Research Claude Skills
2 269 research skills from 396 authors. They find sources and get you up to speed on unfamiliar ground. Half of them fit into 2 278 tokens or less — that is what one costs your context window when the agent loads it. 663 ship runnable scripts rather than instructions alone. 4 of them cannot work without an MCP server, most often rube. We also found 264 copies of these same skills sitting in other people's repositories — counted once here, not 264 times.
2 269 unique 396 authors 1 169 updated this month 93 from vendors
Design a fact-checking protocol for AI-generated text, extending SIFT with AI-specific adaptations for hallucination detection. Use when students need to verify AI claims and citations.
Generate tiered sentence frames for academic tasks that scaffold language production across proficiency levels. Use when EAL students need structured language support for classroom discourse.
Tier vocabulary from a text or topic into everyday, academic, and technical categories with teaching priorities. Use when pre-teaching vocabulary or identifying language barriers in a text.
Anchor curriculum learning in a specific local place with connections to community, culture, and identity. Use when connecting academic content to students' local environment and heritage.
Design a complete lesson study cycle from research question through collaborative planning to research lesson. Use when planning jugyou kenkyuu or collaborative teacher inquiry into practice.
Design a practitioner inquiry cycle from research question through data collection to evidence-informed action. Use when starting action research, teacher-led investigation, or professional inquiry.
Design structured perspective-taking activities with anti-projection guardrails. Develops genuine understanding of complexity across history, social sciences, and literature — not performed empathy.
Design a lesson that embeds PERMA wellbeing elements alongside academic learning objectives. Use when planning lessons that intentionally support both content mastery and student flourishing.
Map evidence-based connections between a wellbeing initiative and specific academic learning outcomes. Use when justifying wellbeing programmes, integrating SEL, or linking pastoral and academic work.
Adaptive content summarization - auto-detect content type and produce relevant summary
Research-to-implement pipeline chaining 5 MCP tools with graceful degradation
Migration workflow - research → analyze → plan → implement → review
AI-powered web search, research, and reasoning via Perplexity
Formal theorem proving with research, testing, and verification phases
Full dropshipping pipeline for US/EU/global markets — product research (winning criteria, Minea, PiPiAds), supplier sourcing (AliExpress, CJ Dropshipping, Spocket, Zendrop), Shopify store setup (themes, apps), ad creative pipeline (10 ads/week methodology, UGC pattern), audience targeting (interest stacking, lookalike, broad), pricing math (3-5x markup, BE-ROAS), customer service (long shipping, refunds), scaling playbook (CBO, vertical), compliance (FTC, EU CHRD). Trigger: 'dropshipping', 'shopify store', 'AliExpress', 'winning product', 'Facebook ads dropship', 'TikTok ads dropship', 'Shopify conversion'.
3-tier competitor analysis (direct, indirect, secondary) for global markets — positioning, SWOT, content benchmark, market gap. Tools: SimilarWeb, Ahrefs, Semrush, Minea (dropshipping). Trigger: 'competitor research', 'competitive analysis', 'what competitors are doing', 'competitor analysis', 'market research'.
Build deep customer profiles — Consumer vs Shopper, JTBD framework, customer journey mapping, insight validation, internal monologue research
Maps a customer journey across stages, touchpoints, emotional curve, pain points, and moments of truth into a markdown artifact with an optional mermaid timeline or flowchart. Use when synthesizing existing research into the shape of a customer's experience, end-to-end or for one phase. Without research signal yet, run discover-interview-synthesis or measure-survey-analysis first; refuses to fabricate emotional or behavioral data.
Synthesizes user research interviews into actionable insights, patterns, and recommendations. Use after conducting user interviews, customer calls, or usability sessions to extract and communicate findings across participants. Distinct from foundation-meeting-recap, which summarizes one internal meeting for its attendees; this skill aggregates research conversations into evidence-backed findings.
