Explorar skills

Record agent activity during Claude Code sessions. Captures plans, human input, agent decisions, and deviations via hooks and agent self-reporting.

Use this skill for any production incident, outage, or critical system failure. Triggers on: "production is down", "outage", "incident", "something broke in prod", "users are affected", "SEV-1", "SEV-2", "rollback needed", "postmortem", "post-mortem", "RCA for incident", "system is down", "critical bug in production", "emergency deploy", "data issue in production". This skill coordinates the respo

Read or update project changelog. Use PROACTIVELY whenever you need context about what was done previously in ANY area of the codebase, and after making changes or decisions worth preserving. This is your strategic memory - use it liberally to avoid redoing work or missing context.

Company research using Exa search. Finds company info, competitors, news, tweets, financials, LinkedIn profiles, builds company lists.

Interactive clinical safety hazard log creator and reviewer. Walks through FMEA-based hazard identification for health IT systems, producing a structured hazard log aligned with NHS DCB0129/DCB0160 templates and the clinical risk matrix (Severity × Likelihood). Use when starting a hazard log, reviewing an existing one, or identifying new hazards after a system change.

Best practices for Go project Makefiles. Use when creating or modifying a Go project Makefile: adding/reviewing targets, PHONY declarations, tab indentation, docker compose v2 targets.

Comprehensive testing specialist for all levels and types. Use when writing unit, integration, E2E, performance, or security tests; creating test strategies and plans; analyzing test coverage; building automation frameworks; managing defects; debugging test failures; manual testing (exploratory, usability, accessibility); scaling CI/CD test pipelines.

Evaluate AI model capabilities, limitations, and trade-offs relevant to a product decision. Use this skill when a team needs to understand what an AI model can and cannot reliably do for their use case.

Structure the trade-off decision between AI models, providers, or approaches for a given product use case. Use this skill when a team needs to choose between AI options with different capability, cost, latency, and risk profiles.

Recommend what to do after an experiment based on the result quality, effect size, and business context. Use this skill when the user has a completed experiment and needs a practical product decision such as roll out, rerun, iterate, segment-rollout, or reject.

Harness-aware issue triage with effort calibration and agent brief generation. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

Salva e restaura o estado de trabalho de codificação entre sessões. Use ao finalizar uma sessão, trocar de tarefa ou retomar o trabalho, para ter uma transição concisa de onde parou.