Loading...
Loading...
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.
npx skill4agent add googlecloudplatform/cxas-scrapi cxas-agent-foundry# Lint before push (catches structural issues early)
cxas lint --app-dir <project>/cxas_app/<AppName>
# Push local files to platform
cxas push --app-dir <project>/cxas_app/<AppName> \
--to projects/<project_id>/locations/<location>/apps/<app_id> \
--project-id <project_id> --location <location>
# Pull platform state to local
cxas pull projects/<project_id>/locations/<location>/apps/<app_id> \
--project-id <project_id> --location <location> --target-dir <project>/cxas_app/
# Run evals + triage + report (single command)
python .agents/skills/cxas-agent-foundry/scripts/run-and-report.py --message "what changed" --runs 5
# Inspect app architecture
python .agents/skills/cxas-agent-foundry/scripts/inspect-app.py
# Triage failures
python .agents/skills/cxas-agent-foundry/scripts/triage-results.py --last 3.venv/.active-project<project>/gecx-config.json<project>/cxas_app/| Signal | Action |
|---|---|
No | First-time setup needed. Load |
| Returning user, new project. Route normally. |
| All exist | Returning user. Route normally. |
| User says... | Phase | Load |
|---|---|---|
| "Build me an agent from this PRD" | Build | |
| "Create evals for my agent" | Build | |
| "Generate tool tests", "create callback tests" | Build | |
| "Update evals -- requirements changed" | Build | |
| "Update the TDD" | Build | |
| "Run evals", "push evals", "check results" | Run | |
| "Run tool tests", "test the callbacks" | Run | |
| "Generate a report" | Run | |
| "Why is this eval failing", "get to 90%" | Debug | |
| "Fix the failing evals", "debug the agent" | Debug | |
| "Tool test is failing", "callback test broke" | Debug | |
todo.md[ ][x]