Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Integration testing for amd-smi Python packaging. Use when: testing package installs, multi-OS testing, manylinux wheel builds, offline install verification, glibc/Python version compatibility, post-install smoke tests.
Use when writing, planning, or improving unit tests for low-level transport or systems code — especially when reasoning about branch coverage, test gaps, identifying which uncovered paths are worth pursuing, or deciding when a feature's test suite is ready to merge.
Audit whether the unreleased touchdesigner-mcp diff (since the last tag) is adequately covered by integration tests before a release is cut. Walks every API/MCP surface change in the release range, maps each to the integration suite that should cover it, and reports covered / gap / waived per change. Use before releasing, when checking release test coverage, or when asked whether the release diff "has enough tests". This skill AUDITS coverage across the whole release; it delegates HOW to write or run a test to the `integration-test-guard` skill. Pairs with `prepare-release` and the `release-manager` agent.
Analyze QA regression impact for Tonkeeper Web by comparing the current branch with the relevant release tag, reviewing sources/Web/regress.txt, and recommending test blocks, missing coverage, extra checks, and a generated TXT test collection.
A generic workflow for self-starting TouchDesigner via computer-use (or an already-running instance), loading mcp_webserver_base.tox, and verifying any TD-side Python change (td/modules/**) directly from the Textport — reading back real TD runtime values and reconciling them. Use after changing TD-side code in the touchdesigner-mcp repo when E2E verification on a real TD is needed, or when told to "start TD and check," "verify on the actual machine," or "import and run the .tox." Includes the shortcut of calling api_service directly, bypassing the HTTP WebServer / OpenAPI schema.
Diagnose and fix Lingui SWC plugin compatibility errors with Next.js, Rspack, or other SWC runtimes. Use when seeing errors like "failed to invoke plugin", "failed to run Wasm plugin transform", "out of bounds memory access", or "LayoutError" during builds with @lingui/swc-plugin.
MUST invoke before creating or editing any Angular component's tests (spec file). Enforces the Page Object Model pattern – tests drive components through the rendered DOM (their public contract) rather than reaching into component internals.
Review an existing LLM harness for correctness and gameplay-impacting bugs. Use when the user asks to "review", "audit", "check", "look over", or "find bugs in" a harness, or asks whether a harness has issues that could affect win rates. Covers static code review (prompt accuracy, parser robustness, common anti-patterns), optional replay-archive scanning to quantify real-world impact, and an optional cross-harness sweep for the same anti-patterns.
Use when building, deploying, running, screenshotting, clicking through, or debugging the Voltius Tauri app on a real Android phone — drives the on-device debug APK through the tauri-android MCP (adb + Chrome DevTools Protocol) so changes are seen and interacted with on the device, not just compiled.
Use when building, deploying, running, screenshotting, clicking through, or debugging the Voltius Tauri app on a headless Android emulator running in Docker (no physical phone) — drives the in-container x86_64 emulator through the tauri-android MCP (adb + Chrome DevTools Protocol) so changes are seen and interacted with, not just compiled.