Delegate independent tasks to specialized agents working concurrently with isolated context.
Epistemology Skill
epistemology
Master epistemology - the theory of knowledge, justification, and belief. Use for: knowledge, justification, skepticism, sources of knowledge, epistemic virtue. Triggers: 'knowledge', 'epistemology', 'justification', 'belief', 'Gettier', 'skepticism', 'certainty', 'evidence', 'testimony', 'percep...
SKILL.md
Full skill instructions
Epistemology Skill
Master the theory of knowledge: What is knowledge? How is belief justified? Can we know anything?
Core Questions
| Question | Issue | Stakes |
|---|---|---|
| What is knowledge? | Analysis | Definition of knowledge |
| What justifies belief? | Justification | Epistemic norms |
| Can we know anything? | Skepticism | Scope of knowledge |
| What are sources of knowledge? | Sources | Perception, reason, testimony |
The Analysis of Knowledge
Traditional Analysis
JTB: Knowledge = Justified True Belief
S knows that P iff:
1. S believes that P (belief condition)
2. P is true (truth condition)
3. S is justified in believing P (justification condition)
Gettier Problem
Gettier Cases show JTB is not sufficient:
GETTIER CASE #1
═══════════════
Smith has strong evidence that Jones will get the job
(told by company president).
Smith also knows Jones has 10 coins in his pocket.
Smith infers: "The man who will get the job has 10 coins
in his pocket."
Unknown to Smith: HE (Smith) will get the job.
And Smith happens to have 10 coins in his pocket.
Smith's belief is:
✓ Justified (by evidence about Jones)
✓ True (Smith will get job, has 10 coins)
✗ NOT knowledge (too lucky!)
Post-Gettier Theories
Fourth Condition Approaches:
- No false lemmas
- Causal connection
- Defeasibility (no truths that would defeat justification)
Tracking (Nozick):
- S knows P iff: If P were false, S wouldn't believe P
- Sensitivity condition
Safety (Sosa, Pritchard):
- S knows P iff: S couldn't easily have been wrong
- In nearby possible worlds where S believes P, P is true
Virtue Epistemology:
- Knowledge = true belief from intellectual virtue
- Success attributable to cognitive ability
Theories of Justification
Foundationalism
FOUNDATIONALIST STRUCTURE
═════════════════════════
DERIVED BELIEFS
├── Justified by inference
├── From more basic beliefs
└── Not self-justifying
↑
│
BASIC BELIEFS
├── Self-justifying
├── Need no support from other beliefs
└── Foundation of knowledge
Basic Beliefs:
- Classical: self-evident, incorrigible
- Modest: defeasibly justified without inference
Coherentism
COHERENTIST STRUCTURE
═════════════════════
┌─────────────────────┐
│ │
┌───▼───┐ ┌─────┴───┐
│ Belief ├──────────►│ Belief │
│ A │◄──────────┤ B │
└───┬────┘ └────┬───┘
│ │
│ ┌─────────┐ │
└────► Belief ◄──────┘
│ C │
└────────┘
No foundations; mutual support
Objection: Coherent fiction could be well-justified but false (isolation problem)
Infinitism
- No basic beliefs
- No circular justification
- Infinite regress is not vicious
- We can always provide further reasons
Internalism vs. Externalism
| Internalism | Externalism |
|---|---|
| Justifiers must be accessible to subject | Justifiers may be external |
| What I can know by reflection | Reliable processes suffice |
| Epistemic responsibility | Connection to truth matters |
| Examples: evidentialism | Examples: reliabilism |
Skepticism
Cartesian Skepticism
SKEPTICAL ARGUMENT
══════════════════
1. I cannot know I'm not a brain in a vat (BIV)
2. If I know I have hands, I can deduce I'm not a BIV
3. If I can't know the conclusion, I can't know the premise
4. Therefore, I don't know I have hands
CLOSURE PRINCIPLE:
If S knows P, and S knows P→Q, then S can know Q
Responses to Skepticism
Moorean Shift:
- I know I have hands
- If I have hands, I'm not a BIV
- Therefore, I know I'm not a BIV
- Common sense trumps skeptical premises
Contextualism:
- "Know" has different standards in different contexts
- In everyday contexts, we do know
- In philosophical contexts, standards are higher
- Both claims are true (in their contexts)
Relevant Alternatives:
- Knowledge requires ruling out relevant alternatives
- BIV is not a relevant alternative in normal contexts
Sources of Knowledge
Perception
Direct Realism: We perceive external objects directly Indirect Realism: We perceive sense-data caused by objects Idealism: Objects are mind-dependent
Problems:
- Perceptual error, illusion
- Skepticism about external world
- Theory-ladenness of observation
Reason (A Priori Knowledge)
Rationalism: Some knowledge is innate or a priori Examples: Mathematics, logic, conceptual truths
Problems:
- How do we access a priori truths?
- Are they merely analytic?
- Quine's attack on analytic/synthetic distinction
Testimony
Reductionism: Testimony reducible to other sources Anti-Reductionism: Testimony is fundamental source
Conditions: Speaker sincerity, competence, listener's critical uptake
Memory
Preservative: Memory preserves justification Generative: Memory can generate new knowledge Problems: False memories, reliability
Key Concepts
Epistemic Virtues
| Virtue | Description |
|---|---|
| Intellectual humility | Recognizing limits |
| Open-mindedness | Considering alternatives |
| Intellectual courage | Pursuing truth despite cost |
| Thoroughness | Careful investigation |
| Fair-mindedness | Impartial assessment |
Evidence
Evidentialism: Justification proportional to evidence Evidence types: Perceptual, testimonial, inferential
Degrees of Belief (Bayesian)
- Credences: Degrees of belief (0-1)
- Conditionalization: Update on evidence
- Bayes' theorem: P(H|E) = P(E|H)·P(H)/P(E)
Key Vocabulary
| Term | Meaning |
|---|---|
| Justified | Having good reasons |
| A priori | Independent of experience |
| A posteriori | Dependent on experience |
| Analytic | True by meaning |
| Synthetic | True by world |
| Infallible | Cannot be wrong |
| Defeasible | Can be overridden |
| Propositional knowledge | Knowledge that P |
| Knowledge how | Practical knowledge |
| Epistemic luck | Being right by chance |
| Closure | Knowledge closed under known entailment |
Integration with Repository
Related Themes
thoughts/knowledge/: Epistemological explorationsthoughts/consciousness/: Perception, self-knowledge
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
