Explorar skills

화면 단위 E2E 테스트 자동화. Figma/코드 기반 테스트 케이스 도출 → Playwright 코드 생성 → Forge Loop(에스컬레이션 기반 자율 실행). "E2E 돌려줘", "화면 테스트 만들어줘", "이 페이지 자동 테스트" 등의 요청에 사용.

This skill should be used when writing commits, PRs, or comments that will be visible to OSS maintainers — it covers the no-AI-attribution rule, AI-tell avoidance in writing, and the situations where a human contributor should respond instead of the AI tool. Sibling to oss-contribution and pr-etiquette.

교차 모델 토론. Agent Teams / Codex CLI / self-debate 모드 선택. 설계 결정, 아키텍처 선택 시 활용. "어느 쪽이 나을까", "설계 비교해줘", "토론시켜줘", "교차 검증해줘" 등의 요청에 사용.

Generate C4 Container diagrams (Simon Brown standard) as editable .drawio XML files. Use when the user asks for architecture diagrams, system diagrams, C4 diagrams, container diagrams, or wants to visualize system architecture. Also use proactively when explaining systems with 3+ components where a visual would clarify the architecture.

Compare two document versions and produce a structured changelog — no git needed. Use for PRDs, SOPs, contracts, strategy docs. Triggers: 'compare these two documents', 'what changed between versions', 'generate a changelog', 'сравни две версии документа', 'что изменилось', 'сделай changelog'.

Send NPS/CSAT surveys and analyze results using [Delighted](https://composio.dev/toolkits/delighted) or [Satismeter](https://composio.dev/toolkits/satismeter)

Audit active Cowork plugins and get a keep/disable table. Reduces token usage and cognitive noise. Use when reviewing Cowork setup, adding new plugins, or starting a new project. Triggers: 'audit my plugins', 'cowork plugin audit', 'which plugins to disable', 'аудит плагинов', 'какие плагины отключить'.

First-time Cortex setup — creates team directory, config, and chief of staff agent.

Prioritize and group your reading list from a local md-file by topic and relevance to your role. Use when you have too many saved articles and need a weekly reading plan. Triggers: 'prioritize my reading list', 'what should I read first', 'расставь приоритеты в списке чтения', 'что мне читать первым'.

Detects when Claude is uncertain but presenting answers confidently. Teaches Claude to recognize and communicate uncertainty clearly instead of masking it with confident language.

Ensure every factual claim in a response is backed by verifiable evidence from the codebase, documentation, or external sources. Use when preparing technical documentation, code reviews, or any output where accuracy is non-negotiable.

Send CSAT follow-up emails to customers after ticket resolution via [Gmail](https://composio.dev/toolkits/gmail)