Evaluate interfaces against 168 research-backed UX/UI principles, detect antipatterns, and inject UX context into AI coding sessions.
Turn a PRD or product description into a production-grade Vercel v0 prompt. Researches industry conventions, picks a bold aesthetic direction, selects fancy UI libraries…
Guides the methodology for investigating V8 concepts, codebase structure, performance, memory, and architecture.
Protocolo 1 do plugin. Valida vigencia normativa nos 4 niveis (federal + conselho profissional CFM/CFO + regulador ANS/ANVISA + estadual/municipal) e a jurisprudencia STJ/STF/TRFs…
Validation & Testing specialist — helps teams test assumptions and run experiments through 14 frameworks including Lean Startup MVP, A/B Testing, Hypothesis Board, and HEART…
Validate design hypotheses via code experiments, codebase analysis, and external research.
Validate statistical analysis output through double programming, independent verification, and reference comparison.
Use when when you have a ranked list of GCF-MF (genomic cluster family–molecular feature) link predictions from one or more scoring functions, a curated set of known validated…
Use when when you have scored GCF-MF (gene cluster family–molecular family) links using two or more complementary scoring approaches (e.g., standardised strain correlation and…
Validates benchmark evidence for claims. Use for comparison footing/比較土俵, baseline/基準線, leakage/ラベル漏れ, prequential tests, implausible scores, confounded ablations/交絡,…
Problem and solution validation methodologies, assumption testing, and MVP validation experiments
Designs internal, external, temporal, and functional validation strategies at the protocol stage for medical research studies.
AutoResearch에서 학습 전에 config의 유효성을 검증하는 Skill. growing-memory 설계공간에서 샘플한 config가 동치/shape 규칙(논문 충실성)을 만족하는지 작은 차원으로 먼저 통과시켜, 무효·무의미 조합이 비싼 학습에 진입하지 못하게 막는다.
Detect and prevent computational bugs in the DCF / scenario valuation engine that produce nonsensical target prices.
Apply the foundational taxonomy of workflow control patterns to evaluate, design, and debug complex coordination systems.
变异与区间文件处理 skill。用于 VCF/BCF、BED、GFF/GTF、interval_list、peak、DMR、loop、genomic ranges 的过滤、合并、交集、注释、坐标系转换和 genome build 一致性检查。
Design recurring knowledge-base update loops for Obsidian-style vaults, project wikis, second-brain folders, and research notebooks.
Show statistics and overview of the Obsidian vault — note counts, type/tag distribution, recent activity.
Capture an architectural decision as an ADR in .vault/adr/. Use after research, before planning, when a significant design choice and its trade-offs must be recorded.
Ground a coding task in real source code, reference implementations, and library docs. Use before implementing a complex feature or when documentation is thin.
Explore an unfamiliar problem and weigh options before committing. Use when unsure how to approach a complex feature, refactor, or bug.
Generate professional primary market / venture capital industry research reports, including sector deep-dives, investment memos, and market analysis.
Research VCF 9 and its ecosystem (vSphere 9, vSAN 9, NSX 9, VKS, VCF Operations, VCFA, VMware Live Recovery, Private AI Foundation).
Create data-driven charts with Vega-Lite (declarative) and Vega (programmatic). Best for statistical visualization of numeric data — bar, line, scatter, heatmap, area, radar…
Use when you have a collection of raw mass spectrometry data files from multiple instrument vendors (Agilent, Bruker, Thermo) and/or mzML exports that need to be converted to a…
Run Venice AI research through an isolated subagent workflow and return summarized results without blocking the main session.
Server-side extension that completes the full analysis pipeline for continuous outcome variables after vera-stat-continuous-testing has run.
Server-side extension that completes the full analysis pipeline for count outcome variables after vera-stat-count-testing has run.
Server-side extension that completes the full analysis pipeline for designed experiments (DOE) after vera-stat-doe-testing has run.
Brainstorm 3-5 verdienmodellen met doelgroepfit, risico's en validatie-experimenten. De stap vóór prijsstrategie: eerst HOE je geld verdient, dan pas HOEVEEL.
Verify work against explicit criteria using direct, source-faithful evidence, reproducible checks, and clear verdicts.
Enforce evidence-first research, coding, hardware, and system-change practices. Use whenever an agent must determine how a product, device, repository, service, or configuration…
Use BEFORE asserting any fact you're not 100% certain about. Anti-hallucination protocol. Triggers latest, recent, current, какая версия, что нового в, как сейчас принято, в новой…
Verify the computation-rule tables and holiday tables that the Australian litigation-deadlines workflows rely on against the official publishers — legislation sites for…
Use when reliability/recoverability is being assumed rather than proven — deliberately inject the failure (dependency down, AZ/region loss, restore from backup, failover, on-call…
Verify a markdown proof in the order it is written. Use when the task is to check local correctness, theorem applicability, and reasoning gaps statement by statement through a…
Version machine learning datasets using DVC (Data Version Control) with remote storage backends, build reproducible data pipelines with dependency tracking, integrate with Git…
Support veterinary understanding from pet care to clinical practice and research.
Search PubMed with veterinary-specific filters and MeSH terms to find relevant animal health research. Handles the sparse, multi-species nature of veterinary literature.
Conduct AI-led research with autonomous literature review, hypothesis generation, analysis, and synthesis while human provides vision.
Deep research and market validation for app ideas. Use when starting a new project, validating an idea, or when the user says "research my idea", "validate my app", or "help me…
Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved. — from th3vib3coder/vibe-science
Scientific research in serendipity mode. Infinite loops until discovery, rigorous tracking, adversarial review.
Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved. — from th3vib3coder/vibe-science
Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved. — from th3vib3coder/vibe-science
Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved. — from th3vib3coder/vibe-science
Scientific research engine with adversarial review, tree search, and serendipity detection. Use when: exploring hypotheses, validating findings against literature, running…
Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved. — from th3vib3coder/vibe-science
Scientific research engine v6.0 NEXUS — adversarial review (Reviewer 2), 32 quality gates, tree search, serendipity tracking, confounder harness, cross-session learning.
Build world-class skills through guided conversation and recursive self-review. Use when creating or improving a skill.
Dispatches research agents to find real projects, papers, and documented failures before proposing any feature, architecture, or technology choice.
Produkční gate pro AI-asistované změny v aplikacích s produkční ambicí (libovolný stack). Použij VŽDY, když se změna dotýká auth/autorizace, RLS/policies/grants, migrací či…
Use for VidSeeds MCP analytics and research — YouTube analytics, channel intelligence, video autopsy, outliers, competitors, trending/breakout discovery, keyword research, comment…
Automated Vietnamese stock price and index checking on FireAnt.vn. Use when checking current stock prices, market indices, trading volumes, or financial information for Vietnamese…
Renders the response as a self-contained, visually polished HTML page saved to /tmp and opened in the browser, replacing plain markdown or wall-of-text output.
Research a Vikunja feature area in the codebase and update or create end-user help documentation. Use when asked to document a feature, expand help pages, or when a review…
Think like Vilfredo Pareto — engineer-economist-sociologist (1848–1923); Pareto efficiency/distribution, residues & derivations, circulation of elites.
Manual for the marginaleffects R and Python package, and guide to the book "Model to Meaning". Use when users ask about predictions, comparisons, slopes, marginal effects — from…
Orchestrate a multi-agent virtual academic reading group. Use when reading multiple papers, generating expert discussion notes, cross-examining positions across papers, and…
Hire specialised agents to handle any task — data analysis, trading, content generation, research, on-chain operations, 3D printing, physical goods, gift delivery, and more.