mrhy7176/cloudgpu-agent-skills 5 graded agent skills from mrhy7176
mrhy7176/cloudgpu-agent-skills brings together 5 skills for AI agent and LLM engineering, video, image, audio and creative, DevOps and cloud. Start with the task descriptions below, then compare the individual skill's score, source files and license.
5 listed skills; recorded scores 77/100. 5 full reviews with separate installation details. Scores describe the saved source snapshot, using the Suede Skill Check.
Download the collection manifest: complete task descriptions, scores, license information, source revisions and install routes for all 5 listed skills. Use it to compare options or hand your selection to an agent.
Choose a skill for your task
Every listed skill in this collection is explained below. Task descriptions come from the publisher; score explanations come from the saved report.
cloudgpu-ai-short-drama 77/100 · C
Publisher's task description: Rent GPU compute for an AI short-drama pipeline using open video models, character LoRA and image workflows. Use when creating GPU-rendered shots and collecting reusable video assets, with a user-approved stage budget and a review before final rendering.
Score evidence: Full points for structural checks, recent maintenance and instruction depth. Largest point gaps: curated-list citations (0/7); boundary clause (0/4).
See all score components for cloudgpu-ai-short-drama
Structural checks
56 of 56
Description length
5 of 5
Boundary clause
0 of 4
Example request
0 of 3
Instruction depth
7 of 7
Reference files
0 of 3
Bundled scripts
0 of 2
Recent maintenance
9 of 9
Curated-list citations
0 of 7
Tool permissions declared
0 of 2
Compatibility declared
0 of 2
License: MIT governs reuse and modification of these files.
Named environment variables: CLOUDGPU_API_KEY.
Requires an approved GPU workload, CloudGPU account connection for paid work, spend/time caps and export checks. Public instance tunnels need access protection for private data. Export outputs before disk destruction or balance exhaustion. Model and dataset rights are separate from the MIT skill license. The optional external cloudgpu-mcp package was not reviewed. Static skill review only; no runtime or security scan. Publisher setup instructions.
Publisher's task description: Rent a GPU to generate images with ComfyUI and an open image model such as FLUX, then retrieve images and workflow metadata. Use when a user-provided image workflow needs more GPU memory or CUDA than the local machine.
Score evidence: Full points for structural checks, recent maintenance and instruction depth. Largest point gaps: curated-list citations (0/7); boundary clause (0/4).
See all score components for cloudgpu-comfyui-images
Structural checks
56 of 56
Description length
5 of 5
Boundary clause
0 of 4
Example request
0 of 3
Instruction depth
7 of 7
Reference files
0 of 3
Bundled scripts
0 of 2
Recent maintenance
9 of 9
Curated-list citations
0 of 7
Tool permissions declared
0 of 2
Compatibility declared
0 of 2
License: MIT governs reuse and modification of these files.
Named environment variables: CLOUDGPU_API_KEY.
Requires an approved GPU workload, CloudGPU account connection for paid work, spend/time caps and export checks. Public instance tunnels need access protection for private data. Export outputs before disk destruction or balance exhaustion. Model and dataset rights are separate from the MIT skill license. The optional external cloudgpu-mcp package was not reviewed. Static skill review only; no runtime or security scan. Publisher setup instructions.
Publisher's task description: Discover and compare GPU compute for an AI agent, without an account. Use when local CUDA or VRAM is insufficient, or when asked how an agent can find GPUs, estimate task cost and obtain user approval before computing.
Score evidence: Full points for structural checks, recent maintenance and instruction depth. Largest point gaps: curated-list citations (0/7); boundary clause (0/4).
See all score components for cloudgpu-discover-compute
Structural checks
56 of 56
Description length
5 of 5
Boundary clause
0 of 4
Example request
0 of 3
Instruction depth
7 of 7
Reference files
0 of 3
Bundled scripts
0 of 2
Recent maintenance
9 of 9
Curated-list citations
0 of 7
Tool permissions declared
0 of 2
Compatibility declared
0 of 2
License: MIT governs reuse and modification of these files.
Named environment variables: CLOUDGPU_API_KEY.
