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 weight-elicitation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。
正在显示 SKILL.md
| name | weight-elicitation |
| description | Determine criteria weights using AHP, Swing, BWM, MACBETH, or Simos methods. |
| dependencies | {"tactics":["multi-method-triangulation"],"sops":["criterion-definition","weight-elicitation-sop"]} |
Purpose: Determine relative weights for evaluation criteria through structured methods, supporting AHP, Swing, BWM, MACBETH, Simos, and other weighting methods.
When to use:
| Base SOP | Target | ±10% Range |
|---|---|---|
| criterion-definition | 5-8 criteria | 4-9 |
| weight-elicitation-sop | ≥2 methods | 2-3 |
| rank-comparison | 1 comparison | 1 |
strategy: weight-elicitation
status: pending
criteria_defined: false
method_1: null
method_2: null
weights_1: []
weights_2: []
compared: false
final_weights: []
## Weight Determination Results
### Weight Comparison
| Criterion | AHP Weight | BWM Weight | Average | Difference |
|-----------|------------|------------|---------|------------|
### Consistency Check
- AHP CR: [value] (< 0.1 ✓)
- BWM ξ*: [value]
### Final Weights
| Criterion | Weight | Rank |
|-----------|--------|------|
### Method Selection Rationale
[Why the chosen method's weights are used as the final result]
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use |
|---|---|
| multi-method-triangulation | Apply 2-3 MCDA methods to the same candidates, compare rankings, and identify method-sensitive options. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| criterion-definition | Extract evaluation criteria from research goals and candidate alternatives. |
| weight-elicitation-sop | Compute criteria weights using a specified elicitation method (AHP, Swing, BWM, MACBETH, or Simos). |
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