evidence-justification-assessment

Evaluate epistemic warrant, assess evidence quality and relevance, apply epistemic standards appropriate to different domains, and identify sources of knowledge

509 stars

Best use case

evidence-justification-assessment is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Evaluate epistemic warrant, assess evidence quality and relevance, apply epistemic standards appropriate to different domains, and identify sources of knowledge

Teams using evidence-justification-assessment should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/evidence-justification-assessment/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/domains/social-sciences-humanities/philosophy/skills/evidence-justification-assessment/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/evidence-justification-assessment/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How evidence-justification-assessment Compares

Feature / Agentevidence-justification-assessmentStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Evaluate epistemic warrant, assess evidence quality and relevance, apply epistemic standards appropriate to different domains, and identify sources of knowledge

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Evidence and Justification Assessment Skill

Evaluate epistemic warrant and evidence quality using appropriate standards across different domains of inquiry.

## Overview

The Evidence and Justification Assessment skill enables evaluation of epistemic warrant, assessment of evidence quality and relevance, application of epistemic standards appropriate to different domains, identification of knowledge sources, and analysis of justificatory structures.

## Capabilities

### Evidence Evaluation
- Assess evidence quality
- Evaluate relevance to claims
- Consider evidence weight
- Identify evidence types
- Check evidence reliability

### Justification Analysis
- Identify justificatory structures
- Evaluate warrant transmission
- Assess foundational vs. coherentist structures
- Analyze inferential chains
- Check for circular reasoning

### Epistemic Standards Application
- Apply domain-appropriate standards
- Distinguish epistemic contexts
- Evaluate certainty requirements
- Consider practical stakes
- Balance rigor and feasibility

### Source Assessment
- Identify knowledge sources
- Evaluate source reliability
- Consider testimony
- Assess expertise claims
- Check for bias and conflict

### Skeptical Analysis
- Address skeptical challenges
- Evaluate defeaters
- Consider alternative explanations
- Assess epistemic closure
- Navigate skeptical arguments

## Usage Guidelines

### When to Use
- Evaluating knowledge claims
- Assessing arguments
- Analyzing evidence
- Teaching epistemology
- Developing epistemic policies

### Best Practices
- Consider context and stakes
- Apply appropriate standards
- Document assessment reasoning
- Acknowledge uncertainty
- Remain open to revision

### Integration Points
- Conceptual Analysis skill
- Argument Mapping and Reconstruction skill
- Fallacy Detection and Analysis skill
- Formal Logic Analysis skill

## References

- Epistemic Evaluation process
- Evidence Assessment process
- Skeptical Challenge Analysis process
- Metaphysics and Epistemology Agent
- Logic Analyst Agent

Related Skills

compliance-evidence-collector

509
from a5c-ai/babysitter

Automated evidence collection across compliance frameworks from cloud providers, identity systems, and security tools

psychometric-assessment

509
from a5c-ai/babysitter

Develop, validate, and adapt measurement instruments including factor analysis, reliability testing, and cross-cultural validation

regulatory-compliance-assessment

509
from a5c-ai/babysitter

Evaluate organizational compliance with healthcare regulations including HIPAA, CMS Conditions of Participation, and accreditation standards through gap analysis and audit procedures

assessment-item-development

509
from a5c-ai/babysitter

Create valid, reliable assessment items across formats (multiple choice, constructed response, performance tasks) following psychometric best practices

conservation-assessment

509
from a5c-ai/babysitter

Assess condition of artworks and cultural objects, develop treatment proposals, and document conservation interventions following AIC ethical guidelines

safety-assessment

509
from a5c-ai/babysitter

Skill for structured safety assessment following ARP4761 guidelines

culture-assessment

509
from a5c-ai/babysitter

Assess and measure organizational culture using validated frameworks

adkar-assessment

509
from a5c-ai/babysitter

Assess and track ADKAR change readiness across stakeholder groups with intervention recommendations

process-builder

509
from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509
from a5c-ai/babysitter

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)

yolo

509
from a5c-ai/babysitter

Run Babysitter autonomously with minimal manual interruption.

user-install

509
from a5c-ai/babysitter

Install the user-level Babysitter Codex setup.