‹ 首页

formated-specs

@yogsoth-ai · 收录于 5 天前 · 上游提交 2 周前

Spec-slot skill for the research-executor. Emit the 4-layer DARE orchestration of the assigned topic as one research-graph JSON fenced block in your reply. Replaces the generic spec-writing step.

适合你,如果你需要为研究执行器生成结构化的DARE编排规范。

/ 通过 npx 安装 校验哈希
npx oh-my-skill add yogsoth-ai/de-anthropocentric-research-engine/formated-specs
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- yogsoth-ai/de-anthropocentric-research-engine/formated-specs
/ 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-specs
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
~401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

取代常规的规范编写步骤,在回复中直接生成一个4层DARE编排的research-graph JSON代码块,包含节点、边、层标签和清单。

什么时候触发

当Claude处于研究执行器的规范步骤时触发,它会输出research-graph JSON而不是写spec文件。

装好后可以这样说
触发research-graph输出。
替换标准的spec编写。
直接输出结构化数据。
技能原文 SKILL.md作者撰写 · Apache-2.0 · 59ace64

formated-specs

You occupy the spec step of the research executor. Instead of writing a spec file, you emit the orchestration you are about to (notionally) run as a single JSON object inside one fenced block, directly in your reply.

Hard contract
  1. Emit exactly one fenced block opened with `research-graph (that exact info-string, hyphen, NOT `json ) and closed with ` .
  2. The block body is a single valid JSON object, the schema below.
  3. Emit it into your reply (the dialogue) — do NOT write it to a file. The block lands in this session's transcript; the harness cuts it from there.
  4. Atomicity: produce the whole block within one assistant turn.
  5. If you revise after pushback, emit a new full research-graph block; the harness keeps the LAST one. Never emit a half block.
  6. Mandatory final step: after the graph block, load and run formated-results.
research-graph schema
{
  "nodes":        [ {"id": "n1", "skill": "<skill-name>", "layer": "campaign|strategy|tactic|sop"} ],
  "edges":        [ {"from": "n1", "to": "n2", "kind": "calls|sequences"} ],
  "layer_labels": { "n1": "campaign|strategy|tactic|sop" },
  "manifest":     [ "<skill actually orchestrated>" ],
  "prereq_dag":   [ {"node": "n2", "requires": ["n1"]} ]
}

Populate manifest only with skills you actually orchestrated; do not fabricate. layer and layer_labels must respect the 4-layer architecture (campaign → strategy → tactic → sop). Judge nothing against academic standards; this is a structural record of orchestration only.

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。