mcpField
C
concept-graph

concept-graph

github.com/willoscarProductivity51744 installsUpdated 4w ago
Repository

About concept-graph

concept-graph turns a structured tutorial specification into a directed acyclic graph of concepts and prerequisite relationships. It is for tutorial workflows that need a stable, sortable concept outline before writing learner-facing prose.

Key features

  1. 01Creates a concept graph from a tutorial spec
  2. 02Represents prerequisite relationships
  3. 03Emits stable node IDs
  4. 04Checks that the graph is acyclic
  5. 05Writes YAML output

Use cases

  1. 01Order tutorial concepts by prerequisites
  2. 02Prepare a concept outline from a tutorial spec
  3. 03Validate a tutorial graph before module planning

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/willoscar/research-units-pipeline-skills --skill concept-graph

After installing, type/concept-graphin Claude Code to confirm it loaded.

Bundled filesscripts/run.py

Details

From the project README

Concept Graph

Triggers & routing

  • Trigger: concept graph, prerequisite graph, dependency graph, 概念图, 先修关系.
  • Use when: source-tutorial 的 C2，已有 output/TUTORIAL_SPEC.md，需要把教程概念转成可排序的 DAG。
  • Skip if: 还没有 tutorial spec。
  • Network: none.
  • Guardrail: 只做结构，不写 reader-facing prose；图必须保持无环。

Materializes the tutorial spec's structured concept inventory into outline/concept_graph.yml.

Input

  • output/TUTORIAL_SPEC.md

Output

  • outline/concept_graph.yml

Contract

The graph must contain:

  • nodes: {id, title, summary, source_ids, objective_refs}
  • edges: {from, to} meaning prerequisite order

Script boundary

scripts/run.py should:

  • load structured spec data
  • emit stable node ids and prerequisite edges
  • fail if the result would be cyclic or empty

Do not duplicate spec-parsing heuristics in multiple places; keep them in shared tutorial tooling.

Acceptance

  • outline/concept_graph.yml exists
  • all nodes have stable ids
  • the graph is a DAG

Non-goals

  • module clustering
  • exercise generation
  • tutorial prose

Comments

Markdown supported