Compare agent skills before installing.

Rebuild the user's mental model of the current session with a tight recap — what we're doing, why, and where we are. Use this to recover after a break, a tangent, or a long subagent run. Trigger when the user invokes /human-context-rebuild, or says "remind me what we're doing", "我忘了", "我们到哪一步了", "where are we", "what was I doing", "summarize this session", "我们在干啥来着", "这是啥来着", "这个是干嘛的来着", "想不起来这个 session 在做什么", "脑子糊了", or similar re-orientation cues — including a bare "?" or "这是啥" pointing at the current work. Default to firing when the user signals lost context about the session itself; the cost of an unneeded recap is low. Do NOT trigger for "explain this code", "summarize this file", or any task-summary request — those are different.

Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo. Always use this skill when the user asks for 单色海报、双色印刷、单色调视觉、蓝色/绿色孔版印刷、risograph、网点照片、复古或当代编辑排版、zine poster, monochrome editorial poster, duotone print, or asks to use the mono-color style. It uses an adaptive white, gray, or pale-beige substrate, no more than two printing inks, active negative space, terse human language, and strong serif/grotesk/mono typography without making retro styling the default or copying a source composition, wording, logo, or artwork. Produce both the final generation prompt and the generated raster image unless the user explicitly asks for prompt only.