Research & Search

faaz17 Skill

Where to find and how to verify secondary data for the MBS4820 Capstone — FedEx SEC filings and investor relations, GCC/UAE logistics and e-commerce market data, Statista/Passport/IBISWorld, World Bank LPI, UAE government statistics, and academic databases. Includes the source-quality hierarchy, the data-log protocol, and rules against fabricated figures. Use when researching market size, company financials, competitor data, industry trends, or any quantitative claim.

iamk77 Bundle

The experiment-design lens: turn the surviving method into a protocol that produces evidence a reviewer believes — for any field that runs experiments to publish (ML, optimization, operations research, systems). Use after crucible lands a method, when planning the experiments, or stress-testing a plan. The one shift: you write down what counts as EVIDENCE before you look at the data — the protocol (claims, instances, baselines, metrics, and the bar for support OR refutation) is FROZEN before the main run, because choosing a good story after the fact is p-hacking. The keystone is a firewall between EXPLORATION (generates hypotheses, never enters the paper) and CONFIRMATION (survivors, fresh seeds). Triggers on "design the experiments / experiment protocol", "which baselines / is this comparison fair", "p-hacking / pre-register", "is my evaluation honest".

iamk77 Bundle

The research-gap prospecting lens: find a defensible, fundable research gap BEFORE you sink months of compute and writing into it — for any field where you run experiments to publish (machine learning, combinatorial optimization, operations research, systems, scheduling). Use when choosing a topic, doing a literature review, or stuck for an idea — or when stress-testing a gap you already have. The one shift: a gap is NOT read out of the literature, it is MINED out — by running fixed extraction strategies in parallel — and then it must SURVIVE an adversarial "prove it's already been done" attack before you bet on it. Triggers on "what should I work on", "find a research gap / direction", "literature review", "is this novel / has anyone done X".

christopheralphonse Skill

Unified founder-mode product review. Orchestrates intake, interrogation, scope mapping, strategy selection, opportunity surfacing, and artifact writing. Delegates parallel research to sub-agents. Keeps user in control of every scope change.

christopheralphonse Skill

Research how to implement a phase or planning topic before detailed planning. Produces RESEARCH.md for downstream plan and review skills.

iankiku Skill

(forwward) Turns transcripts, rough notes, or voice memos into a clean summary with decisions, action items (owner + deadline), and open questions. Use when the user pastes unstructured notes or asks "summarize this meeting", "meeting notes", "what were the action items", "write up from this call", "debrief", "what did we decide". Works for any meeting type — standups, 1:1s, client calls, all-hands, retrospectives.

niekcandaele Bundle

Sweep a repository's open dependency PRs (Renovate, Dependabot, or similar): tier each by risk, merge the trivial green ones, research and verify the rest, and leave one upserted comment per PR a maintainer can act on in under five minutes.

niekcandaele Skill

Summarize all changes in current branch compared to base branch

niekcandaele Skill

Generate user-facing release notes from technical change information (commits, PRs, diffs, branch comparisons, or raw text). Goes deep — follows commit references to PRs, issues, and bug reports to understand the full story behind each change, then produces narrative prose that communicates what changed and why it matters. Works with GitHub, GitLab, and Jira. Use this skill whenever the user asks for release notes, changelogs, "what's new" summaries, or wants to communicate changes to users, stakeholders, or customers — even if they just say "write up what changed" or "summarize the release."

the-hugin Bundle

Search the internet and news using a local SearXNG instance. Use when the user wants to search the web, find current information, search for news, or research a topic without depending on third-party APIs.

the-hugin Skill

Manages context in long sessions by suggesting /compact at logical task boundaries — after research phases, debugging, or phase transitions. Prevents losing critical context mid-implementation.

the-hugin Skill

Academic research assistant for literature reviews, paper analysis, and scholarly writing. Use when reviewing academic papers, conducting literature reviews, formatting citations (APA/MLA/Chicago), or writing research summaries.

