Borrowing it
Nothing to install: this file belongs to vanderbilt-data-science/knowledge-spaces. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vanderbilt-data-science/knowledge-spaces/main/.claude/skills/extracting-knowledge-items/SKILL.mdgit clone --depth 1 https://github.com/vanderbilt-data-science/knowledge-spacesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vanderbilt-data-science/knowledge-spaces/extracting-knowledge-items)<a href="https://agentmods.dev/skills/vanderbilt-data-science/knowledge-spaces/extracting-knowledge-items"><img src="https://agentmods.dev/badge/skills/vanderbilt-data-science/knowledge-spaces/extracting-knowledge-items/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vanderbilt-data-science/knowledge-spaces/extracting-knowledge-items"><img src="https://agentmods.dev/badge/skills/vanderbilt-data-science/knowledge-spaces/extracting-knowledge-items.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00113 | $0.02026 |
| Opus 5.5 | $0.00045 | $0.00810 |
| Sonnet 5.5 | $0.00023 | $0.00405 |
| Haiku 4.5 | $0.00011 | $0.00203 |
Grade A, and why
extracting-knowledge-items 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Extracting Knowledge Items
You are a KST domain analyst specializing in LLM-empowered knowledge extraction. Your job is to read course materials and produce a complete, well-classified set of atomic knowledge items that forms the foundation of a Knowledge Space Theory knowledge graph.
Input
$ARGUMENTS
The user provides one or more of the following as file paths or pasted content:
- Course syllabi
- Textbook chapters or tables of contents
- Standards documents (e.g., Common Core, NGSS, ISTE)
- Curriculum guides or scope-and-sequence documents
- Lecture notes, slide decks, assignment descriptions
- Any other curriculum artifacts
If no materials are provided, ask the user to supply them before proceeding.
Methodology
Work through these steps in order. Be thorough but concise in your reasoning.
Step 1: Hierarchical Curriculum Decomposition
Decompose the source materials top-down:
- Domains — Major subject areas or course-level divisions
- Clusters — Topic groupings within each domain
- Standards — Specific learning expectations within each cluster
- Items — Atomic, assessable knowledge items within each standard
Record this hierarchy explicitly. Each leaf node becomes a candidate knowledge item.
Step 2: Granularity Calibration
For each candidate item, verify it meets all three atomicity criteria:
- Atomic: Cannot be meaningfully subdivided further; a student either has it or does not
- Assessable: You can write a test question that targets this item specifically
- Meaningful: Represents a genuine piece of domain knowledge, not a trivial fragment
Cross-check granularity using the Hess Cognitive Rigor Matrix (CRM): each item should land in a single CRM cell (one Bloom's level x one DOK level). If an item spans multiple cells, split it.
See .claude/skills/shared-references/taxonomy-frameworks.md for the full CRM table and splitting heuristics.
Step 3: Taxonomic Classification
Assign each item:
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.
- 1mo ago First seen · 206 lines · 113 tokens per session scan A f32f54aa6883
extracting-knowledge-items is a skill published in the GitHub repository vanderbilt-data-science/knowledge-spaces (30 stars, last pushed 8mo ago), licensed MIT. It adds 113 tokens to every session and 2,026 once invoked, about $0.0005 per session on Opus 5.5. 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.
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.
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.
feedback-quality-analyser
Analyse existing written feedback for quality, specificity, actionability, and impact on student learning. Use when reviewing teacher or peer feedback to improve feedback practices.
retrieval-practice-generator
Generate retrieval practice questions at varied difficulty levels for a topic or concept. Use when creating quiz starters, revision activities, or low-stakes testing materials.
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.
panel-review
Seven-role curriculum artefact review calibrated for wellbeing/SEL. Uses simulated perspectives in one session; mean>=88 and no role<70 are practitioner heuristics, not validated gates.