Fix plugin hooks JSON, align Skill docs with repo API, and make skill generation portable

plugins/.claude-plugin/README.md

@@ -16,7 +16,6 @@ This folder contains the plugin metadata for the Semantica Claude/Cursor/Codex p
 ```bash
 /plugin marketplace add <owner>/semantica
 ```
-```
 
 ## Supported platforms
 

plugins/hooks/hooks.json

@@ -1,7 +1,8 @@
 {
   "hooks": {
     "PostToolUse": [
-      {"matcher": "Write|Edit", "hooks": [{"type": "command", "command": "FILE=$(jq -r .tool_input.file_path 2>/dev/null); if echo $FILE | grep -qE semantica/; then python -c "import ast,sys; ast.parse(open(sys.argv[1]).read())" $FILE 2>&1; fi"}]},
+      {"matcher": "Write|Edit", "hooks": [{"type": "command", "command": "FILE=$(jq -r .tool_input.file_path 2>/dev/null); if echo $FILE | grep -qE semantica/; then python -c 'import ast,sys; ast.parse(open(sys.argv[1]).read())' $FILE 2>&1; fi"}]},
+
       {"matcher": "Write|Edit", "hooks": [{"type": "command", "command": "echo PostToolUse provenance check"}]}
     ],
     "PreToolUse": [

plugins/skills/deduplicate/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: deduplicate
-description: Identify and merge duplicate entities, relations, and graph objects in Semantica using fuzzy matching, schema heuristics, and graph similarity.
+description: Detect duplicate entities, duplicate groups, and relationship duplicates in Semantica using fuzzy matching, schema heuristics, and graph similarity.
 ---
 
 # /semantica:deduplicate
@@ -13,25 +13,29 @@ Remove duplicates from the knowledge graph. Usage: `/semantica:deduplicate <stra
 
 ## `entities [--threshold <score>] [--field <name>]`
 
-Find and merge duplicate entities.
+Detect duplicate entities and group them by similarity.
 
 ```python
 from semantica.deduplication import DuplicateDetector
 
 finder = DuplicateDetector()
-merged = finder.merge_duplicates(entity_type=entity_type, threshold=threshold)
+candidates = finder.detect_duplicates(entities, threshold=threshold)
+groups = finder.detect_duplicate_groups(entities, threshold=threshold)
 ```
 
-Output: merged entity IDs, discarded duplicates, and merge confidence.
+Output: duplicate candidate list, duplicate groups, and representative merge recommendations.
 
 ---
 
 ## `relations [--similarity <score>]`
 
-Detect duplicate relationships and normalize edges.
+Detect duplicate relationships and normalize edge representations.
 
 ```python
-relations = finder.find_duplicate_relations(similarity=similarity)
+from semantica.deduplication import DuplicateDetector
+
+finder = DuplicateDetector()
+relations = finder.detect_duplicates(relation_list, threshold=similarity)
 ```
 
-Result: relation clusters, normalized relation set, and cleanup summary.
+Result: duplicate relation candidates, normalized relationship groups, and cleanup summary.

plugins/skills/export/SKILL.md

@@ -16,22 +16,23 @@ Export knowledge graph data. Usage: `/semantica:export <format> [args]`
 Export graph data as JSON.
 
 ```python
-from semantica.export import GraphExporter
+from semantica.export.methods import export_json
 
-exporter = GraphExporter()
-exporter.export_json(output_path=output, filter_query=filter_query)
+export_json(data=graph_data, file_path=output, format='json')
 ```
 
 Output: JSON file or inline JSON payload.
 
 ---
 
-## `rdf [--format turtle|xml|ntriples] [--output <path>]`
+## `rdf [--format turtle|rdfxml|jsonld|ntriples|n3] [--output <path>]`
 
 Export the graph in RDF serialization.
 
 ```python
-exporter.export_rdf(format='turtle', output_path=output)
+from semantica.export.methods import export_rdf
+
+export_rdf(data=graph_data, file_path=output, format='turtle')
 ```
 
 Return: RDF text or file path.
@@ -43,7 +44,24 @@ Return: RDF text or file path.
 Export nodes and edges to Parquet for analytics.
 
 ```python
-exporter.export_parquet(output_path=output)
+from semantica.export.methods import export_parquet
+
+export_parquet(data=graph_data, file_path=output, compression='snappy')
 ```
 
 Output: Parquet dataset ready for downstream processing.
+
+---
+
+## `graphml|gexf|dot [--output <path>]`
+
+Export the graph to a supported graph format.
+
+```python
+from semantica.export import GraphExporter
+
+exporter = GraphExporter(format='graphml', include_attributes=True)
+exporter.export(graph_data, output)
+```
+
+Output: Graph format file suitable for visualization tools.

plugins/skills/ingest/SKILL.md

@@ -16,10 +16,9 @@ Ingest new data into the knowledge graph. Usage: `/semantica:ingest <source> [ar
 Ingest structured data from a local file.
 
 ```python
-from semantica.ingest import DataIngestor
+from semantica.ingest import ingest_file
 
-ingestor = DataIngestor()
-ingestor.ingest_file(file_path=path, file_format=file_format)
+data = ingest_file(file_path=path, method='file', file_format=file_format)
 ```
 
 Output: imported node/edge count and ingestion summary.
@@ -31,7 +30,9 @@ Output: imported node/edge count and ingestion summary.
 Ingest data from a database source.
 
 ```python
-ingestor.ingest_database(connection_string=conn, query=query)
+from semantica.ingest import ingest_database
+
+result = ingest_database(connection_string=conn, query=query)
 ```
 
 Return: rows ingested, mapped entities, and warnings.