formated-results
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…
Select the single best candidate from a set using WSM, TOPSIS, AHP, MAUT,
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill best-option-selection --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/best-option-selectionContext preview
The summary Claude sees to decide when to auto-load this skill.
Select the single best candidate from a set using WSM, TOPSIS, AHP, MAUT,
name: best-option-selection description: Select the single best candidate from a set using WSM, TOPSIS, AHP, MAUT, or VIKOR methods. dependencies: tactics: - convergence-scoring-matrix-construction
**Purpose:** Select the single best-performing alternative from a candidate set, supporting WSM, TOPSIS, AHP, MAUT, VIKOR, and other methods.
**When to use:**
| Base SOP | Target | ±10% Range | |----------|--------|------------| | criterion-definition | 5-8 criteria | 4-9 | | weight-elicitation-sop | 1 weight vector | 1 | | alternative-scoring | 1 score matrix | 1 | | normalization | 1 normalized matrix | 1 | | scoring-synthesis | 1 recommendation | 1 |
strategy: best-option-selection status: pending criteria_defined: false weights_computed: false scores_computed: false normalized: false synthesized: false selected_method: null result: null
1. Invoke scoring-matrix-construction tactic to build the score matrix 2. Select aggregation method based on problem characteristics (WSM for simple scenarios, TOPSIS when ideal solution reference is needed, VIKOR when compromise solution is needed) 3. Invoke scoring-synthesis to produce final recommendation 4. If user questions the result, switch methods, recompute, and compare
## Best Option Recommendation **Recommended:** [Alternative name] **Overall Score:** [Score value] **Method Used:** [WSM/TOPSIS/AHP/MAUT/VIKOR] ### Score Ranking | Rank | Alternative | Overall Score | Key Strengths | |------|-------------|---------------|---------------| ### Sensitivity Notes [Impact of weight changes on the result]
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | convergence-scoring-matrix-construction | Build a complete scoring matrix through criterion definition, weighting, scoring, normalization, and sensitivity testing. |
<!-- END available-tables (generated) -->
The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.
Repo: yogsoth-ai/de-anthropocentric-research-engine
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…
Spec-slot skill for the research-executor. Emit the 4-layer DARE orchestration of the assigned topic as one research-graph JSON fenced block in your reply.…
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…
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…
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…
Tactic: Extract atomic units from one paper and score how much of a caller-supplied summary covers. Use for ACU-style binary or Nugget-style ternary recall…