Skip to content

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

docs(skills): update graph structure references

初晨a30c226bf4c5
diff --git a/understand-anything-plugin/skills/understand-chat/SKILL.md b/understand-anything-plugin/skills/understand-chat/SKILL.md
index b49749e3..b4910221 100644
--- a/understand-anything-plugin/skills/understand-chat/SKILL.md
+++ b/understand-anything-plugin/skills/understand-chat/SKILL.md
@@ -12,11 +12,13 @@ Answer questions about this codebase using the knowledge graph at `.understand-a
The knowledge graph JSON has this structure:
- `project` — {name, description, languages, frameworks, analyzedAt, gitCommitHash}
-- `nodes[]` — each has {id, type, name, filePath, summary, tags[], complexity, languageNotes?}
- - Node types: file, function, class, module, concept
- - IDs: `file:path`, `function:path:name`, `class:path:name`
+- `nodes[]` — each has {id, type, name, filePath?, summary, tags[], complexity, languageNotes?}
+ - Code node types: file, function, class, module, concept
+ - Non-code node types: config, document, service, table, endpoint, pipeline, schema, resource
+ - Domain/knowledge node types: domain, flow, step, article, entity, topic, claim, source
+ - IDs use the node type as prefix, e.g. `file:path`, `function:path:name`, `config:path`, `article:path`
- `edges[]` — each has {source, target, type, direction, weight}
- - Key types: imports, contains, calls, depends_on
+ - Key types: imports, contains, calls, depends_on, configures, documents, deploys, triggers, contains_flow, flow_step, related, cites
- `layers[]` — each has {id, name, description, nodeIds[]}
- `tour[]` — each has {order, title, description, nodeIds[]}
diff --git a/understand-anything-plugin/skills/understand-diff/SKILL.md b/understand-anything-plugin/skills/understand-diff/SKILL.md
index 482d35be..fd33264b 100644
--- a/understand-anything-plugin/skills/understand-diff/SKILL.md
+++ b/understand-anything-plugin/skills/understand-diff/SKILL.md
@@ -11,11 +11,13 @@ Analyze the current code changes against the knowledge graph at `.understand-any
The knowledge graph JSON has this structure:
- `project` — {name, description, languages, frameworks, analyzedAt, gitCommitHash}
-- `nodes[]` — each has {id, type, name, filePath, summary, tags[], complexity, languageNotes?}
- - Node types: file, function, class, module, concept
- - IDs: `file:path`, `function:path:name`, `class:path:name`
+- `nodes[]` — each has {id, type, name, filePath?, summary, tags[], complexity, languageNotes?}
+ - Code node types: file, function, class, module, concept
+ - Non-code node types: config, document, service, table, endpoint, pipeline, schema, resource
+ - Domain/knowledge node types: domain, flow, step, article, entity, topic, claim, source
+ - IDs use the node type as prefix, e.g. `file:path`, `function:path:name`, `config:path`, `article:path`
- `edges[]` — each has {source, target, type, direction, weight}
- - Key types: imports, contains, calls, depends_on
+ - Key types: imports, contains, calls, depends_on, configures, documents, deploys, triggers, contains_flow, flow_step, related, cites
- `layers[]` — each has {id, name, description, nodeIds[]}
- `tour[]` — each has {order, title, description, nodeIds[]}
@@ -39,7 +41,7 @@ The knowledge graph JSON has this structure:
4. **Find nodes for changed files** — for each changed file path, use Grep to search the knowledge graph for:
- Nodes with matching `"filePath"` values (e.g., `grep "changed/file/path"`)
- - This finds file nodes AND function/class nodes defined in those files
+ - This finds file-level nodes (including non-code types) AND function/class nodes defined in those files
- Note the `id` values of all matched nodes
5. **Find connected edges (1-hop)** — for each matched node ID, Grep for that ID in the edges to find:
diff --git a/understand-anything-plugin/skills/understand-explain/SKILL.md b/understand-anything-plugin/skills/understand-explain/SKILL.md
