Testing & Quality skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

appium

Use for dynamic inspection and navigation of the Blokada app through the repo-local Appium machine session. Trigger when Codex needs to explore the live native UI on a real device, inspect labels or structure, tap through screens, capture screenshots or XML on demand, or verify interactive behavior without writing a static WDIO spec. The current workflow is implemented for iOS, but the skill name stays generic so it can later cover other Appium-backed platforms too.

3.25k repo starsObserved in 1 repos

Testing & Quality

device-log

Use for pulling recent Blokada app logs from a connected device, using the same share-log file exposed in Settings. Trigger when Codex needs the most recent app log lines for debugging, wants logs from the last hour or today, or needs a manual operator workflow for recent device logs without going through Appium UI automation.

3.25k repo starsObserved in 1 repos

Testing & Quality

compare-results

Establish baseline-vs-candidate evaluation plans, delegate missing evaluations, compare validated results, and decide quantization feasibility. Use when the user asks to compare baseline vs quantized runs, explain an accuracy drop/regression, verify whether a quantized checkpoint is acceptable, or compare NEL/MLflow evaluation outputs. Do NOT use for generic single-model evaluation without comparison intent (use evaluation), live NEL status/debugging (use launching-evals), or generic MLflow browsing without a comparison goal (use accessing-mlflow).

3.24k repo starsObserved in 1 repos

Testing & Quality

eagle3-review-logs

Review EAGLE3 pipeline experiment logs from the launcher's experiments/ directory. Summarizes pass/fail status for all 4 tasks, diagnoses failures with root causes and fixes, and flags warnings. Use when the user asks to review job logs, check experiment results, or diagnose why a specific task failed.

3.24k repo starsObserved in 1 repos

Testing & Quality

eagle3-triage

Triage a failed EAGLE3 pipeline run. Identifies which step failed (data synthesis, hidden state dump, training, or benchmark), diagnoses root cause from logs, and suggests fixes. Use when user reports an EAGLE3 pipeline failure or asks why a specific step failed. Also helps debug new model support issues.

3.24k repo starsObserved in 1 repos

Testing & Quality

eagle3-validate

Validate that an EAGLE3 pipeline run completed successfully end-to-end. Checks all 4 steps produced expected artifacts, verifies acceptance rate meets threshold (>= 2.1), and produces a summary report. Use when user wants to verify a pipeline run or check benchmark results.

3.24k repo starsObserved in 1 repos

Testing & Quality

evaluation

Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU", "evaluate quantized model", "run nel". Handles deployment, config generation, and evaluation execution. Not for quantizing models (use ptq), deploying/serving models (use deployment), or comparing completed baseline-vs-quantized results (use compare-results).

3.24k repo starsObserved in 1 repos

Testing & Quality

launching-evals

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals, analyzing or analysing runs or results, run directories or artifact paths on clusters, Slurm job issues, invocation IDs, or inspecting logs (client logs, server logs, SSH to cluster, tail logs, grep logs). Do NOT use for creating or modifying evaluation configs.

3.24k repo starsObserved in 1 repos

Testing & Quality

neural-link

Expert tactical knowledge on sequencing Neural Link MCP tools to inspect, debug, and manipulate live Neo.mjs applications. Triggers: Use this skill if the user asks you to interact with the browser, inspect the UI natively, patch live code, or use the Neural Link.

3.23k repo starsObserved in 1 repos

Testing & Quality

tech-debt-radar

Proactive architectural review skill using Frontier Model semantic RAG to sweep historical issues and Memory Core sessions for technical debt. Triggers: Use this skill when conducting architectural analysis, proactively searching for technical debt, auditing the repository for abandoned logical loops, when explicitly requested to scan for ambient architectural debt, or during PR review for fundamental architectural shifts.

3.23k repo starsObserved in 1 repos

Testing & Quality