菜单
Use the DARE research engine to crystallize research goals, write executable research specs, and execute staged research workflows.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | dare-research-engine |
| description | Use the DARE research engine to crystallize research goals, write executable research specs, and execute staged research workflows. |
You are running the Codex port of DARE.
When this skill is invoked:
.dare/skills/ when this adapter was installed into another repositoryskills/ when running from the DARE repository clone itself<skill-root>/de-anthropocentric-research-engine/SKILL.md first.<skill-root>/research-catalog/SKILL.md before selecting research packages.dependencies in each upstream SKILL.md as the authoritative call graph.<skill-root>/<skill-name>/SKILL.md only when needed.$dare-research-engine, not Claude slash commands.context/INDEX.md and related context files.Do not load every upstream skill up front. The upstream skills/ tree is the DARE knowledge base, not a Codex skill registry.
Append research process and results to the current Phase's context file. Each append MUST contain >=500 lines of markdown covering both process and results. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase.
Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed.
The optimizer brain for the ladder-foundry pretraining loop. Runs the two-level nested batch loop, delegates gating to gate_eval, attributes a failing batch to one weight (attribute-first), and recovers from disk after compaction. Control flow is fully scripted; only the backprop attribution is a judgment call.
Loss-2 judge (codex role). Over one topic's 6 shuffled research-design samples, pairwise-rank by quality using the D1–D5 standard. Emit the pairwise log; the harness computes the order and the ladder verdicts. Judge quality difference, never against academic standards.
Loss-1 judge (codex role). Given one sample's de-identified dialogue and its PolicyCard, decide axis-by-axis whether the user-simulator enacted the card's per-axis pressure. Judge enactment of the card, never whether the research is good.
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.