Analyze survey results into actionable PM insights. Produces persona segmentation, hypothesis validation status, thematic clustering of open-text responses, statistical confidence labels, prioritized recommendations, and what-NOT-to-conclude warnings. Refuses to overstate statistical significance from weak samples or biased instruments.
Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries (--library). Use when learning about libraries, patterns, or comparing approaches. Searches HexDocs, ElixirForum, GitHub.
Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries (--library). Use when learning about libraries, patterns, or comparing approaches. Searches HexDocs, ElixirForum, GitHub.
Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries; Use when learning about libraries, patterns…
Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries (--library). Use when learning about libraries, patterns, or comparing approaches. Searches HexDocs, ElixirForum, GitHub.
Run upstream brand discovery covering audience research, competitive landscape, category dynamics, problem space, and positioning territory exploration. Use this skill at the very start of a brand or website project when the user needs to understand who they're for, who they compete with, what the audience actually needs, and where the brand could plausibly stand. Triggers on brand discovery, audience research, market research, competitive scan, category research, customer research, who is this for, who are we, positioning research, intake, kickoff. Also triggers when a creative brief is requested but the upstream inputs (audience, competitors, problem space) are not yet clear.
Turning research artifacts into actionable PM insight. Customer interviews, user research notes, support ticket reviews, sales call transcripts, survey data, in-app feedback, all synthesized into the decisions they are meant to inform. The discipline of moving from raw discovery data to clear product direction without losing signal in the synthesis or fabricating insight that was not actually there. Triggers on research synthesis, customer interview synthesis, user research analysis, discovery readout, research insights, sales call analysis, support ticket analysis, qualitative data analysis. Also triggers when a team has done research but cannot turn it into decisions, when synthesis is producing pretty decks but no roadmap movement, or when an upcoming PM decision needs to be grounded in research already conducted.
Patterns for individual long-form content pieces. Case studies, whitepapers, research reports, definitive guides, manifestos, ebooks, long-form tutorials. The structural disciplines that distinguish publication-quality long-form from bloggy-long padding or academic bloat. Different from pillar-content-architecture (which covers hub structure); this skill covers individual deep-dive pieces. Triggers on long-form content, case study writing, whitepaper, research report, definitive guide, ebook, manifesto, long-form tutorial, deep-dive article, anchor piece, foundational article, structural archetypes. Also triggers when a piece is over 3,000 words and the team is unsure how to structure it, when a long-form draft feels padded or saggy, or when a flagship asset needs the depth to actually earn the length.
Designing first-run product onboarding wizards that get users to the ah-ha moment without overwhelming them. Step architecture, progressive disclosure, escape hatches, completion incentives, drop-off measurement. Honest about tutorial-overload (dump everything upfront), skip-friendly-empty (skipped onboarding leads to abandoned product), and earned-progressive-disclosure (right things at the right moments) patterns. Triggers on onboarding wizard, product onboarding, first-run experience, signup flow, activation flow, FRX, time-to-value, ah-ha moment design. Also triggers when activation rates are low, when users skip onboarding and never return, when onboarding flows are being scoped for the first time, or when audience research shows users not finding key features.
Plan and execute user research including research planning, recruiting, interview design, qualitative synthesis, and translating findings into product decisions. Use this skill whenever the user wants to plan user research, design interviews, recruit participants, conduct discovery, run formative research, or synthesize qualitative findings. Triggers on user research, UX research, user interviews, discovery research, generative research, formative research, qualitative research, user insights, research synthesis, recruitment, interview guide, jobs to be done. Also triggers when product decisions are being made without user input and the user wants to fix that.
Expert economics paper writing assistant synthesizing advice from 50+ top guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Glaeser, Kremer, and other leading economists. USE THIS SKILL whenever the user writes, edits, reviews, rewrites, or structures any economics paper, thesis, job market paper, abstract, introduction, conclusion, results section, literature review, or referee response. Also handles LaTeX formatting, presentations, and paper audits. Covers all paper types (applied, theory, structural, mixed) and all sections.
