Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.
Explores interconnected memories and entities to reveal comprehensive context across projects and relationships.
/plugin marketplace add rjmurillo/ai-agents/plugin install project-toolkit@ai-agentsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Forgetful stores knowledge as an interconnected graph: memories link to other memories, entities link to memories, and entities relate to each other. Deep exploration reveals context that simple queries miss.
| Trigger Phrase | Operation |
|---|---|
what do you know about X | Full knowledge graph traversal |
how do I explore the knowledge graph | Graph exploration workflow |
how are these concepts connected | Entity relationship traversal |
give me comprehensive context on X | Deep multi-phase exploration |
map out related knowledge for X | Entity discovery and memory linking |
Explore the knowledge graph when:
Track visited IDs to prevent cycles. Execute phases sequentially.
execute_forgetful_tool("query_memory", {
"query": "<topic>",
"query_context": "Exploring knowledge graph for comprehensive context",
"k": 5,
"include_links": true,
"max_links_per_primary": 5
})
Collect: primary_memories + linked_memories (1-hop connections).
For key memories, get full details:
execute_forgetful_tool("get_memory", {"memory_id": <id>})
Extract: document_ids, code_artifact_ids, project_ids, additional linked_memory_ids.
Find entities in discovered projects:
execute_forgetful_tool("list_entities", {
"project_ids": [<discovered project ids>]
})
For relevant entities, map relationship graph:
execute_forgetful_tool("get_entity_relationships", {
"entity_id": <id>,
"direction": "both"
})
Relationship types: works_for, owns, manages, collaborates_with, etc.
For each entity, find all linked memories:
execute_forgetful_tool("get_entity_memories", {
"entity_id": <id>
})
Returns {"memory_ids": [...], "count": N}. Fetch any new memories not already visited.
Group findings by type:
Memories: Primary (direct matches) → Linked (1-hop) → Entity-linked (via entities)
Entities: Name, type, relationship count, linked memory count
Artifacts: Documents and code snippets found via memory links
Graph Summary: Total nodes, key themes, suggested follow-up queries
Match depth to task complexity. Start shallow, go deeper if context insufficient.
Use this skill when:
Use using-forgetful-memory instead when:
Use curating-memories instead when:
| Avoid | Why | Instead |
|---|---|---|
| Running all 5 phases for simple queries | Wastes tokens on unnecessary traversal | Start shallow (phases 1-2), go deeper only if needed |
| Not tracking visited IDs | Causes infinite cycles in graph traversal | Maintain a visited set, skip already-seen nodes |
| Expanding every linked memory | Exponential blowup on dense graphs | Focus on high-importance memories (7+) |
| Skipping entity phases when entities exist | Misses cross-project connections | Check for entities in Phase 3 before skipping |
| Presenting raw results without grouping | Overwhelming and unstructured | Group by type: memories, entities, artifacts |
After graph exploration:
truncated flag from query_memory (8000 token budget)project_ids filter to scope explorationActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.