Explorar skills

Review research code for reproducibility and quality, extract the paper's main empirical claims, compare paper to code, and write a constructive markdown report. Designed for quantitative marketing / economics projects with LaTeX papers and R or Python code.

Use this skill during Phase 7 after a successful deployment to generate or update monitoring, logging, alerting, and observability artifacts that catch exceptions and issues in the deployed code. Produces platform-neutral scripts when no observability platform is configured, and integrates with Grafana/Datadog/CloudWatch via MCP when configured. Trigger after deploy, or when the user says "add mon

Infrastructure management orchestrator for CI/CD pipelines, deployments, and cloud services. Routes to specialized subagents for GitHub, Cloudflare, Railway, and Stripe. Handles pipeline analysis, deployment coordination, troubleshooting, and secret management. Trigger keywords: devops, deploy, infrastructure, GitHub Actions, Cloudflare, Railway, Stripe, CI/CD, secrets, workflow.

(Industry standard: Review and Critique Pattern) Primary Use Case: Iterative generation paired with adversarial review, continuing until an 'Approved' verdict is reached. Orchestrated adversarial review loop. Use when: research, designs, architectures, or decisions need to be reviewed by red team agents (human, browser, or CLI). Iterates in rounds of research → bundle → review → feedback until app

Guidelines for shell commands. Avoid `cat`, `find`, `grep`, `head`, and `tail`; prohibit `rm` (use `trash` instead). Use when invoking shell commands via Bash.

Arquitetura Enformer para predição regulatória a partir de DNA, mutagênese in silico (ISM) e priorização de variantes.

Digestão de restrição in silico, detecção de extremidades compatíveis, design de primers (modelos de Tm) e simulação de gel.

Use when the user wants to "model a problem", "translate to math", "formalize a problem", "mathematical modeling", "how to model this", "set up the math", "define the problem", "what kind of problem is this", or discusses translating real-world problems into formal mathematical structures. Covers any computational domain — discrete, continuous, statistical, or hybrid.

This skill should be used when the user asks to 'bookmark URLs from this session', 'save links we found', 'bookmark discoveries', 'save notable URLs to Raindrop', 'bookmark what we discovered', 'save session URLs', 'raindrop bookmarks from session'. Scans the current conversation for high-signal URLs discovered during research, previews 1-3 bookmark candidates, and creates them in the AI-bookmarke

Notação Big O, classes de complexidade, compensações entre espaço e tempo, e regras de análise de complexidade.

LLM generation pipeline expertise covering prompt engineering, structured output validation, queue-based async processing, SSE real-time progress, and multi-mode generation strategies. Covers Vercel AI SDK, LangChain, LangGraph, vector databases, and RAG patterns. Trigger keywords: AI generation, LLM pipeline, prompt engineering, structured output, Zod schema, BullMQ, SSE, RAG, vector database, em

Generates and maintains two changelog files from git tags, TASKS.md, DECISIONS.md, and feature folders. CHANGELOG.md at repo root is developer-facing in Keep a Changelog format with task IDs and decisions. CHANGELOG_CLIENT.md is plain English, grouped by "what you can now do", written like a product update — no task IDs or framework names. Version detection reads git tags first, then package.json