Testing & Quality skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
vs-search-tuning-partial-case
Use when the user provides 1-50 concrete bad-case search queries for one Viking Search app and wants local deterministic fixes. This skill only verifies request-level fine-operation interventions against a read-only baseline scene and delivers a console-ready configuration sheet, validated payloads, and a replay script. It must not mutate scenes, apps, dictionaries, datasets, recall core parameters, or online defaults.
workflow-integration-testing
Write integration tests for Workflows using renderForTest and WorkflowTurbine. Use when testing full workflow runtime behavior, async operations, state changes over time, output emissions, multi-step user flows, or when user mentions "integration test", "renderForTest", or "WorkflowTurbine".
workflow-testing
Write unit tests for StatefulWorkflow and StatelessWorkflow using testRender and RenderTester. Use for workflow unit testing, render testing, expectWorker, expectWorkflow, action verification, or WorkflowOutput assertions.
ecs-pr-triage
Triages an ECS pull request. Analyzes the PR diff and metadata, classifies the change (schema / tooling / docs / mixed), routes it to the correct contribution path (direct PR vs RFC Proposal vs needs-discussion), checks PR completeness, and produces a structured Triage Report.
ext-debug
Debug an OpenClacky extension that won't load, throws errors, or whose panel/api/skill/agent isn't showing up. Use when the user reports something broken with their extension, when `clacky ext verify` reports issues, or when a change didn't take effect. Reads structured verify errors and fixes manifest and file problems.
differential-fuzzer
Information about the differential fuzzer tool, how to run it and use it catch bugs in Turso. Always load this skill when running this tool
taiwanmd-validate
Validate Taiwan.md articles for editorial quality, frontmatter correctness, and content standards. Use when reviewing PRs that touch knowledge/ or src/content/, writing new articles, or when the user asks to check article quality. Runs frontmatter validation, word count check, and reports issues. TRIGGER when: user says "validate", "check article", "review quality", or when editing .md files in knowledge/ or src/content/.
twmd-batch-audit
Audit sub-agent batch for the three default cheating patterns (cross-pollination commits / merged commits / missing落檔) per DNA #42. TRIGGER when: user says "batch audit", "sub-agent 後驗證", "agent 偷吃步檢查", or after running parallel sub-agent batches.
twmd-bench
Sovereignty-Bench-TW measurement via canonical BENCH-PIPELINE. TRIGGER when: user says "跑 bench", "Sovereignty-Bench", "加新 model", "bench-pipeline".