Skill329 estrellas del repoactualizado 5d ago

assumption-constraint

The assumption-constraint skill identifies and ranks the most fragile assumptions in research experiments through systematic vulnerability analysis. It quantifies how likely each assumption is to fail and what impact that failure would have, then prioritizes validation testing starting with the cheapest experiments that resolve the highest-impact uncertainties. Use this when designing experiments to stress-test your foundational beliefs before committing significant resources.

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/assumption-constraint && cp -r /tmp/assumption-constraint/skills/assumption-constraint ~/.claude/skills/assumption-constraint

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

Definición

SKILL.md

# Strategy: Assumption Constraint

## Methodology

Systematic assumption vulnerability analysis:
- **Extraction**: Surface all implicit and explicit assumptions
- **Scoring**: Quantify vulnerability (confidence × evidence / testability)
- **Impact assessment**: Blast radius × recovery cost
- **Prioritization**: Vulnerability × Impact = Priority
- **Validation planning**: Cheapest test that resolves uncertainty

Assumption categories:
| Category | Examples |
|----------|----------|
| Technical | Method convergence, architecture suitability |
| Data | Availability, quality, representativeness |
| Resource | Sufficiency of compute, time, expertise |
| Environmental | Tool stability, API access, policy |
| Theoretical | Effect existence, measurability, magnitude |

## Execution Flow

1. **Challenge Assumptions** → call `assumption-challenging` SOP
   - Input: experiment plan, hypothesis
   - Output: assumption inventory with validity assessment

2. **Quantify Validation Cost** → call `resource-quantification` SOP
   - Input: validation experiments for top assumptions
   - Output: cost to validate each assumption

3. **Rank Sensitivity** → invoke `sensitivity-ranking` tactic
   - Determine which assumptions are most binding

4. **Report** → synthesize vulnerability assessment
   - Top-5 fragile assumptions with validation paths
   - Binding assumption constraint identification

## Budget Gate

| Resource | Budget | Notes |
|----------|--------|-------|
| Subagent calls | ≤5 | 2 SOPs + synthesis |
| Iterations | ≤2 | Re-rank if new assumptions surface |
| Output size | ≤3000 tokens | Ranked table + validation plan |

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