Desenvolvimento

Print the currently-installed airc version (short git SHA, branch, commit subject, install dir). Use this to verify everyone in a mesh is on the same build.

Depura reproduzindo, isolando a causa raiz e corrigindo. Use para corrigir bugs, investigar falhas ou quando o usuário relata um erro ou comportamento inesperado, aplicável a qualquer linguagem, tempo de execução ou sistema.

Deploy TenantFlow to staging or production on Vercel. Handles build, test gate, and Vercel deployment.

Revisão de código automatizada e implacável para qualquer stack de tecnologia, com suporte a mais de 31 frameworks, verificação post-mortem, desenvolvimento de jogos e detecção anti-código-lixo de IA.

Use when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles — surface assumptions before coding, keep it simple, make surgical changes, define verifiable goals. Triggers on "review my diff", "check complexity", "am I overcomplicating this", "karpathy check", "before I commit", or any code quality concern where the LLM might be overcoding.

Send a message to the chat room. No target = everyone. Prefix @peer for a DM.

Prove the completed feature — full tests + build + typecheck + lint + browser-proof ladder — walking `spec.md` acceptance criteria one by one. Use when the user says "prove this", "run the full tests", "is this feature really done", "check it end-to-end". Not for single-slice or pre-completion proof.

webpify CLI の使い方、WebP 変換のベストプラクティス、品質設定ガイドを提供するスキル。「webpify の使い方」「画像を WebP に変換したい」「WebP 変換のベストプラクティス」「画像最適化の品質設定」「webpify のオプション」などのリクエストで使用する。

O endereçamento de conteúdo UOR é a base para a persistência holônica. Ele se ativa ao discutir identidade baseada em conteúdo, a relação 'mesmos bytes, mesmo hash', derivação de GUID, independência de infraestrutura, codificação Braille IRI ou por que a identidade segue o conteúdo e não a localização.

Run parallel feature work safely with Git worktrees. Standardizes branch isolation, port allocation, environment sync, and cleanup so each worktree behaves like an independent local app. Optimized for multi-agent workflows where each agent or terminal session owns one worktree. Use when running multiple feature branches simultaneously, isolating experimental work, or coordinating multi-agent devel

Use when the user asks to write specs before code, define acceptance criteria, plan features before implementation, generate tests from specifications, or follow spec-first development practices.

Industrial-strength NLP with spaCy 3.x for text processing and custom classifier training. Use when "installing spaCy", "selecting model for nlp" (en_core_web_sm/md/lg/trf), "tokenization", "POS tagging", "named entity recognition" (NER), "dependency parsing", "training TextCategorizer models", "troubleshooting spaCy errors" (E050/E941 model errors, E927 version mismatch, memory issues), "batch pr