Verify scholarly references and claim-citation support for Light stage 10. Use when auditing a manuscript, claim map, bibliography, DOI/arXiv/PMID/ISBN/URL, BibTeX/CSL, citekeys, chimeric or fabricated citations, retraction/correction alerts, or preparing a canonical citation registry for typesetting. Builds provenance-preserving inventories, confirms metadata with independent authoritative sources, distinguishes CONFIRMED/CONFIRMED-MISSING/UNAVAILABLE/UNRESOLVED, records Crossref update direction, and emits the citation gate plus delivery artifacts.
>- → 产**值得做且做得成的分层候选 idea**(moonshot 冲刺/solid 稳妥/safe 保底),每个必答**为什么值得做·创新点· 比现有强在哪·解决什么具体问题·能投什么层次**,且**提出时就自带撞车前置自查**(最像的前作+delta,吃上游 想 idea / 创新点 / 研究思路 / 选题 / 突破口 / 差异化 / 这个方向能做什么 / 有什么可做的 / brainstorm / critical 门,生成端只产撞车 warn 信号);用**证据根→机制/假设 delta→信息增益→最小判别实验**谱系约束候选； 过 **innovation_engine 反拼接门**，把原创来源分型(新问题/新机制/新测量/新数据/新理论/跨域迁移/工程增量)与 claim 强度绑定； 数量/七角度只作 advisory，机制多样性才是硬门。
>- 检索分别排序**,合成研究脉络 + 方法谱系 + 未解问题地图,揪出**最像你设想的那一篇**→喂 idea-critique 领域地图 / 研究现状 / 有哪些工作 / 相关工作 / related work / literature review / survey / 前沿 / 综述 / 不一锅 relevance;撞车只产**信号**不下 novel 判决(归 idea-critique);覆盖度按真实 HTTP 码诚实标。
>- Prepare evidence-backed patent invention disclosure materials for attorney or patent-agent review. Use when the user asks for 专利点挖掘, 技术交底书, 现有技术/查新记录, claim/patent-point support mapping, invention disclosure drafts, patent figures, or a handoff package for a software/research/project invention. This is an not submit filings, does not guarantee novelty, grant, allowance, validity or registration, and emits no Light research findings or back-edges.
>- Light 科研主线第 8 步·论文写作：围绕「如何让审稿人相信值得发表」组织，初稿→审稿人视角循环打磨； 每个 claim 都有证据、措辞强度匹配证据强度、绝不过度宣称。何时用：实验+分析做完要写论文 / 写/改摘要·引言· 贡献句·结论 / 担心「claim 无证据 或 措辞夸大」/ 要让贡献三处(摘要·引言·结论)一致 / 引言四段式(痛点→不足→ 洞察→贡献) / 要当审稿人自己挑一遍 / 论文初稿润色去 AI 腔/被动/语法。 触发词：写论文 / 论文写作 / 写摘要 abstract / 写引言 introduction / 贡献句 contribution / 写结论 / 润色 polish / 改写 / 措辞 / 过度宣称 overclaim / claim 无证据 / 审稿人视角 / 自我审稿 / 贡献一致 / hedge / 学术腔 / AI 腔 / 被动语态 / paper writing / draft。 核心纪律：**claim 无证据 = critical 诚信门**（spec §4.2，STAGE_GATES[8]=[claim_evidence,overclaim]）； 过度宣称 / 贡献三处不一致 = warn（critical 措辞红线在 research-ethics 交付门）；**措辞强度必须匹配证据强度**、 不显著只能报「未见显著差异」、绝不过度宣称；机检措辞有边界，逻辑/创新/论证终判仍需人/审稿人。 本技能是 **8→7（claim 无证据→result-analysis）/ 8→6（实现缺口→experiment-coding）回炉发起方**。
>- 学术不端/数据造假/统计自洽/结论夸大/幻觉与撤稿 引用/自我抄袭/隐私/版权/署名与 AI 披露/软著专利权属/论文工厂洗稿等风险,把"别造假别夸大"从口头建议 落成**可机检、可阻断、可被总控 run_checkpoint 聚合的机读门**(产 light.findings.v1,Critical fail → exit 1)。 AI 不能自评 → 一律"机读门 + 人工复核";查不到写"待核查/UNRESOLVED",绝不编造;全程在线核实、零本地知识库、零付费 key。
