Explorar skills

Audit and harden VPS security — fail2ban, SSH hardening, firewall setup

Writes a detailed, production-ready brief for an infographic designer from raw data or findings — specifying the story, the key figures, the recommended visual approach, the hierarchy of information, and the format requirements.

Translates the key findings of a scientific paper — abstract, methods, and conclusions — into clear, accurate plain English that any reader can understand without specialist knowledge.

Use when reviewing AI-generated code for architectural quality, design patterns, and engineering practices

Run coding agent benchmarks and verify results with nasde. Use this skill when the user wants to: - Run a benchmark (all tasks, single task, specific variant) - Re-run assessment evaluation on existing trial results - Check or verify results in Opik (traces, feedback scores, experiments) - Troubleshoot a failed benchmark run - View or compare trial results Even if the user doesn't say "benchmark"

Send a design document to Codex CLI for review, then revise the document based on the findings. Automatically loops until no critical issues remain or 5 rounds are completed.

Writes a targeted re-engagement email (or short sequence of two emails) for subscribers who have stopped opening the newsletter, designed to recover attention or prompt a clean unsubscribe before list hygiene becomes a deliverability problem.

Add new capabilities or modify NanoClaw behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to understand what the user wants.

Test coverage analysis: detect test framework, run test suite, capture failures and coverage metrics, identify coverage gaps in recent changes, and create a structured GitHub issue.

Delegate coding to OpenAI Codex CLI (features, PRs).

Esta skill converte desenhos 2D ortográficos de wireframe PNG em modelos 3D do Blender, exportados como glTF/GLB. Use-a ao fornecer imagens de wireframe para gerar um modelo 3D ou arquivo .glb.

Deep code review via Claude subagent — reviews uncommitted changes by default, loops until no critical issues remain. Use after /qq:test passes, before /qq:commit-push.