Research & Search

jinplu Bundle

Use when a broad or deep external investigation needs multiple source classes, claim-level evidence synthesis, or contradiction resolution; do not use for a narrow lookup or local code inspection.

minitour Skill

Summarize and triage ontology repo issues for contribution. Use whenever the user wants to review an issue, find good first issues, summarize open issues for an ontology, or understand what an NTR or other issue needs—e.g. "review this issue", "is this a good first issue", "summarize open issues for this ontology", "what does this NTR need". Use for both single-issue review and listing/batching issues.

skillmedev Skill

Translates common lab panels - CBC, CMP, lipid panel, thyroid, hormones, HbA1c - into plain language, flags values against the lab's own reference ranges, and produces a prioritized question list to bring to a physician. Use when someone asks "what does my bloodwork mean", "is my ALT high", "explain my lipid panel", or "what should I ask my doctor about these results". General wellness education, not medical advice - it flags and explains, never diagnoses or prescribes. Do NOT use to summarize a medical chart or clinical document - use clinical-summary instead; for diet changes motivated by results, hand off to nutrition-planner.

raroque Skill

Write a tight, retention-focused YouTube script from a topic, outline, or research brief. Use when the user asks for a video script, wants to turn notes or research into a YouTube video, needs a hook/intro rewritten, or wants to plan a video end-to-end with pacing, visual beats, and CTAs.

rlaope Skill

Reverse engineering and mechanism-comparison research — when the docs run out, read the artifact itself and prove how the thing actually works. Use when the user asks "how does <tool> actually do it", says "reverse engineer this", "undocumented behavior", "the docs don't match what happens", or "the docs never mention it"; when a dependency, vendor SDK, legacy system, or external API behaves in ways nobody on the team can explain; when the ask is to compare implementations of the same mechanism across libraries or competitors; when someone says "we've tried everything" about a black-box system; or when the only source of truth is minified bundles, compiled binaries, or network traffic.

ryanthedev Bundle

Runs parallel multi-angle web research at four depth modes (scan, brief, breadth, deep): a planner grounds the query in local context and plans search dimensions, parallel search agents pull verbatim extracts with source URLs, one dimension always hunts counter-evidence, and synthesis is grounded back in the local project. Use when researching a topic, library, or tool on the web, comparing options or products, surveying a landscape of approaches, or checking current, version-sensitive, or time-sensitive information. Not for: driving or automating a live browser session (use oberskills:browser), academic literature search across arXiv or Semantic Scholar, or questions about the current repo, project, or files already on disk — read those directly.

vanthienha199 Skill

Turn meeting transcripts or voice recordings into structured notes with action items, decisions, and owners. Use when the user shares a transcript, meeting recording, or asks to summarize a meeting. Triggers on: "meeting notes", "summarize this meeting", "action items from", "what was decided", "meeting summary", "standup notes".

djordjemojsilovic Skill

Aktiviere diesen Skill IMMER wenn der User /ultraplan schreibt oder eine Aufgabe kommt die eine tiefe, strukturierte Analyse erfordert. Behandelt jede Aufgabe wie eine Militäroperation: Lageerkundung (Web Research), Lagebeurteilung (Analyse mit vollem Kontext über den User), Operationsplan (klare Empfehlung), Ausführung (präzise Antwort). Kein Raten, kein Bullshit, kein unnötiger Output. Trigger auch bei: "analysier das für mich", "was ist besser", "wie soll ich vorgehen", "mach einen Plan", "deep dive", "ultraplan".

ainergiz Skill

Use Google Gemini for AI chat, research, image/video creation, and analysis. Use when user wants to use Gemini, ask complex questions, generate images or videos, do deep research, or use Gemini's thinking capabilities.

shobcoder Skill

GOD MODE deep research skill. Multi-phase autonomous research loop: query decomposition → multi-source crawling → claim cross-referencing → conflict resolution → structured synthesis with inline citations. Use for any question that demands depth, sourcing, and verifiable accuracy.