>- Light 科研主线第 5 步·研究方案与实验设计：把 idea-critique 放行的 idea 与 data feasibility 拆成**能真执行、能写进论文、 能复现**的 question/estimand、实验矩阵与预注册包。何时用：idea 已通过审查要落地 / 要设计实验·消融·对比·敏感性· 泛化·鲁棒性 / 写研究方案 PROJECT_PLAN / 锁 primary outcome、排除/停止规则或 preregistration / 规划样本量、种子与统计功效 / 算实验算力预算 / 复现已有论文 / 担心 baseline 放水或假设推不翻。触发词：研究方案 / 实验设计 / 实验矩阵 / 假设 / 对照 baseline / 消融 ablation / 公平比较 / 可证伪 / 统计功效 power / 多少种子 / 复现 / reproducibility / research plan / experiment design / 可复现。核心纪律：**对照不公平(baseline 放水)/不可证伪 = critical 一票否决** （spec §4.2，STAGE_GATES[5]=[fair_baseline,falsifiable]）；消融不隔离/欠功效 = warn；功效是计划阶段反推非结果检验； lint 是启发式有边界，公平/可证伪终判仍需人/领域判断，绝不吹"证明了对照绝对公平"。
Build and preflight submission-ready LaTeX/PDF artifacts for Light stage 11. Use when receiving a paper-writing manuscript, figure delivery, citation delivery.json/references.bib/citekey-audit.json, or a venue/template profile; when selecting pdfLaTeX/XeLaTeX/LuaLaTeX and BibTeX/Biber; when diagnosing LaTeX errors or unresolved references; when checking page limits, double-blind identity, PDF metadata, template, page box, embedded fonts, TODOs, figures, tables, labels and citations; or when producing a reproducible compile manifest, PDF, compliance report, failure bundle and venue-matching handoff. Distinguishes PASS, manuscript ERROR, toolchain UNAVAILABLE and convergence UNRESOLVED without redoing citation authenticity or figure scientific QA.
Semantic search, similar content discovery, and structured research using Exa API
> Optimize any form that is NOT signup or account registration — including lead capture, contact, demo request, application, survey, quote, and checkout forms. Use when the goal is to increase form completion rate, reduce friction, or improve lead quality without breaking compliance or downstream workflows.
Choose recommended plugins and plugin-provided blocks for features core WordPress blocks do not cover - ecommerce (WooCommerce), forms and newsletters (Jetpack), online courses and quizzes (Sensei LMS), polls, surveys and ratings (Crowdsignal), spam protection (Akismet) - while keeping generated content editable and avoiding raw HTML fallbacks. Any request to sell products or build a shop, store, or storefront requires WooCommerce with products.
Debug failed or low-quality extractions by analyzing logs, probing the source site, and identifying root causes
> FigMirror mirrors the visual style of a top-conference paper figure (NeurIPS / ICML / ICLR / Nature family) onto the user's own data. Takes dirty data plus a reference figure screenshot (cropped or uncropped), preprocesses the reference crop, runs a Drawer/Reviewer loop, and outputs a camera-ready PDF plus a self-contained matplotlib script with an inline DATA SECTOR.
| Build per-chapter (H2) writing briefs (NO PROSE) so the final survey reads like a paper (chapter leads + cross-H3 coherence) without inflating the ToC.
| Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.
| Retrieve paper metadata from arXiv using keyword queries and save results as JSONL (`papers/papers_raw.jsonl`).
| Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.
| Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.