dare-research-engine
Use the DARE research engine to crystallize research goals, write executable research specs, and execute staged research workflows.
适合你,如果需要系统化执行多步骤研究任务
/ 通过 npx 安装 校验哈希
npx oh-my-skill add yogsoth-ai/de-anthropocentric-research-engine/dare-research-engine/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- yogsoth-ai/de-anthropocentric-research-engine/dare-research-engine/ 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/dare-research-engine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
~278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
Claude 会使用 DARE 研究引擎来明确研究目标、编写可执行的研究规范,并执行分阶段的研究工作流。
什么时候触发
当你说出需要研究或规划研究项目的指令时触发。
装好后可以这样说
Claude 会启动研究引擎并编写研究规范。
Claude 会读取并执行预设的研究规范。
Claude 会引导你明确研究目标。
技能原文 SKILL.md
DARE Codex Adapter
You are running the Codex port of DARE.
When this skill is invoked:
- Treat "CC" and "Claude Code" in upstream DARE documents as "Codex".
- Resolve the DARE skill root from the first existing path:
.dare/skills/when this adapter was installed into another repositoryskills/when running from the DARE repository clone itself- Read
<skill-root>/de-anthropocentric-research-engine/SKILL.mdfirst. - Read
<skill-root>/research-catalog/SKILL.mdbefore selecting research packages. - Treat YAML
dependenciesin each upstreamSKILL.mdas the authoritative call graph. - Open dependency skills from
<skill-root>/<skill-name>/SKILL.mdonly when needed. - Use Codex-style invocation names such as
$dare-research-engine, not Claude slash commands. - Preserve runtime context in
context/INDEX.mdand related context files. - Never write API keys or secrets into specs, context files, or committed config.
Do not load every upstream skill up front. The upstream skills/ tree is the DARE knowledge base, not a Codex skill registry.
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。
…