Requires an approved GPU workload, CloudGPU account connection for paid work, spend/time caps and export checks. Public instance tunnels need access protection for private data. Export outputs before disk destruction or balance exhaustion. Model and dataset rights are separate from the MIT skill license. The optional external cloudgpu-mcp package was not reviewed. Static skill review only; no runtime or security scan. Publisher setup instructions.
Publisher's task description: Rent a GPU to train or fine-tune an open model with LoRA or QLoRA and retrieve adapters, checkpoints and metrics. Use when model training exceeds local CUDA, VRAM or storage and the user wants a bounded remote training run.
Score evidence: Full points for structural checks, recent maintenance and instruction depth. Largest point gaps: curated-list citations (0/7); boundary clause (0/4).
See all score components for cloudgpu-lora-finetune
Structural checks
56 of 56
Description length
5 of 5
Boundary clause
0 of 4
Example request
0 of 3
Instruction depth
7 of 7
Reference files
0 of 3
Bundled scripts
0 of 2
Recent maintenance
9 of 9
Curated-list citations
0 of 7
Tool permissions declared
0 of 2
Compatibility declared
0 of 2
License: MIT governs reuse and modification of these files.
Named environment variables: CLOUDGPU_API_KEY.
Requires an approved GPU workload, CloudGPU account connection for paid work, spend/time caps and export checks. Public instance tunnels need access protection for private data. Export outputs before disk destruction or balance exhaustion. Model and dataset rights are separate from the MIT skill license. The optional external cloudgpu-mcp package was not reviewed. Static skill review only; no runtime or security scan. Publisher setup instructions.
Publisher's task description: Run open-model GPU inference or evaluation and retrieve outputs, metrics and logs. Use when a private or custom model needs CUDA, larger VRAM, an Ollama instance or a bounded batch beyond the local machine.
Score evidence: Full points for structural checks, recent maintenance and instruction depth. Largest point gaps: curated-list citations (0/7); boundary clause (0/4).
See all score components for cloudgpu-open-model-inference
Structural checks
56 of 56
Description length
5 of 5
Boundary clause
0 of 4
Example request
0 of 3
Instruction depth
7 of 7
Reference files
0 of 3
Bundled scripts
0 of 2
Recent maintenance
9 of 9
Curated-list citations
0 of 7
Tool permissions declared
0 of 2
Compatibility declared
0 of 2
License: MIT governs reuse and modification of these files.
Named environment variables: CLOUDGPU_API_KEY.
Requires an approved GPU workload, CloudGPU account connection for paid work, spend/time caps and export checks. Public instance tunnels need access protection for private data. Export outputs before disk destruction or balance exhaustion. Model and dataset rights are separate from the MIT skill license. The optional external cloudgpu-mcp package was not reviewed. Static skill review only; no runtime or security scan. Publisher setup instructions.
Select one skill. Use the folder-specific command beside its description; a whole-repository install can include other files or miss nested skills, so use the listed skill's folder. Skills with publisher-specific license terms link to that publisher's setup route.
Read the setup requirements. Check the source, license and any named tools or environment variables. Installing a SKILL.md folder supplies instructions to the agent; any external CLI, MCP server, account or service still needs its own setup.
Check the result. Open the installed SKILL.md and confirm that its name matches your selection. In Claude Code use the project's .claude/skills/ folder; in Codex use .agents/skills/. The skills CLI also supports other Agent Skills hosts.
Try one representative task. Supply the input files, expected output and success criteria. Compare the result with those criteria before adding more skills or running the workflow on live work.
For AI agent and LLM engineering, compare task fit first, then the score components, installation requirements and license. Two skills with the same score can earn their points in different ways; use their reports to see the difference.
This general badge links to the repository listing. Each skill keeps its own score and grade; skills scoring 80–99 add a numeric and a letter quality badge. Choose Improve this score in the skill table to request a fresh review.
Limited-time feature offer: Display either quality badge in your repository or skill README, linked to your listing, then request verification. Suede checks the rendered README at a recorded commit. Eligible skills scoring 80–99 with a verified badge can receive a featured placement while the offer is open. Request badge verification.
Where this repository is cited
mrhy7176/cloudgpu-agent-skills is listed as its publisher's official collection or from a listing request.