skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
googlecloudplatform/cxas-scrapi71 installs

cxas-sim-eval

Converts CXAS golden evaluations to SCRAPI SimulationEvals test cases. Use when generating high-level, goal-oriented test cases from turn-by-turn evaluation JSONs, and when enriching test expectations with inferred tool calls.

How do I install this agent skill?

npx skills add https://github.com/googlecloudplatform/cxas-scrapi --skill cxas-sim-eval
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill provides tools to convert and evaluate Google Cloud CXAS agents. It is susceptible to indirect prompt injection because it processes external evaluation data and conversation logs through large language models without sanitization or boundary markers.

  • Socketwarn

    1 alert: gptAnomaly

  • Snykpass

    Risk: LOW · No issues

What does this agent skill do?

CXAS Evaluation to Simulation Converter

This skill helps convert turn-by-turn CXAS golden evaluations into high-level, goal-oriented test cases for the SCRAPI SimulationEvals framework. It analyzes the agent's tools to enrich expectations with specific tool calls.


Steps

1. Check Environment

Ensure cxas_scrapi is installed as a python package. You can check this by running:

python -c "import cxas_scrapi"

Ensure gcloud is authenticated properly:

gcloud auth list

If needed, login with:

gcloud auth login

2. Get App Name and Output Directory

[!IMPORTANT] You MUST ask the user for the full resource name of the app/agent (e.g., projects/.../locations/.../apps/...) and the base output directory before proceeding with any execution steps.

Ask the user for these values.

3. Fetch Evaluations

Fetch the list of evaluations using the CES API. Save each evaluation as a JSON file named after its display name under [output_dir]/golden_evals/.

4. Fetch Tool Schemas

Fetch the full schemas for all tools available in the app and save them under [output_dir]/tools/.

5. Fetch Agent Tools Configuration

Fetch the list of tools and toolsets used by the agent and save the configuration (e.g., to [output_dir]/agent_tools.json).

6. Convert Evaluations

Run the conversion script (convert_eval.py) to process the fetched evaluations and save the converted test cases under [output_dir]/sim_evals/.

Automation Scripts

Three scripts are available to automate the process:

1. Fetch Evaluations and Agent Config

scripts/fetch_app_data.py

Fetches evaluations and the list of tools used by the agent from the CES API.

Usage:

python .agents/skills/cxas-sim-eval/scripts/fetch_app_data.py \
  --app-name "projects/.../locations/.../apps/..." \
  --output-dir /path/to/output_directory

2. Fetch Tool Schemas

scripts/fetch_tool_schemas.py

Fetches the full schemas for all tools available in the app.

Usage:

python .agents/skills/cxas-sim-eval/scripts/fetch_tool_schemas.py \
  --app-name "projects/.../locations/.../apps/..." \
  --output-dir /path/to/output_directory

3. Convert Evaluations

scripts/convert_eval.py

Converts the fetched evaluations to simulation test cases, using the fetched tool schemas to infer expectations.

Usage:

python .agents/skills/cxas-sim-eval/scripts/convert_eval.py \
  --output-dir /path/to/output_directory \
  --parallelism 5

4. Run Evaluations (Local or Platform Milestone Evals)

scripts/run_evals.py

Runs the simulation evaluations, logs raw results, and generates a combined HTML report.

Cognitive Diagnostics Analysis: If the agent has the intercept_and_score_reasoning tool enabled, this script will automatically extract and analyze the agent's internal monologue for failed evaluations. It detects issues like overthinking, hesitation, and backtracking. Furthermore, it correlates these diagnostics with the agent's instructions to generate actionable suggestions for improvement directly in the HTML report.

Usage (local execution):

python .agents/skills/cxas-sim-eval/scripts/run_evals.py \
  --app-name "projects/.../locations/.../apps/..." \
  --output-dir /path/to/output_directory \
  --parallelism 5 \
  --start-index 0 \
  --end-index 10

Usage (CXAS 2.0 Platform Milestone execution via CLI or SDK):

# Push converted sim_evals directly to the CES platform as Milestone evaluations
uv run cxas push-eval \
  --app-name "projects/.../locations/.../apps/..." \
  --file /path/to/output_directory/sim_evals/

# Run all scenario/milestone evaluations on the platform
uv run cxas run \
  --app-name "projects/.../locations/.../apps/..." \
  --eval-type scenarios \
  --run-count 3 \
  --wait

[!NOTE] Tool fakes (use_tool_fakes: true) are supported on platform Milestone evaluations via EvaluationConfig.tool_call_behaviour = FAKE. When executing via SimulationEvals.run_simulations(..., run_on_platform=True), text simulations with tool fakes run directly on the platform, while local-only features (audio_analysis, voice_config, audio_expectations, barge_in_after_ms, naturalness_metric) automatically route to local client simulation.

Interpreting Cognitive Diagnostics

When running evaluations with the intercept_and_score_reasoning tool enabled, the system extracts diagnostics to help you identify issues in agent reasoning.

Key Signals

  1. Overthinking (Verbosity)

    • Symptom: Internal monologue exceeds 350 or 600 characters.
    • Meaning: The agent is struggling to process complex or circular instructions.
    • Fix: Simplify instructions. Break down complex tasks into smaller, linear steps.
  2. Hedging

    • Symptom: Use of words like "might be", "guess", "unsure", "assume".
    • Meaning: The agent is uncertain about its next action, often due to missing edge case handling.
    • Fix: Add explicit instructions for the scenario the agent is unsure about.
  3. Backtracking

    • Symptom: Use of words like "wait", "actually", "on second thought".
    • Meaning: The agent is abandoning a plan mid-turn or correcting itself, indicating unclear triggers.
    • Fix: Clarify triggers and state transitions in instructions.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/googlecloudplatform/cxas-scrapi/cxas-sim-eval">View cxas-sim-eval on skillZs</a>