formated-results
Closing skill for the research-executor, loaded as the last step of formated-specs. Summarize the design just produced into one research-result JSON fenced block in your reply. Do not execute the research.
适合你,如果需要在研究执行后自动生成结构化结果
/ 通过 npx 安装 校验哈希
npx oh-my-skill add yogsoth-ai/de-anthropocentric-research-engine/formated-results/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- yogsoth-ai/de-anthropocentric-research-engine/formated-results/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify yogsoth-ai/de-anthropocentric-research-engine/formated-results安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
388GitHub stars
~281上下文体积 · 单文件
索引托管
怎么用
商店整理自技能原文 · 版本 59ace64 · 表述以原文为准它做什么
在对话的最后一轮,将前一步生成的研究设计总结成一个固定的代码块,输出JSON格式的结果(标题、章节、附件引用),不执行新研究。
什么时候触发
当 formated-specs 流程执行完毕,需要输出最终研究成果时自动触发。
装好后可以这样说
触发总结并输出 research-result 代码块。
强制在对话中输出结构化结果。
按规范输出 title 和 sections。
技能原文 SKILL.md
formated-results
You are the closing step, loaded by formated-specs. Summarize the design you just produced into one fenced block, in the same dialogue. Add no new research — only summarize what formated-specs already orchestrated.
Hard contract
- Emit exactly one fenced block opened with
`research-result(that exact info-string) and closed with`. - Body is a single valid JSON object, the schema below.
- Emit it into your reply (the dialogue), not to a file.
- Atomicity: one assistant turn.
- On revision, emit a new full block; the harness keeps the LAST one.
- Same-source: only summarize the design
formated-specsproduced. The depth is document-level (hypothesis + design body); do not run experiments.
research-result schema
{
"title": "<one-line title of the design>",
"sections": [ {"heading": "<section heading>", "body": "<design prose>"} ],
"artifacts": [ "<spec filename or figure reference>" ]
}
Sections carry the design body. Judge nothing against academic standards.
按 Apache-2.0 许可原样转载,未经改动 · 在 GitHub 查看 →
评论
登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…