Explorar skills

Compatibility wrapper for the legacy PM execution workflow covering delivery, launches, retros, and operational follow-through.

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

Diagnostica a precisão da previsão no nível de SKU para equipes de cadeia de suprimentos. Calcula WMAPE, FVA, segmentação ABC, padrões de demanda ADI/CV² e cobertura do denominador, exportando um relatório Excel com gráficos e uma lista de ações priorizadas.

Um portão de qualidade adversarial de 5 camadas para o Claude Code, que emprega Ground Truth Anchor, Subagent Critic, Calibrated Judge, Ratchet Loop e Learning Loop. Ele identifica erros factuais, inflação de pontuação e conclusões ocultas, carregando automaticamente regras específicas para apresentações e ativos visuais.

Compatibility wrapper for the legacy PM communication workflow covering writing, stakeholder alignment, presentations, and messaging.

Polls Notion and Jira for pending MorningStar PRDs and dispatches the GitHub Actions executor when work is found. Use when the user says any of "watch the queue", "poll for prds", "check queue", "trigger morningstar now", "is anything queued", "force a queue scan", or "morningstar 24/7 status". Safe to run on a schedule -- read-only against Notion/Jira, only writes a workflow_dispatch event and a

Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create vi

Always-on multi-agent AI workstation for Claude Code. 142 specialist agents (ML, security, K8s, backend, frontend) · 366 curated skills · 200+ prompt templates · auto prompt-matcher · auto skill-matcher · MCP support · token router cuts Anthropic bill 6x via Kimi/Haiku/Ollama. LiteLLM · BYOK · MIT + Apache. One-line install.

Pluralidade e tecnologia cooperativa (⿻) para 0xagentprivacy. Ativa-se ao discutir votação/financiamento/voz quadrática, identidade interseccional, a linhagem de Audrey Tang / Glen Weyl, colaboração entre diferenças, ou como a privacidade preserva a diferença que a pluralidade exige.

Use para editar arquivos visual.json na pasta visuals/ de um relatório Power BI PBIR. Abrange a estrutura de nível superior, incluindo visual vs visualGroup, filterConfig e isHidden no nível raiz, bem como sufixos literais de expressão como 'text', 14D, 14L, 2.4M, '#FF0000', datetime e null.

Use when planning video content strategy, writing video scripts, optimizing YouTube channels, building short-form video pipelines (Reels, TikTok, Shorts), or repurposing long-form content into video. Triggers: 'start a YouTube channel', 'video content strategy', 'write a video script', 'repurpose into video', 'YouTube SEO', 'short-form video'. NOT for written blog content (use content-production).

Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.