CtrlK
BlogDocsLog inGet started
Tessl Logo

load-testing

Load test a Databricks App to find its maximum QPS. Use when: (1) User says 'load test', 'benchmark', 'QPS', 'throughput', or 'performance test', (2) User wants to find how many queries per second their app can handle, (3) User wants to set up load testing scripts for their agent, (4) User wants to view load test results/dashboard, (5) User wants to validate results or observe latency/error rate with MLflow tracing.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

The canonical home for this skill is load-testing in databricks/app-templates

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, well-sequenced load-testing skill with strong actionability and workflow checkpoints, held back primarily by progressive disclosure: the body repeatedly points to examples/*.py files that are not present in the bundle. Minor conciseness trims would tighten it further.

Suggestions

Ship the referenced example files (examples/locustfile.py, examples/validate_with_mlflow.py, examples/mock_openai_client.py) so the in-body markdown links resolve, or remove the references and inline the minimal needed code.

Tighten the Step 6 'two planes' framing and the mocking bullet rationale to cut conceptual padding without losing the actionable signal.

Make the validation gating more explicit (e.g. bold 'Validate' and 'Only proceed when valid' steps) to lift the load-test workflow from a 4 to a 5.

DimensionReasoningScore

Conciseness

Mostly information-dense (directory trees, flag tables, executable code, troubleshooting tables) with only minor over-explanation that could be trimmed, e.g. the parenthetical rationale in the mocking bullet list and the 'two planes' conceptual framing in Step 6.

4 / 5

Actionability

Provides concrete executable guidance — a full pyproject.toml, bash deploy/run commands, a bundle YAML block, a copy-paste MLflow search_traces snippet, and example CLI invocations — with the minor gap that the core locustfile.py/run_load_test.py are given as prose specs rather than full inline code (delegated to examples/).

4 / 5

Workflow Clarity

Clear numbered step sequence (Before You Start through Step 6) with most validation checkpoints present — 'Verify apps are ACTIVE before proceeding', healthcheck+warmup before each test, MLflow cross-check ('if they diverge, trust the server for reliability') — plus a troubleshooting feedback table, though the gating is less formally explicit than the anchor-5 'Only when valid' pattern.

4 / 5

Progressive Disclosure

The SKILL.md itself is well-structured with clear headers and signaled markdown references to examples/locustfile.py, examples/validate_with_mlflow.py, and examples/mock_openai_client.py, but those referenced bundle files do not exist in the skill directory, so the one-level-deep references are dangling and navigation breaks.

3 / 5

Total

15

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a strong example: third-person voice, concrete capabilities, comprehensive natural trigger terms, and an explicit five-clause 'Use when' clause covering both what and when. It matches the rubric's good_overall_examples closely.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Load test a Databricks App to find its maximum QPS', 'set up load testing scripts', 'view load test results/dashboard', 'validate results or observe latency/error rate with MLflow tracing' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (load test a Databricks App to find max QPS) and 'when' via a five-clause 'Use when' trigger list with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms users would actually say — 'load test', 'benchmark', 'QPS', 'throughput', 'performance test' — plus product-specific terms (Databricks App, MLflow) covering synonyms and the relevant domain vocabulary.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Databricks App load testing / QPS discovery) with distinct triggers and product-specific scope, giving minimal conflict risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
databricks/app-templates
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.