validating-knowledge-structure

A quality-checking guide for knowledge graphs, which are structured maps of items and their relationships. It combines automated schema and relationship checks with reviews of mathematical and educational consistency.

In plain words
What is it for?
Use it to validate a completed knowledge graph and produce a pass, warning, or failure report.
Why use it?
It catches broken references, cycles, missing relationships, and learning structures that may not make sense before the graph is used.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/vanderbilt-data-science/knowledge-spaces/validating-knowledge-structure
Any agent
npx skills add vanderbilt-data-science/knowledge-spaces --skill validating-knowledge-structure
Clone the repo
git clone --depth 1 https://github.com/vanderbilt-data-science/knowledge-spaces

Made for: Claude Code, Codex.

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,562 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00091 $0.02562
Opus 5 $0.00046 $0.01281
Sonnet 5 $0.00018 $0.00512
Haiku 4.5 $0.00009 $0.00256

Measured 2d ago against content hash 2919aaaae80f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validating-knowledge-structure scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/validating-knowledge-structure/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validating Knowledge Structure

Role

You are a KST quality assurance analyst validating knowledge graphs for mathematical consistency, educational plausibility, completeness, and CbKST integrity. You ensure the knowledge structure satisfies KST axioms (Doignon & Falmagne, 1999), CbKST alignment (Heller & Stefanutti, 2024), and educational soundness before the graph enters Phase 3 application skills.

Input

$ARGUMENTS

The user provides:

  • A path to a complete knowledge graph file (with items, surmise relations, and optionally competences, competence relations, knowledge states, learning paths)
  • Optionally, original course materials for coverage checking

Load the graph and verify it conforms to schemas/knowledge-graph.schema.json.

Step 0: Automated Validation

Run the automated validation script as the first step:

python3 scripts/kst_utils.py validate <graph-path>

This checks:

  • Referential integrity (all IDs in relations reference existing items)
  • Duplicate relations
  • Acyclicity (no cycles in surmise relation)
  • Transitivity (all transitive relations present)
  • Self-loops (reflexivity should be implicit)
  • Item ID uniqueness
  • Knowledge state properties (if populated): empty set, full set, union closure
  • Bloom's level consistency
  • Prerequisite load (>7 direct prerequisites)
  • Orphaned items

Review the FAIL/WARN/PASS output, then perform the additional reasoning-based checks below.

Validation Checks

Category 1: Mathematical Validity

Hard requirements -- failures mean the structure is mathematically incorrect. See shared-references/kst-foundations.md for formal definitions.

1.1 Surmise Relation Properties:

  • Transitivity: for all a -> b and b -> c, a -> c exists. Fix: python3 scripts/kst_utils.py closure <graph-path> --apply
  • Acyclicity: no cycles among distinct items
  • Referential integrity: all IDs in surmise_relations reference items in items[]
  • No self-loops: no explicit (a -> a) entries
  • No duplicate relations: no repeated (prerequisite, target) pairs

Read the full file on GitHub · 229 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 229 lines · 91 tokens per session scan A 2919aaaae80f

Subscribe to this mod's changes

validating-knowledge-structure is a skill published in the GitHub repository vanderbilt-data-science/knowledge-spaces (20 stars, last pushed 6mo ago), licensed MIT. It adds 91 tokens to every session and 2,562 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

learning-analytics-interpretation-guide

Interpret learning analytics data and translate dashboard findings into actionable teaching decisions. Use when reviewing LMS data, quiz patterns, or engagement metrics.

GarethManning/education-agent-skills · 34 tokens

criterion-referenced-rubric-generator

Generate a criterion-referenced rubric with descriptive performance levels for a task or objective. Use for marking guides and general curriculum contexts. For Manning programmes where Competent = success, use coherent-rubric-logic-builder instead.

GarethManning/education-agent-skills · 52 tokens

kud-chart-author

Authors or reviews Know/Understand/Do charts for competency-based learning targets across developmental bands. Handles seven input types from raw curriculum documents to existing LT sets. Routes to upstream skills when stronger inputs are available.

GarethManning/education-agent-skills · 46 tokens

project-brief-designer

Design a project-based learning brief with a driving question, milestones, and assessment criteria. Use when planning PBL units, inquiry projects, or extended investigations.

GarethManning/education-agent-skills · 37 tokens

ai-feedback-design-principles

Audit and redesign AI-generated feedback for pedagogical quality, timing, and learning impact. Use when building or reviewing automated feedback in digital learning tools.

GarethManning/education-agent-skills · 36 tokens

cognitive-tutoring-architecture-designer

Map knowledge components and skill hierarchies for a cognitive tutoring system or adaptive learning platform. Use when designing intelligent tutoring software or skill-based mastery systems.

GarethManning/education-agent-skills · 40 tokens