thettwe Bundle

Generate a Conventional Commits message from the staged diff and create the commit after user confirmation. TRIGGER when the user says "commit these changes", "commit this", "generate a commit message", "stage and commit", "commit with CC", "write a commit message", "summarize my diff into a commit", "/nyann:commit". Do NOT trigger on "git commit" in an informational context or when the user is just asking what a commit message means. DISAMBIGUATION: if the user mentions BOTH branch creation AND committing in the same message (e.g. "start a branch and commit this", "new branch + commit"), route to the `new-branch` skill FIRST; `commit` will take over after the branch is created. When nothing is staged, guide the user to stage first rather than silently staging everything.

arndvs Skill

Cache expensive exploration into a research document before building. Use when asked to 'research', 'investigate before building', 'gather context', 'flush unknowns', or before a large feature where unknowns need flushing.

aws-samples Skill

Write a full document draft, incorporating research and outline if available. Invoke ONLY via the /ai-draft slash command. Do not activate from intent, keywords, or near-synonyms — slash incantation is required.

aws-samples Skill

Research a codebase or a topic, producing structured findings; emits SDD phase suggestions only when asked. Invoke ONLY via the /ai-research slash command. Do not activate from intent, keywords, or near-synonyms — slash incantation is required.

captainflasmr Skill

Write and structure academic papers, theses, and research documents. Trigger on phrases like "academic writing", "scholarly writing", "research paper", "thesis writing", "academic paper structure".

captainflasmr Skill

Organize information, evaluate sources, and synthesize findings on any topic. Trigger on phrases like "research assistance", "research this topic", "literature review", "synthesize findings", "source evaluation".

captainflasmr Skill

Human-centered design thinking guidance through empathy, ideation, prototyping, and testing. Trigger on phrases like "design thinking", "design thinking process", "human-centered design", "user research", "design sprint".

captainflasmr Skill

Use Emacs for academic writing, research, and publication preparation with Org-mode and LaTeX. Trigger on phrases like "academic writing in emacs", "emacs academic workflow", "research in emacs", "org-mode thesis", "emacs latex writing".

celestialdust Skill

Map the codebase/DB exactly as it is today — a goal-blind, fact-only survey produced by parallel read sub-agents that never see the design, each persisting its own findings to docs/features/<slug>/research/ — BEFORE any design decision is made. Use this the moment Spec starts, after intent.md is signed and before spec-grilling opens the decision tree; also whenever someone says "research the codebase," "do the codebase dive," or is tempted to decide against a guess about how the code works. Run it AGAIN at the head of Plan, before plan-breakdown cuts slices — the goal-blind Spec survey mapped what the intent implied, and the signed decisions now point at code it had no reason to open. Skip either pass and the ADRs or the slices get decided against recollection.

sarojkjha Bundle

Use when the user wants to build buyer personas or an ideal customer profile (ICP) — the target's goals, pains, buying triggers, objections, and where they research. Also use when the user mentions personas, ICP, target audience profile, customer avatar, "who are we selling to", or buyer journey. Produces structured personas grounded in real signals, not demographic guesswork.

sarojkjha Bundle

Use when the user wants to design a customer or market survey — choosing the questions, structure, scales, and sample size to get unbiased, decision-useful answers. Also use when the user mentions survey, questionnaire, NPS, customer feedback, market research survey, product-market fit survey, sample size, margin of error, "how many responses do I need," or "what should I ask my customers." Produces a structured survey with unbiased questions mapped to decisions, plus computed sample-size, invite, and segment-readability numbers from a runnable engine.

sarojkjha Bundle

Use when the user wants to optimize content so it gets cited by AI engines (ChatGPT, Perplexity, Claude, Google AI Overviews) and wins answer-engine snippets — i.e. GEO (generative engine optimization) and AEO (answer engine optimization). Also use when the user mentions AI citations, getting quoted by LLMs, llms.txt, answer-first content, featured snippets, or "make this content rank in AI answers." Rewrites/augments a page to maximize citation likelihood.

