Skip to content

Browse Secure Claude Skills

Search verified agent skills and review security grades before installing · full A–Z index

PapersALevanta papers científicos sobre metodologias de IA aplicadas à medicina publicados nos últimos 7 dias, sobre um tópico específico que o usuário fornece. Use esta skill SEMPRE que o usuário pedir "/papers", "papers da semana", "o que saiu essa semana sobre [tópico]", "varrer arxiv/pubmed/medrxiv", "levantamento semanal de papers", "novidades em IA médica", "papers recentes sobre [tema]", "o que foi publicado essa semana em IA médica", "semana de [tópico]", "últimos papers sobre IA em saúde". ...datapythongoVotes: 0GitHub stars: 2
Lab ExpARoda um experimento preditivo clinico de ponta a ponta no padrao do laboratorio, da auditoria de vazamento ate o zip e o repositorio privado. Comeca sempre pela auditoria que decide se o experimento faz sentido (momento da predicao, censura disfarcada de desfecho, variavel que sozinha da AUC alta demais), depois monta o pipeline com Boruta dentro do fold, sete modelos com regra de desempate declarada antes, limiar fora da amostra, IC por bootstrap e calibracao, e entrega notebook do Colab, no...datapythongoVotes: 0GitHub stars: 2
Author CreditAMonta a declaração de contribuição dos autores (CRediT) de um manuscrito, e antes disso levanta no repositório quem de fato fez o quê, para não atribuir trabalho a pessoa real por dedução. Pergunta apenas os papéis que a evidência não resolve, escreve a declaração no padrão da taxonomia e aplica em todos os artefatos do paper de uma vez (.tex, .docx, markdown), para não divergirem. Sub-comandos: `/author-credit` (levanta, pergunta e escreve), `/author-credit check` (audita uma declaração exis...datagobashVotes: 0GitHub stars: 2
Fused RuntimeAWhat a Fused UDF can import and shell out to at run time — the Python packages and versions in the realtime and batch images, system binaries, DuckDB extensions, and how to get a package that isn't installed. Use before importing a library in a UDF, when a UDF fails with ModuleNotFoundError or a version-specific API error, or when choosing between libraries for a UDF.datapythongoVotes: 0GitHub stars: 5
Sql ReviewAProve an app's numbers against live Snowflake and leave a record a person signs. Builds or repairs the app's sql_review/ page files, checks objects, grants and DDL drift, runs every section as aggregates, has reviewer agents judge the logic, drops findings the evidence does not support, and writes the committed review log. Use when the user says "review the SQL", "are these numbers right", "trace the data", "audit the lineage", before a release or deploy, or from /review-app --sql. It spends ...datagobashVotes: 0GitHub stars: 3
Build AppAThe front door for building a Streamlit-in-Snowflake app from idea to opened PR, or resuming one mid-build. Orchestrates spec, data discovery, page design, scaffold, a parallel page build and review by subagents, and ship, with human checkpoints between them. Start here for any new app, to document an existing one, to add a page, or to act on feedback about a live app. Use when the user says "build an app", "new dashboard", "add a page", "spec this out", "pick up where we left off", "here's f...datagobashVotes: 0GitHub stars: 3
FusionalyAUse when user asks about website analytics, traffic, visitors, page views, referrers, or mentions "fusionaly". Queries Fusionaly analytics via SQL API.datagobashVotes: 0GitHub stars: 13
DesignAUse when styling Fusionaly UI components, pages, or charts - applies the Fusionaly design system with black/white palette and brand accentsdatasqlreactVotes: 0GitHub stars: 13
MlviewAAnalyze an ML or deep-learning workflow with the active host model and publish a source-linked interactive MLView artifact.datajavascriptpythonVotes: 0GitHub stars: 22
New Page Indexation TrackerATracks how long new pages take to get picked up by Google and start earning traffic, from live Google Search Console data in your Coupler.io workspace — days from publish to first impression, to first click, to a settled ranking, and which pages have gone nowhere. Use for "are my new pages getting indexed by Google", "how long until new content ranks in search", "which of my pages is Google ignoring", "did my new posts get picked up in search", "why isn't my new page showing up in Google", "h...datagobackendVotes: 0GitHub stars: 35
Gsc Search Opportunity FinderAFinds the clicks you're leaving on the table in Google Search, from live Search Console data in your Coupler.io workspace — queries ranking just off page one, pages that get seen but not clicked, and pages quietly competing with each other for the same query. Use for "which keywords are close to page one on my site", "striking distance keyword report", "which of my pages get search impressions but no clicks", "find my organic CTR gaps", "are my pages cannibalizing each other in search", "wher...datarustgoVotes: 0GitHub stars: 35
Gsc Ga4 Landing Page PerformanceAJoins Google Search Console and GA4 to show which landing pages bring organic traffic and what that traffic does once it lands, from live data in your Coupler.io workspace — search clicks and rankings next to engagement, key events and revenue, per page. Use for "does my organic search traffic convert", "which landing pages actually make money from SEO", "which SEO pages are worth the effort", "my rankings are up but sales aren't", "which pages get search clicks but no conversions", "landing ...datarustgoVotes: 0GitHub stars: 35
Gsc Country Device PerformanceABreaks organic search performance down by country and device, from live Google Search Console data in your Coupler.io workspace — clicks, impressions, click-through rate and average position by market and by phone/desktop/tablet, against the site's own average. Use for "how does my organic search do by country", "which markets underperform in search", "is mobile or desktop better for my search traffic", "where am I losing search clicks by device", "should I localise for SEO", "which countries...datagobackendVotes: 0GitHub stars: 35
Content Decay DetectorAFinds pages that are quietly losing organic traffic over time, from live Google Search Console data in your Coupler.io workspace — which pages are down on clicks, whether it's a ranking slip or fewer people searching, and which are worth updating first. Use for "which of my pages are losing search traffic", "what content is decaying", "which blog posts should I refresh", "why is my organic search traffic sliding", "which pages dropped in Google since last quarter", "find pages that need updat...datagobackendVotes: 0GitHub stars: 35
Branded Vs Nonbranded Search SplitASplits your organic search into brand and non-brand and tells you which is really growing, from live Google Search Console data in your Coupler.io workspace — clicks, impressions, CTR and position for people searching your name versus people finding you cold, the non-brand share and its trend, and new non-brand queries coming in. Use for "is my SEO growth real or just brand", "brand vs non-brand organic search", "how much of my search traffic is people searching my name", "is my non-brand sea...datagobackendVotes: 0GitHub stars: 35
TableauALoad when the user asks about Tableau: find, build, copy, edit, redesign, or check a Tableau workbook, dashboard, view, or data source. Covers the tableau_* tools, the .twb builder with its design layer, data sources on SignalPilot connections, the design standard, and the render review.datapythongoVotes: 0GitHub stars: 485
Convert To Benchmark ScriptATurn the script a user really runs into a benchmark script an optimization loop can run over and over. Same shape as the real job, a few minutes long, repeatable, and leaving nothing behind. It produces the script and a table of what changed, and it does not run it.datagoVotes: 0GitHub stars: 3
Trl TrainingAPost-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.datapythongoVotes: 0GitHub stars: 11,142
XlsxAUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the...datapythonrustVotes: 0GitHub stars: 179,886
Bare Skill No FrontmatterAThis file has no YAML frontmatter fence, so it declares nothing about itself. It must NOT count as evidence of a shipped skill capability.dataVotes: 0GitHub stars: 2