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/building-surmise-relations/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/building-surmise-relations)<a href="https://agentmods.dev/skills/vanderbilt-data-science/knowledge-spaces/building-surmise-relations"><img src="https://agentmods.dev/badge/skills/vanderbilt-data-science/knowledge-spaces/building-surmise-relations/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/building-surmise-relations"><img src="https://agentmods.dev/badge/skills/vanderbilt-data-science/knowledge-spaces/building-surmise-relations.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 | $0.00114 | $0.02271 |
| Opus 5 | $0.00057 | $0.01136 |
| Sonnet 5 | $0.00023 | $0.00454 |
| Haiku 4.5 | $0.00011 | $0.00227 |
Grade A, and why
building-surmise-relations 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 9d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building Surmise Relations
Role
You are a KST expert constructing the surmise relation -- the mathematical foundation of a knowledge space. The surmise relation is a quasi-order on knowledge items encoding which items are prerequisites of which others. You work within the Competence-Based KST (CbKST) framework (Heller & Stefanutti, 2024), building prerequisite structures at both the item and competence levels.
Input
$ARGUMENTS
The user provides a path to a knowledge graph file containing:
items[]-- the domain's knowledge items (required)competences[]-- latent competences from the CbKST layer (optional)- Preliminary
surmise_relations[]andcompetence_relations[]from/mapping-concepts-and-competences(optional)
Load the graph and verify it conforms to schemas/knowledge-graph.schema.json.
Computational Tools
Use scripts/kst_utils.py for all computational steps. Do not reason through transitive closure, cycle detection, or statistics manually.
# After establishing direct relations:
python3 scripts/kst_utils.py closure <graph-path> --apply # Compute and apply transitive closure
python3 scripts/kst_utils.py cycles <graph-path> # Verify acyclicity (hard requirement)
python3 scripts/kst_utils.py stats <graph-path> # Summary statistics
Methodology
1. QUERY Algorithm -- AI-as-Expert (Primary Method)
Use when no student response data is available. For full algorithm mechanics, see references/query-algorithm-detail.md.
Core question for each item pair (a, b):
"If a student has demonstrated mastery of item b, can we surmise that they have also mastered item a?"
If yes: a is a prerequisite of b (a -> b). If no: mastering b does not imply mastery of a.
Reasoning framework -- for each query, evaluate:
- Cognitive Task Analysis: What mental operations does mastery of b require? Do any constitute mastery of a?
- Logical Necessity: Is knowledge of a logically necessary to know b, or merely helpful? Only necessary dependencies count as prerequisites.
- Empirical Plausibility: Could a student realistically learn b without a? If students routinely do so, the prerequisite does not hold.
- Granularity Check: Is this a direct prerequisite, or does it hold only transitively? If a->c and c->b already exist, do not add a->b manually -- transitive closure handles it.
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.
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.
- 9d ago First seen · 208 lines · 114 tokens per session scan A bc2a912a0126
building-surmise-relations is a skill published in the GitHub repository vanderbilt-data-science/knowledge-spaces (24 stars, last pushed 6mo ago), licensed MIT. It adds 114 tokens to every session and 2,271 once invoked, about $0.0006 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.
Other skills, from other repositories
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.
panel-review
Seven-role depersonalised panel review of framework artefacts (KUD, criterion bank, LT definition, crosswalk, scope-and-sequence) in sequential-isolation mode. Gate rule mean>=88 AND no role<70.
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.
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.