Skill329 estrellas del repoactualizado 5d ago

assumption-audit

The assumption-audit skill systematically identifies hidden assumptions within methods, theories, or research gaps and classifies them by vulnerability using a load-bearing versus likely-false matrix. Use it when you need to surface dangerous assumptions that are both foundational to an argument yet remain unexamined or unstated, validating their causal logic through structured validation checks.

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

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

Definición

SKILL.md

# Assumption Audit

Systematically audit assumptions underlying a method, theory, or gap.

## When to Use

Need to identify which hidden assumptions are most dangerous — load-bearing yet unexamined.

## Budget

| Base SOP | Target | ±10% Range |
|----------|--------|------------|
| web-search | 30 | 27–33 |
| web-research | 10 | 9–11 |
| paper-overview | 30 | 27–33 |
| paper-search | 20 | 18–22 |
| paper-research | 10 | 9–11 |

## State Ledger

```
<HARD-GATE>
| SOP | Done | Target | % |
|-----|------|--------|---|
| web-search | ? | 30 | ? |
| web-research | ? | 10 | ? |
| paper-overview | ? | 30 | ? |
| paper-search | ? | 20 | ? |
| paper-research | ? | 10 | ? |
Budget Gate: OPEN/CLOSED (>=80% required to exit)
</HARD-GATE>
```

## Available Tactics

- assumption-stress-test

## Available SOPs

**Import:** web-search, web-research, paper-overview, paper-search, paper-research
**Subagent:** abp-vulnerability-classification, clr-validation
**Shared:** assumption-surfacing

## Execution Guidance

Surface all assumptions (shared SOP), classify by vulnerability (ABP), validate causal logic (CLR 8-check). Focus on load-bearing + non-explicit assumptions.

## Output Format

Assumption Audit Report — assumption inventory, vulnerability matrix, CLR validation results, priority list for challenging.

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