shyxin Skill

基于已达成的设计共识，调研并比较适合的技术库、包或框架，输出有证据支撑的技术选型报告与推荐结论。在 grilling、grill-me 或 grill-with-docs 达成共识后，需要技术调研、框架比较、依赖选型，或为 to-spec 准备技术决策时使用。

stencila Skill

Lint Stencila documents and summarise the diagnostics.

tianque6916 Skill

学术论文全流程 — research → write → review → finalize，含文献综述、论文撰写、审稿回复

nero1688 Bundle

研究方法選擇顧問:判斷一個研究題目適用量化(檔案資料/問卷)、質化(訪談/個案)、實驗、或混合方法,並給出 Q1 期刊等級的完整研究過程套模與 skill 呼叫鏈。核心邏輯:Edmondson & McManus (2007) 方法論適配(methodological fit)——理論成熟度決定方法,新生理論走質化、中介理論走混合、成熟理論走量化;外加資料可得性、因果識別需求、研究者資源三個現實約束。輸出:方法建議(含理由與替代方案)、該方法的 Q1 過程檢查表、對應的家族 skill 串接順序。何時用:題目有了但不知道該用什麼方法、量化質化拿不定、被質疑方法與問題不匹配、想知道頂刊怎麼做這類研究;或者連研究方向都還沒有——內建小白引導模式,從興趣挖掘到代擬可行題目到第一週行動清單,給新手一條明確可走的路。觸發詞:該用什麼方法、量化還是質化、方法選擇、研究設計選擇、混合方法、mixed methods、方法論適配、methodological fit、適合做實驗嗎、適合做訪談嗎、研究方法建議、Q1 怎麼做、頂刊研究流程、不知道要研究什麼、想不到題目、怎麼開始做研究、學術新手、研究小白、給我一個方向、老師叫我自己想題目。與 research-orchestrator 劃界:orchestrator 依『生命週期階段』路由到工具,本 skill 決定『方法論路線』本身——先用本 skill 定方法,orchestrator 再沿該方法排工具鏈。與 phd-researcher 劃界:那個逆向拆解單篇文獻的方法,本 skill 為你的新研究正向選擇方法。

nero1688 Skill

深度訪談研究的『前段』設計師(Q1 質化標準):研究問題的質化證成、半結構式訪談大綱設計(主題-主問-追問三層,開放不誘導)、受訪者抽樣策略(立意/理論/滾雪球+飽和判準先訂)、倫理與知情同意(錄音授權/匿名化/資料保存)、訪談執行守則(rapport、追問技術、田野筆記)、逐字稿規格。輸出:訪談研究設計書+訪談大綱+知情同意書模板+執行檢核表。何時用:要做深度訪談、個案研究的訪談設計、訪談大綱怎麼寫、訪幾個人才夠、質化研究倫理。觸發詞:深度訪談、訪談法、訪談大綱、訪談題目、半結構式、質化研究設計、個案訪談、理論抽樣、飽和、saturation、知情同意、訪談倫理、受訪者、訪談技巧、追問、interview protocol、質性訪談設計。與 qualitative-thematic-coder 劃界:本 skill 管訪談『之前與之中』(設計、抽樣、執行),那個管訪談『之後』(逐字稿編碼分析);逐字稿到手就交棒給它。與 survey-research-architect 劃界:結構化問卷走那邊,本 skill 是開放式深訪。與 ob-hrm-scale-adaptor 的認知訪談劃界:那個的訪談是為了驗量表題項,本 skill 的訪談本身就是研究資料。

