Central orchestrator for the knowledge pipeline. Discovers available knowledge skills at runtime, classifies requests, routes to constructors/extractors/ontology skills, and drives the full 格物致知 workflow. Triggers on requests like "build a user manual", "extract knowledge", "run knowledge pipeline", "discover ontology graphs".
Observe and record user behavior on websites via Chrome DevTools MCP. Injects tracker IIFE, captures DOM events with PII masking, and produces structured observation summaries. Triggers on operations like "start_tracking", "stop_tracking", "get_observations".
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Extract knowledge from applications (source code repos, docs, URLs, running apps, files) and package into KB intake format. Use when extracting documentation, user manuals, or knowledge from application sources. Triggers on requests like "extract knowledge", "knowledge extraction", "extract user manual", "analyze application".
Represent human intent at end-user-facing touchpoints as an autonomous human representative (工程師 persona). Answers, clarifies, critiques, instructs, approves, or passes through to downstream agents. Triggers on requests like "represent human intent", "human representative guidance", "human representative", "approval-like guidance".
Searches and retrieves existing knowledge from persistent memory and ontology. Provides overview scanning (extract_overview) and detailed content retrieval (extract_details). Read-only operations. Triggers on operations like "extract_overview", "extract_details".
Cross-graph integration engine that discovers related ontology graphs, normalizes vocabulary into canonical terms, and links nodes across domains. Delegates JSONL I/O to scripts/synthesis_ops.py. Triggers on operations like "discover_related", "wash_terms", "link_nodes".
Graph connector that pushes ontology data to the X-IPE knowledge graph server via HTTP callback, with automatic port resolution and auth token discovery. Triggers on operations like "connector", "push to graph".