v3.1 March 2026 Temporal Knowledge

Extract Knowledge, Not Text

An AI agent skill that distills any document into structured knowledge graphs with temporal awareness. Atomic concepts, explicit relationships, time context, zero redundancy.

claude skill install knowledge-distiller

7-Phase Distillation

01 Extract Read any file format: PDF, DOCX, PPTX, XLSX, CSV, HTML, images
02 Analyze Identify concepts, entities, relationships, temporal context, and core statements
03 Structure Build hierarchical clusters, concept map, and temporal layers
04 Markdown Write atomic knowledge blocks with wikilinks, confidence, and time context
05 JSON-LD Generate rich graph nodes with temporal objects, weighted edges, time-stamped chunks
06 Validate Check JSON, node richness, temporal consistency, chunk time prefixes
07 Deliver Output paired .knowledge.md + .knowledge.json files

Same Knowledge, Two Formats

Every distillation produces a paired set: human-readable Markdown for Obsidian and LLMs, plus machine-readable JSON-LD for graph databases and embeddings. Both carry full temporal metadata.

claude-skills-guide.knowledge.md Humans + LLMs
---
title: Building Skills for Claude
source_type: PDF
source_date: "2026-01"
source_period: null
temporal_confidence: "inferred"
distilled: "2026-03-16"
confidence: high
companion: claude-skills-guide.knowledge.json
clusters:
  - name: Skill Anatomy
    concepts: [Skill, SKILL.md, YAML Frontmatter]
  - name: Design Principles
    concepts: [Progressive Disclosure, Composability]
---

## Kernwissen

### Skill

📊 high | 🏷️ Skill Anatomy | 📅 2026-01

**Was:** A folder-based instruction package
that teaches Claude how to handle specific
task types. SKILL.md is the only required file.

**Zeitbezug:** Valid from 2025 · Source: 2026-01

**Beziehungen:**
- Based on → [[SKILL.md]]
- Uses → [[Progressive Disclosure]]
- Enables → [[Workflow Patterns]]
claude-skills-guide.knowledge.json Graph-DB + Embeddings
{
  "@context": {
    "@vocab": "https://schema.org/",
    "kd": "https://knowledge-distiller.dev/schema/"
  },
  "metadata": {
    "source_date": "2026-01",
    "source_period": null,
    "temporal_confidence": "inferred",
    "schema_version": "3.1"
  },
  "nodes": [{
    "id": "skill",
    "label": "Skill",
    "confidence": "high",
    "temporal": {
      "source_date": "2026-01",
      "valid_from": "2025",
      "valid_until": null,
      "temporal_confidence": "inferred"
    },
    "definition": "A folder-based instruction
  package for Claude...",
    "statements": ["SKILL.md is the
  only required file"]
  }],
  "chunks": [{
    "id": "skill",
    "source_period": null,
    "embedding_text": "As of early 2026:
  A skill is a folder-based instruction
  package that teaches Claude how to
  handle specific task types."
  }]
}

Temporal Dimension

When you distill documents across years, knowledge without a time axis creates contradictions. A concept described in a 2025 guide and updated in a 2026 guide aren't conflicting facts — they're an evolution. v3.1 adds three temporal layers so the graph knows when.

LayerFieldsPurpose
Source source_date, source_period When was the knowledge published?
Validity valid_from, valid_until When does this information apply?
Distillation distilled When was the extraction performed?
2024-12-31 2024-Q4 FY2024 2020/2024

ISO 8601 with flexible granularity: exact date, quarter, fiscal year, or interval

temporal resolution
// Same concept, two documents, no conflict

// From: Skills Guide v1 (2025)
{
  "id": "distribution-model",
  "definition": "Shared via Claude.ai only",
  "temporal": {
    "source_date": "2025-06",
    "valid_from": "2025",
    "valid_until": "2025-12"
  }
}

// From: Skills Guide v2 (2026)
{
  "id": "distribution-model",
  "definition": "Claude.ai + Claude Code + API",
  "temporal": {
    "source_date": "2026-01",
    "valid_from": "2026",
    "valid_until": null
  }
}

// → Not a contradiction — an evolution
// → temporal_confidence: "inferred"
Build time series across documents
Resolve contradictions via time context
Detect stale knowledge automatically
Track supersession chains

Built for Knowledge Systems

Knowledge Graph
Rich nodes with definitions, statements, and relevance. Weighted, typed edges between concepts. JSON-LD with schema.org context.
Temporal Awareness
Every node, fact, and chunk carries time context: source period, validity range, and confidence. Multi-document graphs stay consistent across years.
Hierarchical Clusters
Concepts are grouped into thematic clusters. Each block carries its cluster assignment. Concept map shows the full topology.
Embedding-Ready Chunks
Clean-text chunks without Markdown syntax, emoji, or wikilinks. Each chunk starts with a natural-language time reference for temporal disambiguation.
Per-Block Confidence
Every knowledge block and edge carries a confidence rating: high (evidence-backed), medium (interpretive), or low (inferred).
Obsidian Wikilinks
All cross-references use [[wikilink]] syntax. Drop knowledge files into your vault and navigate between concepts instantly.

Typed Relationships

Eight relationship types capture the full spectrum of how concepts relate. Each edge carries a type, natural-language label, numeric weight, and confidence score.

TypeMeaningSymbol
usesDependency
enablesCausality
based-onFoundation
part-ofComposition
tensionTrade-off / Contradiction
replacesSupersession
extendsExtension
example-ofInstantiation
node schema v3.1
// Each node is self-contained + temporal
{
  "id": "konzept-kebab-case",
  "label": "Display Name",
  "cluster": "cluster-id",
  "confidence": "high",
  "temporal": {
    "source_period": "FY2024",
    "valid_from": "2024",
    "valid_until": null,
    "temporal_confidence": "explicit"
  },
  "definition": "Clear, standalone definition",
  "relevance": "Why this matters",
  "statements": [
    "Atomic statement 1",
    "Atomic statement 2"
  ]
}

// Time-stamped embedding chunks
{
  "id": "concept-a",
  "source_period": "FY2024",
  "embedding_text": "Stand Geschäftsjahr
  2024: Plain text paragraph, no
  markdown, no emoji, no syntax."
}

Version History

v3.1
Temporal Dimension
Three temporal layers: source period, validity range, distillation date. Per-node temporal objects. Time-stamped facts and embedding chunks. ISO 8601 with flexible granularity (date, quarter, fiscal year, interval). Enables time series, contradiction resolution, and stale knowledge detection across multi-document graphs.
v3.0
Dual Output Architecture
Rich graph nodes with definitions and statements as properties. Dual output: .knowledge.md + .knowledge.json. Embedding-ready clean-text chunks. JSON-LD with schema.org context.
v2.0
Hierarchical Clusters + Confidence
Added thematic cluster grouping, YAML machine-readable graph in frontmatter, and per-block confidence ratings (high / medium / low).
v1.0
Initial Release
6-phase workflow. Atomic knowledge blocks with Obsidian wikilinks. Concept map, facts table, open questions.

Supported Input Formats

PDF DOCX PPTX XLSX CSV JSON TXT MD HTML PNG JPG URLs
works with
Obsidian Neo4j Gephi OpenAI Embeddings Cohere RAG Pipelines LangChain LlamaIndex

Start Distilling

Install the skill, point it at any document, and get temporally-aware structured knowledge in seconds.

View on GitHub See Examples