Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add joao-aires/agent-skills-public --skill ai-deepeval-testinggit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/joao-aires/agent-skills-public/ai-deepeval-testing)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/ai-deepeval-testing"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/ai-deepeval-testing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/ai-deepeval-testing"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/ai-deepeval-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.01180 |
| Opus 5.5 | $0.00024 | $0.00472 |
| Sonnet 5.5 | $0.00012 | $0.00236 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
ai-deepeval-testing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Python AI evaluations with DeepEval
Use the accepted task, architecture and quality criteria. Seek available expertise in conceptual AI evaluation for case design and evidence boundaries; retain deterministic correctness, authority and meaningful quality evidence when that specialist is absent. This skill implements an evaluation approach in Python, not the product's acceptance policy or all application testing. The evaluation runner can be Python while the application uses another language; do not migrate the application to run a suite.
Choose a compatible, bounded integration
Inspect the project's Python/dependency constraints, existing tests, datasets, metrics, model/judge settings and CI. Use a locked compatible DeepEval version in the established test/development dependency group. Preserve an accepted alternative unless comparing or migrating is requested. Consult the DeepEval evaluation guide for the selected release's API; documented examples do not establish installed compatibility.
Map the accepted evaluation levels to supported DeepEval APIs. Use output cases for bounded inference, component/trajectory APIs where internal execution matters and conversation cases for supported multi-turn evaluation. Instrument only the relevant path with the existing tracing owner. A protocol-only service may need compatibility checks without DeepEval.
Map actual artifacts to test cases
Keep input scenarios/goldens, expected outcomes/rubrics and test results distinct.
| Evidence or input | Compatible DeepEval representation |
|---|---|
| Single-turn input/output | LLMTestCase |
| Supported multi-turn evaluation | ConversationalTestCase |
| Rerunnable input collection | EvaluationDataset and Golden where appropriate |
Choose the interaction being evaluated, then collect its actual inputs and results. At application level, this may be the user's request and final response; at a component level, it is the input and output of that component. Keep the case at a consistent scope so the metric is judging the behavior intended by the test.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +19 lines f6299ed14e94
- 2d ago First seen · 47 lines · 59 tokens per session scan A f16ce4e15649
ai-deepeval-testing is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 1,180 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.
Other skills, from other repositories
cli-eval
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…
darwinian-evolver
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
validate
Validate Semantica pipelines, extraction quality, graph schemas, and ontology consistency. Returns structured error/warning checklists. Uses PipelineValidator, PipelineBuilder.validatepipeline(), GraphValidator, and OntologyValidator. Sub-commands: pipeline, step, dependencies, extraction, graph, ontology, performance.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.