Pengfei Ni publishes agent skills for multi-agent research orchestration, with Deep Research splitting a research goal into parallel sub-goals and aggregating results into a report, alongside GitHub pull request review using parallel subagents. The catalogue also covers session handoff documents, adversarial design review, requirements brainstorming before implementation, YouTube transcript extraction, and image generation through Google Gemini, with several skills written for Chinese-language triggers.
Claude Code Settings
12 skills · 1,675 stars · MIT
Brainstorming Explore user intent, requirements, and design options through collaborative dialogue before imple…
Codex Skill Leverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review.
Deep Research Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via h…
Github Fix Issue Fix GitHub issues end-to-end — analysis, branch creation, implementation, testing, and PR submiss…
Github Review Pr Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents.
Gpt Image Skill Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc).
Grill Me 针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调…
Handoff 将当前对话压缩为交接文档（handoff document / session handoff brief），供下一个 agent 接续工作。手动调用 /handoff。
Nanobanana Skill Generate or edit images via Google Gemini (nanobanana).
Skill Creator Create, refine, and benchmark agent skills.
Translate Translate English or Japanese tech articles into natural, fluent Chinese.
Youtube Transcribe Skill Extract subtitles/transcripts from YouTube videos.