powernode
Skill4 starsChanged 18 days agoMITView on GitHub
Interact with the Powernode knowledge ecosystem and skill management via MCP tools. Based on the user's request, determine the domain and use the appropriate MCP tool:
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 39
Always search before creating to avoid duplicates (services auto-dedup at >=0.92 similarity but checking first is faster)
- Distinctive: line 41
Use categories consistently: pattern, anti_pattern, best_practice, discovery, fact, failure_mode
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Powernode Platform Operations
Interact with the Powernode knowledge ecosystem and skill management via MCP tools.
Routing
Based on the user's request, determine the domain and use the appropriate MCP tool:
Knowledge Graph
- Search:
platform.search_knowledge_graph(query, mode=hybrid/vector/keyword/graph) - Reason:
platform.reason_knowledge_graph(query, max_hops) - Explore:
platform.get_graph_node,platform.list_graph_nodes,platform.get_graph_neighbors - Extract:
platform.extract_to_knowledge_graph(text — runs LLM extraction pipeline to create nodes/edges) - Stats:
platform.graph_statistics
Shared Knowledge
- Search:
platform.search_knowledge(query) - Create:
platform.create_knowledge(title, content, content_type, tags) - Update:
platform.update_knowledge(entry_id, content, tags) - Promote:
platform.promote_knowledge(entry_id)
Compound Learnings
- Query:
platform.query_learnings(query, category, scope) - Create:
platform.create_learning(title, content, category) - Reinforce:
platform.reinforce_learning(learning_id) - Metrics:
platform.learning_metrics
Skills
- List/Search:
platform.list_skills(search, category, status) - Get:
platform.get_skill(skill_id) - Discover:
platform.discover_skills(task_context) - Create:
platform.create_skill(name, description, category, system_prompt, commands, tags) - Update:
platform.update_skill(skill_id, + fields to change) - Toggle:
platform.toggle_skill(skill_id, enabled) - Delete:
platform.delete_skill(skill_id) — cannot delete system skills - Health:
platform.skill_health,platform.skill_metrics
Guidelines
- Always search before creating to avoid duplicates (services auto-dedup at >=0.92 similarity but checking first is faster)
- Confirm destructive operations (delete, disable) with the user before executing
- Use categories consistently: pattern, anti_pattern, best_practice, discovery, fact, failure_mode
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.