zarubinvibe Skill

Thin-session capability router. Given a task description OR an explicit skill id, finds the single best local skill via GraphiFy (route-skills.mjs) and Reads only that one SKILL.md to follow it. Most of the ~1450 local skills are hidden from the skill listing (skillOverrides=user-invocable-only) to keep sessions lean — their names/descriptions are NOT in context. Use this whenever you need a capability you don't currently see, or to run a named hidden skill.

kotek-7 Skill

Use this skill when the user gives a broad development, research, refactoring, debugging, implementation, experimentation, evaluation, or cleanup goal that may require multiple work cycles, commits, and feedback loops until the goal is achieved.

kotek-7 Bundle

Use when the user asks to explain the project in the current working directory, summarize what this repository does, describe its structure, or provide a user-facing project overview. This skill performs read-only inspection and returns a concise explanation for the user.

kotek-7 Bundle

Use when first entering a project or when the user asks to understand, inspect, summarize, onboard, or get familiar with a repository. This skill performs read-only project orientation: structure, stack, important files, commands, tests, docs, risks, and next investigation targets.

manaflow-ai Bundle

Run a GitHub issue digest for openai/codex by feature-area labels, all areas, and configurable time windows. Use when asked to summarize recent Codex bug reports or enhancement requests, especially for owner-specific labels such as tui, exec, app, or similar areas.

upsonic Skill

Research Skill

kitsune-den Bundle

Structured research workflows for deep dives on any topic. Use when: starting a research question, gathering sources, compiling findings, or publishing research to sage.skulk.ai. NOT for: quick one-off web searches (use web_search directly) or simple fact lookups.

ayushgoel Bundle

Use when the user wants to add a note from an article, mailing list, or reading; update existing notes with new knowledge; link notes into a Foam knowledge graph; or capture any learning into the knowledge base. Triggers: 'add a note about X', 'update my notes on Y', 'I just read about Z', 'add this to my foam repo', 'link this note'.

balabalabalading Bundle

Record and query AI conversation logs — what users asked, how it was solved, and the result. Use when users want to logging conversation, summarize recent work from sessions, or want daily/weekly project summaries from past conversations.

hollis36 Bundle

系统化调试助手，帮助科研人员使用结构化方法定位和修复代码问题。支持4阶段调试流程、根因追踪技术、日志和断点策略、条件等待方法、防御式编程。当用户需要：(1) 调试科研代码错误、(2) 追踪数据分析问题、(3) 定位统计计算错误、(4) 解决实验代码bug、(5) 优化代码性能时触发。关键词：debugging、调试、bug修复、错误追踪、问题定位、troubleshooting。

dav-niu474 Bundle

ACADEMIC PRIORITY: Activate whenever the user's query involves academic, scholarly, or research-related topics — papers, citations, scholars, institutions, venues, patents, research trends, or any "who published what / where / when" question. Takes precedence over general web search for academic data needs. Routes through the z-ai gateway's `/v1/functions/invoke` endpoint to the AMiner Open Platform (27 APIs, 5 workflows).

speckledrattlesnakeinoculant470 Skill

Verify Citation

theaibreakfastclub Bundle

Coaches students and teachers on scientific and academic English: abstracts, IMRAD sections (Introduction/Methods/Results/Discussion), lab reports, literature reviews, peer review, conference posters and oral presentations, academic vocabulary, hedging, grammar and register, and CEFR-aligned assessment (B1-C2). Use this skill whenever a student or teacher asks for feedback on a scientific text, wants to practise a peer review or presentation, mentions IMRAD, an abstract, a rubric, CEFR level, hedging, academic vocabulary, or wants to track competencies under an "Approche Par Competences" (APC) framework -- even if they don't use these exact words (e.g. "is this introduction OK?", "make this sound more academic", "grade my abstract").

