菜单
Use when receiving research review feedback, before implementing suggestions — requires verification against actual data and scientific reasoning, not performative agreement
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 | receiving-research-review |
| description | Use when receiving research review feedback, before implementing suggestions — requires verification against actual data and scientific reasoning, not performative agreement |
Handle review feedback with scientific rigor. Verify claims against actual data before acting. Push back on incorrect assessments with evidence.
Core principle: Verify before implementing. Evidence before agreement. Scientific correctness over social comfort.
When you receive a research review report:
Never respond to a review with:
These are performative, not scientific. The reviewer may be wrong. Verify first.
If ANY item in the review is unclear:
STOP. Do not implement anything.
Ask for clarification on ALL unclear items before proceeding. Why: review items may be related. Partial understanding leads to wrong implementations that waste time and may introduce new errors.
Push back (with evidence) when:
How to push back:
Before implementing any suggestion from an external reviewer:
After addressing CRITICAL and MAJOR issues:
eureka:requesting-research-revieweureka:requesting-research-review returns feedbackeureka:requesting-research-review (for re-review after fixes)Use during or after manuscript writing to verify every quantitative claim traces to actual data, every figure is script-generated, and all results including negative ones are reported
Use when starting any conversation involving research, hypotheses, experiments, data analysis, scientific claims, or manuscript writing — establishes how to find and use Eureka research skills
Use when a research design has been approved and needs to be broken into executable experiment steps — the research equivalent of an implementation plan
Use when creating, updating, or reviewing a research figure (plot, chart, brain map, heatmap, schematic) — guides chart-type selection, typography, colorblind-safe palette, layout, and journal-specific export specs. Dispatches a figure-reviewer subagent after rendering. Complements claims-audit (which checks figure integrity) by checking figure design.
Use when running any experiment or analysis — hypothesis and analysis plan must be registered before seeing results, the scientific equivalent of test-driven development
Use when writing a research manuscript — guides section-by-section writing with prerequisite gates, citation discipline, number traceability, and per-section subagent review. Activated after experiment results are reviewed and before claims-audit.