aria_skills/knowledge_graph/SKILL.md
Build and query Aria's knowledge graph. Store entities and relationships.
npx skillsauth add najia-afk/aria_moltbot aria-knowledgegraphInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Build and query Aria's knowledge graph. Store entities (people, places, concepts) and their relationships.
exec python3 /app/skills/run_skill.py knowledge_graph <function> '<json_args>'
Create or update an entity in the knowledge graph.
exec python3 /app/skills/run_skill.py knowledge_graph add_entity '{"name": "Najia", "type": "person", "properties": {"role": "creator", "relationship": "guardian"}}'
Parameters:
name (required): Entity nametype (required): Entity type (person, place, concept, event, etc.)properties: Optional JSON object with additional attributesCreate a relationship between two entities.
exec python3 /app/skills/run_skill.py knowledge_graph add_relation '{"from_entity": "Najia", "to_entity": "Aria", "relation_type": "created", "properties": {"date": "2024"}}'
Relation types:
created, owns, usesknows, works_with, friends_withlocated_in, part_of, belongs_torelated_to, interested_in, learned_aboutFind entities related to a given entity.
exec python3 /app/skills/run_skill.py knowledge_graph query_related '{"entity_name": "Najia", "depth": 2}'
Search entities by name, type, or properties.
exec python3 /app/skills/run_skill.py knowledge_graph search '{"query": "python"}'
knowledge_entities: | Column | Type | Description | |--------|------|-------------| | id | UUID | Primary key | | name | TEXT | Entity name | | type | TEXT | Entity type | | properties | JSONB | Additional data | | created_at | TIMESTAMP | Creation time | | updated_at | TIMESTAMP | Last update |
knowledge_relations: | Column | Type | Description | |--------|------|-------------| | id | UUID | Primary key | | from_entity | UUID | Source entity | | to_entity | UUID | Target entity | | relation_type | TEXT | Relationship type | | properties | JSONB | Relation metadata |
# Add people
exec python3 /app/skills/run_skill.py knowledge_graph add_entity '{"name": "Najia", "type": "person"}'
exec python3 /app/skills/run_skill.py knowledge_graph add_entity '{"name": "Aria", "type": "ai_agent"}'
# Add relationship
exec python3 /app/skills/run_skill.py knowledge_graph add_relation '{"from_entity": "Najia", "to_entity": "Aria", "relation_type": "created"}'
# Query
exec python3 /app/skills/run_skill.py knowledge_graph query_related '{"entity_name": "Najia"}'
This skill wraps /app/skills/aria_skills/knowledge_graph.py
tools
# aria-working-memory Persistent short-term memory operations for Aria runtime context. ## Purpose - Store, retrieve, rank, checkpoint, and prune working memory. - Provide high-relevance context for decision and response flows. ## Main Tools - `remember` - `recall` - `get_context` - `checkpoint` - `restore_checkpoint` - `forget` - `update` - `reflect` - `sync_to_files`
development
```skill --- name: aria-unified-search description: "🔎 RRF-merged search across semantic + graph + memory backends" metadata: {"aria": {"emoji": "🔎"}} --- # aria-unified-search Unified search engine that queries semantic memories (pgvector cosine), knowledge graph (ILIKE), and traditional memories (text match), then merges results via Reciprocal Rank Fusion (RRF) with content-hash deduplication. ## Architecture ``` Query ↓ (parallel to 3 backends) ├── SemanticBackend (pgvector cosi
tools
# aria-telegram Telegram Bot API integration skill. ## Purpose - Send and reply to messages through bot credentials. - Fetch updates and basic bot metadata. ## Main Tools - `send_message` - `reply_to_message` - `get_updates` - `get_me`
tools
# aria-sprint-manager Sprint planning and board flow management skill. ## Purpose - Operate goal board as Product Owner. - Move, prioritize, and report sprint progress. ## Main Tools - `sprint_status` - `sprint_plan` - `sprint_move_goal` - `sprint_report` - `sprint_prioritize`