Skill329 estrellas del repoactualizado 5d ago

alternative-futures

Alternative Futures generates 2-4 competing scenarios that reinterpret the same evidence base to challenge an artifact's dominant narrative. Use this skill when exploring how different analytical frameworks or assumptions applied to identical evidence could produce fundamentally different conclusions, helping identify which observable indicators would distinguish between plausible alternatives.

Ver fuente Repositorio: de-anthropocentric-research-engine

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/alternative-futures && cp -r /tmp/alternative-futures/skills/alternative-futures ~/.claude/skills/alternative-futures

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

# Alternative Futures

Generates multiple competing scenarios to challenge the dominant narrative.

## Execution

Subagent — spawned via subagent-spawning/spawn-agent.

## Why Subagent

Alternative generation requires creative divergent thinking without anchoring on the artifact's conclusions. Isolated context prevents confirmation bias.

## Input

- **artifact**: The artifact whose conclusions are being challenged
- **evidence_base**: The evidence available (same evidence, different interpretations)

## Output

- **alternatives**: 2-4 divergent scenarios, each internally consistent
- **discriminators**: Observable indicators that would distinguish between alternatives
- **plausibility_ranking**: Relative plausibility of each alternative vs. the artifact's conclusion

Del mismo repositorio

formated-resultSkill

Experiment-specific - summarize the DARE executor's research design into a clean research_result report, forced to write back into the spec file produced by formated-specs.

formated-specsSkill

Experiment-specific - replaces writing-specs, emits DARE's 4-layer call plan as a clean research_graph schema. Last step forces load formated-result.

injection-fidelitySkill

loss-1 judge - read a sample's full dialogue and decide whether the user simulator semantically enacted its Policy Card. check-blind.

ladder-quality-orderSkill

loss-2 judge - pairwise quality comparison across the n rungs within one topic; decide monotonicity and endpoint separation. check-blind, D1-D5 only.

abductive-hypothesis-generationSkill

Strategy: 面对异常的最佳解释推理

ablation-brainstormSkill

Remove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.

ablation-component-mappingSkill

Map system architecture to ablatable units for ablation studies

ablation-designSkill

Design ablation studies to isolate component contributions in ML systems