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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/yogsoth-ai/de-anthropocentric-research-engine --skill spice-application命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Strategy: Dialectic engine retuned for truth-seeking, not survival. A defender steelmans a claim into its MOST falsifiable form, a critic attacks to refute it, a judge classifies the exchange into BROKEN/CORROBORATED/UNFALSIFIABLE — the judge does NOT pick a winner or score persuasiveness. Methods: Irving debate (repurposed), Toulmin argumentation, Mayo severe testing.
Campaign: Logical extreme and boundary testing via reductio ad absurdum and edge-case analysis. Core question: Does this artifact collapse under logical limits and boundary conditions? Methods: Lakatos 1976, Dutilh Novaes 2016, BVA, Flyvbjerg Critical Case, Popper.
Campaign for mapping argument structures — extract claims, link evidence, assess strength, synthesize positions. Produces argument graphs in the wiki vault.
基于 SOC 职业分类
正在显示 SKILL.md
| name | spice-application |
| description | SOP: Apply the SPICE framework to structure an evaluation research question |
| version | 1.0.0 |
| category | hypothesis-formation |
| type | sop |
| campaign | research-question |
| input | Research intent (evaluation research direction) |
| output | Complete SPICE fill-in + RQ statement |
| dependencies | {"skills":["subagent-spawning"]} |
Apply the SPICE framework — suitable for evaluation research.
S: [research setting]
P: [evaluation perspective]
I: [intervention being evaluated]
C: [comparison object]
E: [evaluation metrics and methods]
RQ: "In [S], from [P]'s perspective, how does [I] compare to [C] in terms of [E]?"