verasuperhub Bundle

Runs data quality diagnostics and baseline image classification. Produces class distribution tables, sample image grids, image size and channel statistics, a baseline CNN or pre-trained feature extractor with Logistic Regression, weighted F1 and macro AUC (bootstrapped 95% CIs), confusion matrix, and ROC curves. Ends with a recommendation block listing additional models available in the analysis workflow. Outputs Python scripts with 2 publication-quality plots. Triggered when user has image data and says "image classification," "computer vision," "CNN," "object recognition," "medical imaging," "image detection," "visual recognition," "photo classification," "X-ray classification," or describes a task involving classifying images into categories. Does not handle free-text NLP or tabular-only data.

vincenzoimp Bundle

Use when writing the project survey from the digested SOTA or updating it after the SOTA changed — grouping design, gaps and research directions, and coverage maintenance.

aedelon Skill

Debug errors systematically by searching first, then analyzing, then proposing verified solutions. MUST BE USED when user reports: "error", "bug", "doesn't work", "fails", "crash", stack traces, exception messages, or any troubleshooting scenario. Triggers: "TypeError", "ImportError", "undefined is not a function", "segfault", "panic", "broken", "not working", "unexpected behavior", "regression", "failing", "exception", "traceback", "stack trace", "debug this", "why does this fail", "help me fix". Also enforces confidence levels and output templates. Prevents guessing solutions without research.

aedelon Skill

Conduct rigorous research with proper citations (DOI, arXiv, PMID) and source triangulation. MUST BE USED when user asks: "what is SOTA", "recent developments", "compare X vs Y", "is it true that", "research says", "latest papers on", "scientific evidence", "studies show", "state of the art", "literature review", "find papers", "academic research", "benchmark results", "who published", "when was X released", "current best", "what does the research say", "evidence for", "peer reviewed". Searches multiple sources, evaluates reliability, states confidence level. NOT for verifying API signatures (use anti-hallucination) or general web search (use WebSearch directly).

themattberman Skill

Extract brand/product evidence from an ecommerce product URL before any Brand Shoot Kit planning or generation. Use for PDP scouting, source evidence capture, product image URL collection, degraded-mode notes, and scout.json creation. Do not use for ad spying or competitor ad research.

thinkingwithagents Skill

Structured code review for research code (Stata, R, Python) against DIME, Gentzkow-Shapiro, AEA, and IPA standards — catches silent failures, reproducibility risks, and style issues

thinkingwithagents Skill

Brainstorm and stress-test research ideas as a senior scholar colleague would. Runs a multi-turn dialogue that clarifies the seed question (or generates one from cold start), probes it conversationally, launches a parallel deep literature scan across published and working-paper sources, critiques the question adversarially, generates 2–3 alternative framings, assesses feasibility (delegating to the find-data skill when available), and writes a research brief to the working directory. Trigger when the user asks to brainstorm a research idea, stress-test a research question, workshop a project, develop a new paper idea, assess novelty of a question, evaluate whether an idea is worth pursuing, refine a research direction, or check whether an idea clears a top-journal bar. Also trigger on phrases like "brainstorm with me", "is this novel", "has anyone done this", "what should I work on", "help me think through this idea", "workshop this question", "stress-test this", "poke holes in this", "new research idea", "re

