Skip to main content
Run any Skill in Manus
with one click
$pwd:
hao-ai-lab
GitHub creator profile

hao-ai-lab

Repository-level view of 34 collected skills across 2 GitHub repositories, including approximate occupation coverage.

skills collected
34
repositories
2
occupation fields
2
updated
2026-05-26
occupation focus
Major fields detected across this creator.
repository explorer

Repositories and representative skills

#001
FastVideo
21 skills3.7k350updated 2026-05-26
62% of creator
add-model-02-parity
Software Quality Assurance Analysts & Testers

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.

2026-05-26
add-model-03-port-dit
Software Developers

Use during /add-model Phase 4 or Phase 6 to prototype or parity-debug one FastVideo-native DiT/transformer component.

2026-05-26
add-model-08-trace
Software Developers

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.

2026-05-26
add-model-09-pipeline
Software Developers

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.

2026-05-26
add-model
Software Developers

Manual /add-model workflow for implementing a FastVideo model or first-class component port after add-model-01-prep has staged reference code and weights. Organizes the port into numbered phases with conversion rules, component policies, parity gates, and handoff checks.

2026-05-26
dreamverse-deploy
Network & Computer Systems Administrators

Use when redeploying the migrated Dreamverse app backend and frontend on a chosen local GPU; tears down existing ports, launches services, and waits for readiness checks.

2026-05-23
reseed-performance-baseline
Data Scientists

Re-seed the HF performance-tracking baseline for an intentional runtime, dependency, or environment-caused benchmark shift using one or more reviewed normalized performance JSONs. Use when performance CI fails because metrics such as latency, throughput, component time, or peak memory changed for an accepted reason and the rolling median baseline in FastVideo/performance-tracking must be advanced from a consistent batch of reviewed source results. The workflow backs up existing history under /tmp, validates all source JSONs for the same (model_id, gpu_type), rejects internally inconsistent source batches, uploads one success=true reseed record per accepted source JSON, and offers to clean local temp state after a successful upload.

2026-05-20
launch-experiment
Data Scientists

Generate and execute a training launch command for FastVideo models

2026-05-18
Showing top 8 of 21 collected skills in this repository.
#002
research-agent
13 skills175updated 2026-02-20
38% of creator
alert-handler
Network & Computer Systems Administrators

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

2026-02-20
agent-mode-research-assistant
Data Scientists

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

2026-02-20
plan-mode-planning-assistant
Biological Scientists, All Other

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

2026-02-20
wild-v2-steer
Software Developers

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

2026-02-20
fastvideo-model-porting-alignment
Software Developers

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.

2026-02-20
wild-v2-execution-ops-protocol
Network & Computer Systems Administrators

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

2026-02-20
wild-v2-gpu-discovery-parallel-scheduling
Network & Computer Systems Administrators

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

2026-02-20
wild-v2-idea
Computer & Information Research Scientists

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

2026-02-20
Showing top 8 of 13 collected skills in this repository.
Showing 2 of 2 repositories
All repositories loaded