Skip to main content
hao-ai-lab
GitHub 创作者资料

hao-ai-lab

按仓库查看 3 个 GitHub 仓库中的 31 个已收集 skills。

已收集 skills
31
仓库
3
更新
2026年8月26日
仓库浏览

仓库与代表性 skills

ci-runner
网络与计算机系统管理员

Work on FastVideo's Slurm-only, change-aware GPU CI lanes, static Buildkite graph, trusted ci-runner policy, lane scripts, and GB200 validation.

2026年8月26日
reseed-ssim-references
软件质量保证分析师与测试员

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 subtree on…

2026年8月26日
seed-ssim-references
软件质量保证分析师与测试员

Seed HF reference artefacts for a single newly-added SSIM test (pixel `.mp4` for `run_text_to_video_similarity_test`-style tests, or latent `.pt` for `run_text_to_latent_similarity_test`-style tests). Runs the test on Modal L40S, downloads the generated…

2026年8月26日
add-model-01-prep
软件开发工程师

Use at the start of a FastVideo model port to gather required inputs, inspect/download HF weights, clone and install the official reference repo in the current environment, create a local_tests README skeleton, and produce a handoff before conversion or…

2026年8月9日
add-model-02-parity
软件质量保证分析师与测试员

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.

2026年8月9日
add-model-07-conversion
软件开发工程师

Use during /add-model Phase 5 to write and verify a FastVideo checkpoint conversion script after native component prototypes expose FastVideo state-dict keys/shapes.

2026年8月9日
add-model-08-trace
软件开发工程师

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.

2026年8月9日
add-model-09-pipeline
软件开发工程师

Use during /add-model Phase 7 after all required component parity tests pass to define FastVideo pipeline wiring, configs, presets, registry entries, examples, smoke tests, and pipeline parity tests.

2026年8月9日
已展示 8 / 17 个已收集 Skill。
alert-handler
网络与计算机系统管理员

System prompt for handling experiment alerts. Provides diagnosis guidance, GPU wrapper context, action suggestions, and structured response from allowed choices.

2026年2月20日
agent-mode-research-assistant
数据科学家

Default system prompt for agent chat mode. Provides identity, environment context, compute awareness, API-driven job submission, and workflow reflection.

2026年2月20日
plan-mode-planning-assistant
其他生物科学家

Generates a structured experiment plan with compute-aware recommendations and saves it via the plan API endpoint.

2026年2月20日
wild-v2-steer
软件开发工程师

Wraps user steering input with context signals for the model during a wild loop session

2026年2月20日
fastvideo-model-porting-alignment
软件开发工程师

Ports new models into FastVideo with strict numerical alignment to official implementations. Use when adding a FastVideo model/pipeline, porting an official or Diffusers checkpoint, or debugging parity/alignment.

2026年2月20日
wild-v2-execution-ops-protocol
网络与计算机系统管理员

Single source of truth protocol for Wild V2 preflight, sweep/run auditability, GPU discovery, and parallel scheduling

2026年2月20日
wild-v2-gpu-discovery-parallel-scheduling
网络与计算机系统管理员

Protocol for GPU discovery and parallel run scheduling across local GPU and Slurm clusters

2026年2月20日
wild-v2-idea
计算机与信息研究科学家

Ideation prompt for Wild Loop V2 - generate high-quality, falsifiable research ideas with proposal and plan artifacts

2026年2月20日
已展示 8 / 13 个已收集 Skill。
已展示 3 / 3 个仓库
已展示全部仓库