mastermind-logger
Mastermind Logger Skill (LLM-Wiki Pattern)
This skill acts as an intelligent knowledge base maintainer, inspired by the "LLM-Wiki" pattern. It does NOT just leave "dump" files. When invoked, it compiles crucial technical discoveries, architectural decisions, and constraints from the active session and integrates them into a structured, interconnected wiki.
The core philosophy: Knowledge should be compounding, constantly updated, and heavily cross-referenced, not just appended as isolated time-stamped files.
🛠 Operation Protocol
Whenever the user triggers mastermind-logger, you MUST perform the following steps autonomously in the [workspace-root]/docs/knowledgelib/ directory:
1. Ingest & Analyze (Context Extraction)
Scan the recent conversation history and current file context. Determine what new information was produced:
- Technical rulings, constraints, or environment variables.
- Architectural design choices.
- Fixed bugs and their root causes.
- New concepts or API integrations explored.
2. Update/Create Entity Files (The Wiki Nodes)
Do NOT write all findings into a single date-stamped file. Instead, target specific "Entity/Topic" files.
More from fatih-developer/fth-skills
task-decomposer
Break down large, complex, or ambiguous tasks into independent subtasks with dependency maps, execution order, and success criteria. Plan first, then execute step by step. Triggers on 'how should I do this', 'where do I start', 'plan the project', 'break it down', 'implement' or whenever a task involves multiple phases.
24multi-brain-debate
Two-round debate protocol where perspectives challenge each other before consensus. Round 1 presents independent positions, Round 2 allows counter-arguments and rebuttals. Produces battle-tested decisions for high-stakes choices.
20context-compressor
Compress long conversation histories, large code files, research results, and documents by 70% without losing critical information. Triggers when context window fills up, when summarizing previous steps in multi-step tasks, before loading large files into context, or on 'summarize', 'compress', 'reduce context', 'save tokens'.
18multi-brain-score
Confidence scoring overlay for multi-brain decisions. Each perspective rates its own confidence (1-10) with justification. Consensus uses scores as weights, flags low-confidence areas, and surfaces uncertainty explicitly.
16checkpoint-guardian
Automatic risk assessment before every critical action in agentic workflows. Detects irreversible operations (file deletion, database writes, deployments, payments), classifies risk level, and requires confirmation before proceeding. Triggers on destructive keywords like deploy, delete, send, publish, update database, process payment.
14multi-brain
Evaluate complex requests from 3 independent perspectives (Creative, Pragmatic, Comprehensive), reach consensus, then produce complete outputs. Use for architecture decisions, creative content, analysis, and any task where multiple valid approaches exist.
14