Testing & Debugging Skills

Investigate why an ailang publish cascade didn't fire (or fired and silently failed) on multivac. Inspects gcloud logs across the registry validator, the Pub/Sub ailang-cascade topic, and the coordinator's task queue. Use when the user says "auto-cascade didn't work", "why didn't multivac pick this up", "check cloud logs for cascade", or "the dependents didn't get bumped".

Onboard a new on-device model to the Mac Studio eval rig end-to-end — hardware size/shape feasibility gate, OpenRouter quality pre-screen, ollama pull, opencode+pi cross-harness registration in models.yml, and continuous-rotation wiring. Use when the user wants to add/test/try a new local (Ollama) model on the rig, asks whether a model is the right size/shape for the hardware, or wants to evaluate a candidate before committing rig time.

Run AILANG agent-mode evaluations against local Ollama models on a dedicated Mac Studio rig. Use when user mentions "local ollama", "gemma4", "run eval locally", "smoke tier on the rig", "ollama benchmark", or wants to start/monitor a local-model eval rotation. Covers the M-EVAL-LOCAL-OLLAMA + M-EVAL-LOCAL-OBSERVABILITY workflow.

Test, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check pricing, or update models.yml.

Guides AILANG parser development with conventions and patterns. Use when user wants to modify parser, understand parser architecture, or debug parser issues. Saves 30% of development time by preventing token position bugs.

Optimize and manage AILANG teaching prompts for maximum conciseness and accuracy. Use when user asks to create/update prompts, optimize prompt length, or verify prompt accuracy.

Triage SonarCloud issues and hotspots via the SonarCloud Web API — check gate status, list open BLOCKER/CRITICAL bugs + vulns, group hotspots by rule, bulk-mark hotspots Safe per rule, transition issues to False Positive, and change the New Code period. Use whenever the user mentions SonarCloud, Sonar, quality gate red/failing, code smells to triage, marking hotspots safe, marking issues as false positive, setting new code period, or asks "why is the Sonar gate red" — even if they only reference a specific rule like go:S2245 without naming SonarCloud.

Evaluate sprint implementations against design docs and acceptance criteria. Runs after sprint-executor to assess quality with concrete scoring rubric (100 points, 70 to pass). Provides actionable feedback loop on failure. Use when user says "evaluate sprint", "review implementation", "assess sprint quality", or automatically via coordinator after sprint execution.

Debug performance issues and understand code flow using AILANG telemetry traces. Use when user asks to debug slow compilation, analyze benchmarks, find bottlenecks, investigate hangs, or understand system behavior.

Write and run AILANG code with correct syntax. Use when user asks to write AILANG programs, fix AILANG syntax errors, run AILANG code, or needs help with AILANG syntax. Includes version checking, syntax validation, and common patterns.

Diagnose AILANG WASM browser failures — frozen pages, silent loadModule hangs, type-checker stack overflows, missing effect handler bridges, version drift between wasm/ailang.wasm and the .ail source. Use when a browser demo using AILANG WASM behaves differently than the CLI, or when the page freezes without a console error.