// Extracts conversational transcripts from .drawio XML files.
End-to-end GECX/CXAS/CES conversational agent lifecycle -- build agents from requirements (PRD-to-agent), create and run evals (goldens, simulations, tool tests, callback tests), debug failures, and iterate to production quality. Use this skill whenever the user mentions GECX, CXAS, CES, SCRAPI, conversational agents, voice agents, audio agents, agent evals, pushing/pulling/linting agents, or agent instructions/callbacks/tools on the Google Customer Engagement Suite platform.
Migrate Dialogflow CX (DFCX) agents to CXAS (Customer Experience Agent Studio) agents. Use this skill when the user mentions DFCX migration, migrating agents, converting DFCX to CXAS, porting agents, agent migration, or post-migration optimization/consolidation. Four independently runnable scripts: migrate.py (1:1), stage_1.py (variable dedup + consolidation), stage_2.py (instruction state machines + tool mocks + lint + report), stage_3.py (rewires consolidated topology from source dep graph; only needed when stage_1 ran consolidation). State persists between scripts via <target>_ir.json so each can run / re-run / resume independently.
Retrieves non-contained CCAI Insights conversations (losses), uses agent intelligence to cluster them into common failure patterns, and generates a markdown report. Use when you need to analyze failure patterns and build targeted regression/evaluation reports.
Automates the ingestion of customer requirement documents such as diagrams, BRDs, code etc., synthesizes high-fidelity natural transcripts, and compiles them into highly interactive, responsive Critical User Journey (CUJ) reports.
A robust methodology for LLM-based requirements gathering and high-fidelity artifact generation. Employs 'Divide, Conquer, and Verify' tactics using specialized subagents, iterative exhaustion loops, and batched execution to ensure zero data loss.
A two-phase protocol for extracting structure and generating transcripts from customer artifacts.
| name | cxas-drawio-ingestor |
| description | Extracts conversational transcripts from .drawio XML files. |
Use this skill when you need to extract dialogue turns and conversation flows
from .drawio diagram files.
.drawio files are typically stored as XML. Dialogue turns are often embedded
within the file in encoded or plain text format inside specific XML elements.
.drawio file as a text file.<mxCell> elements or similar tags that contain
value attributes.value attributes. Look
for patterns like "Agent: ..." and "User: ..." or "Provider: ...".<b>, <font>, <br>) that
are often used for formatting inside .drawio labels. Note that XML
attribute values are often HTML-escaped (e.g., <b>). You should
first unescape HTML entities before stripping tags to ensure clean text
extraction.transcript_schema.yml contract.A mxCell might look like this: xml <mxCell id="1" value="<b>Agent:</b> "Hello!"<br><b>User:</b> "Hi!"" ...>
You should extract: - Agent: Hello! - User: Hi!