tomkd555 Bundle

転職活動の工程全体の入口となるハブスキル。依頼がどの作業に当たるかを判別し、対応するサブスキル （job-change-profile / job-change-self-analysis / job-change-job-search / job-change-company-research / job-change-fit-assessment / job-change-documents / job-change-exam-prep / job-change-interview-prep）へ振り分ける。個々の作業は本スキルでは行わない。 複数の作業が絡む依頼では推奨順序を示し、中断した工程の続きを判定する。利用者データの置き場所は設定ファイル だけが決め、未設定なら対話で設定ファイルを作るまでサブスキルへ振り分けない。利用者プロファイル （profile.json）については、有無確認と validate_profile.py によるゲート、および誤字・updated_at などの 単一フィールドに閉じた軽微な修正のみを直接担い、初回作成・全面点検・セクション更新のヒアリングは job-change-profile へ委譲する。日本の転職市場を中心に外資系選考にも対応する。 Use when the user works on a job change in Japan (including foreign-affiliated company selection) and the request spans the process as a whole — where to start, what to do next, or several steps at once — and needs an entry point that gatekeeps the configuration and their profile, then routes the request to the right sub-skill. trigger words: 転職, 転職支援, 転職活動, キャリアチェンジ, 転職の進め方, 転職活動の相談, 何から始めればいい, 次に何をすればいい。

tomkd555 Bundle

転職の応募先候補について、求人票・企業研究・自己分析・時間分析を突き合わせ、7次元（経験の近さ・志向の一致・作業特性の一致・ 条件の適合・文化の適合・報酬の適合・時間の適合）で適合性を評価するサブスキル。 求人票 metrics と企業研究の指標から拘束時間・実質時給を算定し、profile の必須条件を 1対1で判定し、推奨・条件付き推奨・非推奨・判断保留の総合判定を根拠つきで作成する。経験の近さと 志向の一致は別軸で評価し、不足する技術要件は補完に要する期間の段階で示す。すべての判定を evidence に 対応づけ、材料が無い項目は創作せず unknown とする。応募先が決まった段階で、企業研究の後に使う。 job-change-support（hub）から振り分けられて動く。 Use when the user wants to assess how well a target company/job fits them for a job change in Japan — matching a job posting and company research against their profile, self-analysis, and working-time analysis across experience proximity / aspiration alignment / work character / condition / culture / compensation / time dimensions — and needs an evidence-backed recommendation rather than an impression. trigger words: 適合性評価, 適合度, フィット, この会社は自分に合うか, 応募するか判断, 拘束時間, 実質時給, 求人と自分の突き合わせ, 必須条件の充足, 推奨判定, やりたい仕事に近いか, スキルギャップ。

tomkd555 Bundle

転職の企業研究を担うサブスキル。企業名と重点観点を受け、公式資料・報道・口コミサイト等から情報を集め、 すべての主張に出典URLとエビデンスレベル（A=一次公式／B=信頼できる二次／C=口コミ集計／D=個人ブログ・伝聞）を 付した company_research.json を作り、機械的な検証と独立監査を通してから、トピック別の企業研究レポートを納品する。 求人情報URLを渡された場合は、求人票を取り込んで job_posting.json を作ってから調査へ入る。 指示された軸の指標について公表値を集めるところまでを担い、点数化・重み付け・格付けは行わない（profile 非依存）。 job-change-support（hub）から振り分けられて動く。 Use when the user researches a target company for a job change in Japan (including foreign-affiliated selection) — its philosophy, business, financials, compensation, benefits, work style, reputation, and selection process — or imports a job posting from a URL, and needs sourced, evidence-graded findings rather than unverified hearsay. trigger words: 企業研究, 会社を調べる, 企業分析, 事業内容, 財務, 平均年収, 有価証券報告書, 評判, 口コミ, 選考プロセス, 理念, パーパス, 求人URL, 求人票の取り込み, この求人を調べて。

ppx123-web Skill

Record ideas and thoughts to Obsidian vault. Creates structured idea notes with problem analysis and tags. Use when user says "记录想法", "有个idea", "记一下", "记录疑问", or captures inspiration/questions about technical problems, architecture, or research.

ppx123-web Skill

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

ppx123-web Skill

Comprehensive arXiv paper search and retrieval tool with keyword search, category filtering, date range filtering, and daily paper fetching capabilities. Use for "搜索arXiv论文", "获取最新论文", "arXiv文献调研", "生成论文报告", "查找cs.AI相关论文".