From project-toolkit
Traverses knowledge graph across memories, entities, and relationships for comprehensive context. Use before planning complex work, investigating concept connections, or answering 'what do you know about X'.
npx claudepluginhub rjmurillo/ai-agents --plugin project-toolkitThis skill uses the workspace's default tool permissions.
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.
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
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 exploration