Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when testing Pure Pure Bangumi (EasyBangumi) Android features through real adb-driven UI flows, including app launch, app data reset, local mock HTTP servers on Mac, device-to-host port mapping, UI hierarchy dumps, reusable page navigation, and evidence collection for manual or scripted feature verification.
Use after major refactors or risky infrastructure changes to run iterative stabilization loops in kube-test: clean state, run the v3 matrix (k3s/rke2, autoscaler, leapmicro/microos, multi-arch), proactively debug failures over SSH/journalctl, apply fixes, retest until green, then validate upgrade paths from the latest tag to current staging.
Use after making changes to run Terraform/OpenTofu formatting, validation, and plans against the test environment
Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.
Investigate fast-agent session and history files to diagnose issues. Use when a session ended unexpectedly, when debugging tool loops, when correlating sub-agent traces with main sessions, or when analyzing conversation flow and timing. Covers session.json metadata, history JSON format, message structure, tool call/result correlation, and common failure patterns.
Use during /add-model after reference/architecture study to scaffold and later activate local FastVideo component parity tests. Emphasizes early test creation, official-reference loading, standardized FastVideo loading, and non-skip handoff gates.
Use during /add-model Phase 6 when component parity has failed and root cause requires layer-by-layer divergence analysis. Uses FastVideo activation trace first, falling back to custom hooks only for boundaries or stats the utility cannot observe.
Review rubric for FastVideo PRs that add or modify model families, variants, first-class components, checkpoint conversion, pipelines, parity coverage, or generated-media quality baselines. Use when reviewing a PR whose diff touches fastvideo/models/, fastvideo/pipelines/basic/, fastvideo/registry.py, scripts/checkpoint_conversion/, fastvideo/tests/ssim/, or related model-port surfaces. Pairs with review-pr-link as a project-scoped review pass; produces findings, not fixes.
Re-seed HF reference videos for a single existing SSIM test on Modal L40S. Always backs up current refs locally first, regenerates on Modal, pauses for the user to eyeball before-vs-after quality, then overwrites the targeted `<model_id>` subtree on `FastVideo/ssim-reference-videos` with `--force`. Use when an intentional code change (model port fix, attention backend swap, kernel upgrade, hyperparameter change) has invalidated existing refs and they need to be regenerated. Pairs with `seed-ssim-references`, which is for first-time seeding only.