publish a WeChat personal-subscription article from a topic, Feishu doc, notes, or existing draft. Turn research or source material into a ready-to-publish WeChat article and, when credentials allow, push it to the WeChat Official Account draft box with title/digest/cover/author prepared.

shaddyx Skill

Research topics using web search tools.

victorbuto Bundle

Поиск и оформление трендов по методике «Аве Мария»: SPICE-уточнение, сужение областей, верификация ключей человеком, поиск по 4 вариантам источников (каталог, Telegram, отраслевая пресса, глобальный), сбор сигналов, отсев по тирам, синтез трендов с оценками. Триггеры: «найди тренды», «карта трендов», «трендвотчинг», «тренд-рисёрч», «выяви тренды в категории/рынке», «trend research», «trend map», «сигналы трендов». НЕ для быстрых fact-check вопросов (WebSearch) и не для общего deep research без трендовой задачи (Deep-web-search).

victorbuto Bundle

Advanced keyword generation and web search using the Slice Method. Use when the user needs to generate effective search queries, find information beyond surface-level results, or bypass commercial noise in search engines. Triggers on requests for "search keywords", "find information", "research", "search strategy", or when the user struggles to find relevant results with basic searches. This skill focuses on search execution without fact-checking — pair with a fact-checking skill for verification.