nero1688 Skill

問卷研究全流程架構師(Q1 期刊標準):從構念操作化到問卷成品、抽樣與樣本數規劃(先驗檢定力)、發放與回收執行計畫(多波次時點分離、多來源設計、催收與誘因)、共同方法變異(CMV)的程序性預防與統計事後檢驗(Podsakoff 框架)、資料品質防線(注意力檢查、直線作答、作答時間)、回收後的無反應偏誤分析。輸出:問卷藍圖、發放甘特表、資料品質檢核清單、CMV 攻防對照表。何時用:要做問卷調查研究、設計問卷、規劃發放回收、審稿人質疑 CMV、樣本數怎麼定。觸發詞:問卷、問卷設計、問卷發放、問卷回收、調查研究、survey、抽樣、樣本數、檢定力、power analysis、共同方法變異、CMV、common method、反向題、注意力檢查、李克特、Likert、回收率、無反應偏誤、多波次、前測問卷。與 ob-hrm-scale-adaptor 劃界:那個管『單一量表』的跨文化改編與測量恆等性,本 skill 管『整份問卷研究』的設計、抽樣、發放、品質防線;量表改編時轉它。與 experiment-design-architect 劃界:問卷嵌入實驗操弄(情境實驗)時主導權歸實驗那邊,本 skill 支援其測量部分。與 r-spss-syntax-architect 劃界:回收後的建模語法找它,本 skill 止於資料品質放行。

nero1688 Skill

管理與商學實驗設計架構師(Q1 標準):組間/組內/混合設計選型、隨機分派與對抗平衡(counterbalancing:完全對抗/拉丁方陣,處理順序效果與練習效應)、情境實驗(experimental vignette methodology, Aguinis & Bradley 2014)的情境撰寫與擬真度、操弄檢核(manipulation check)與前測、先驗檢定力分析與樣本數、預先註冊建議、受試者倫理。輸出:實驗設計書(設計矩陣+隨機化計畫+分析對應)、情境材料模板、前測計畫、實驗執行檢核表。何時用:要做實驗、情境實驗、受試者內外設計怎麼選、順序效果怎麼處理、操弄有沒有效、實驗樣本數。觸發詞:實驗設計、實驗法、組間、組內、受試者間、受試者內、混合設計、對抗平衡、counterbalancing、拉丁方陣、Latin square、平衡成對、隨機分派、操弄檢核、manipulation check、情境實驗、vignette、情境設計、前測、實驗樣本數、2x2 設計、因子設計、順序效果。與 survey-research-architect 劃界:情境實驗嵌在問卷平台發放時,實驗邏輯(操弄/隨機化/檢核)歸本 skill,測量與發放規劃借那邊。與 r-spss-syntax-architect 劃界:實驗資料的 ANOVA/混合模型語法找它,本 skill 產設計不產語法。與 research-method-selector 劃界:該不該做實驗由它適配,怎麼做實驗歸本 skill。

theophiluschinomona Skill

Switches between development modes (dev, review, research) by loading the appropriate context. Use when the user changes task type or asks to switch modes.

abpai Bundle

Locate, read, and summarize local Claude Code transcripts by session UUID — bounded recent context, opt-in tool summaries, and child subagent transcript paths. Local-only: never runs Claude or contacts Anthropic; use claude to run or resume with new work.

andr-ca Skill

Use when starting a complex multi-step task, a research project, or any task requiring more than 5 tool calls — creates and maintains task_plan.md, findings.md, and progress.md to preserve state across context resets.

aws-samples Skill

Run the AI-DLC `market-research` stage (ideation phase) in isolation, without advancing the main workflow. Packages `/aidlc --stage market-research --single`: the engine emits one run-stage directive for market-research and its gate, the conductor runs it, then the single-stage run commits a synthetic-id pair and stops. The main workflow's Current Stage is never touched.

amit-t Bundle

Research, compare, and select the best npm/pnpm/yarn packages before installing. Use when scaffolding a project, adding a dependency or devDependency, or choosing between competing libraries — including when the user says "add dependency" or "which library should I use".