$npx -y skills add WILLOSCAR/research-units-pipeline-skills --skill concept-graphUse when an approved tutorial spec exists and the run needs a deterministic prerequisite graph before module planning. 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。
| 1 | # Concept Graph |
| 2 | |
| 3 | Materializes the tutorial spec's structured concept inventory into `outline/concept_graph.yml`. |
| 4 | |
| 5 | ## Input |
| 6 | |
| 7 | - `output/TUTORIAL_SPEC.md` |
| 8 | |
| 9 | ## Output |
| 10 | |
| 11 | - `outline/concept_graph.yml` |
| 12 | |
| 13 | ## Contract |
| 14 | |
| 15 | The graph must contain: |
| 16 | - `nodes`: `{id, title, summary, source_ids, objective_refs}` |
| 17 | - `edges`: `{from, to}` meaning prerequisite order |
| 18 | |
| 19 | ## Script boundary |
| 20 | |
| 21 | `scripts/run.py` should: |
| 22 | - load structured spec data |
| 23 | - emit stable node ids and prerequisite edges |
| 24 | - fail if the result would be cyclic or empty |
| 25 | |
| 26 | Do not duplicate spec-parsing heuristics in multiple places; keep them in shared tutorial tooling. |
| 27 | |
| 28 | ## Acceptance |
| 29 | |
| 30 | - `outline/concept_graph.yml` exists |
| 31 | - all nodes have stable ids |
| 32 | - the graph is a DAG |
| 33 | |
| 34 | ## Non-goals |
| 35 | |
| 36 | - module clustering |
| 37 | - exercise generation |
| 38 | - tutorial prose |