index 6a0c67f2..cbf4373e 100644
--- a/understand-anything-plugin/skills/understand-explain/SKILL.md
+++ b/understand-anything-plugin/skills/understand-explain/SKILL.md
@@ -12,11 +12,13 @@ Provide a thorough, in-depth explanation of a specific code component.
The knowledge graph JSON has this structure:
- `project` — {name, description, languages, frameworks, analyzedAt, gitCommitHash}
-- `nodes[]` — each has {id, type, name, filePath, summary, tags[], complexity, languageNotes?}
- - Node types: file, function, class, module, concept
- - IDs: `file:path`, `function:path:name`, `class:path:name`
+- `nodes[]` — each has {id, type, name, filePath?, summary, tags[], complexity, languageNotes?}
+ - Code node types: file, function, class, module, concept
+ - Non-code node types: config, document, service, table, endpoint, pipeline, schema, resource
+ - Domain/knowledge node types: domain, flow, step, article, entity, topic, claim, source
+ - IDs use the node type as prefix, e.g. `file:path`, `function:path:name`, `config:path`, `article:path`
- `edges[]` — each has {source, target, type, direction, weight}
- - Key types: imports, contains, calls, depends_on
+ - Key types: imports, contains, calls, depends_on, configures, documents, deploys, triggers, contains_flow, flow_step, related, cites
- `layers[]` — each has {id, name, description, nodeIds[]}
- `tour[]` — each has {order, title, description, nodeIds[]}
diff --git a/understand-anything-plugin/skills/understand-onboard/SKILL.md b/understand-anything-plugin/skills/understand-onboard/SKILL.md
index ca167a0a..f9ae700e 100644
--- a/understand-anything-plugin/skills/understand-onboard/SKILL.md
+++ b/understand-anything-plugin/skills/understand-onboard/SKILL.md
@@ -11,11 +11,13 @@ Generate a comprehensive onboarding guide from the project's knowledge graph.
The knowledge graph JSON has this structure:
- `project` — {name, description, languages, frameworks, analyzedAt, gitCommitHash}
-- `nodes[]` — each has {id, type, name, filePath, summary, tags[], complexity, languageNotes?}
- - Node types: file, function, class, module, concept
- - IDs: `file:path`, `function:path:name`, `class:path:name`
+- `nodes[]` — each has {id, type, name, filePath?, summary, tags[], complexity, languageNotes?}
+ - Code node types: file, function, class, module, concept
+ - Non-code node types: config, document, service, table, endpoint, pipeline, schema, resource
+ - Domain/knowledge node types: domain, flow, step, article, entity, topic, claim, source
+ - IDs use the node type as prefix, e.g. `file:path`, `function:path:name`, `config:path`, `article:path`
- `edges[]` — each has {source, target, type, direction, weight}
- - Key types: imports, contains, calls, depends_on
+ - Key types: imports, contains, calls, depends_on, configures, documents, deploys, triggers, contains_flow, flow_step, related, cites
- `layers[]` — each has {id, name, description, nodeIds[]}
- `tour[]` — each has {order, title, description, nodeIds[]}
@@ -36,7 +38,7 @@ The knowledge graph JSON has this structure:
4. **Read the tour** — Grep for `"tour"` to get the guided walkthrough steps. These provide the recommended learning path.
-5. **Read file-level nodes only** — use Grep to find nodes with `"type": "file"` in the knowledge graph. Skip function-level and class-level nodes to keep the guide high-level. Extract each file node's `name`, `filePath`, `summary`, and `complexity`.
+5. **Read file-level structural nodes only** — use Grep to find nodes with file-level types (`file`, `config`, `document`, `service`, `pipeline`, `table`, `schema`, `resource`, `endpoint`) in the knowledge graph. Skip function-level and class-level nodes to keep the guide high-level. Extract each node's `name`, `filePath`, `summary`, and `complexity`.
6. **Identify complexity hotspots** — from the file-level nodes, find those with the highest `complexity` values. These are areas new developers should approach carefully.