Explorar skills

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.

Produz um resumo estruturado de como outras mídias já cobriram um determinado tópico, permitindo que você aborde qualquer história com uma visão clara do cenário midiático existente.

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.

Writes a magazine-style profile piece on a person from interview notes, biographical background, and a stated editorial angle — delivering a polished draft that balances character, narrative, and context.

Scan the repo for scattered documentation files, analyze organization issues, and output cleanup recommendations. Analysis only — no changes made.

Produces a step-by-step guide for locating the correct press office, media contact, or spokesperson for a specific organisation, institution, or public figure — so the journalist sends their request to the right person on the first attempt.

Writes a concise summary, standfirst, abstract, or deck for a completed article at a specified length and format — capturing the essential argument and news value without spoiling the reading experience.

Runs a structured checklist over every statistic in your draft — flagging figures that look wrong, comparisons that may mislead, and numbers that need a primary source before they are safe to publish.

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.

Reviews a story brief, draft article, or broadcast script and flags potential legal risks — including defamation, privacy, contempt of court, and data protection — so you know what to check before publication.

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.