Skill collection · mrhy7176

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.

View mrhy7176/cloudgpu-agent-skills on GitHub

At a glance

Publishermrhy7176
Repositorygithub.com/mrhy7176/cloudgpu-agent-skills
Listed skills5
Source assessedNovember 19, 2026
Security scanNot scanned
CategoriesAI Agents and LLM Engineering, Video, Image, Audio and Creative, DevOps and Cloud
LicenseMIT
Last commitNovember 15, 2026
README badgeGet the badge for this listing

What this collection offers

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.

Coverage: AI Agents and LLM Engineering (2) · Video, Image, Audio and Creative (2) · DevOps and Cloud (1).

Snapshot: . The checks measure published files, documentation and maintenance signals. Security scan: not scanned; this is not a runtime test.

Choose a skill · Install and verify · All listed skills · Compare collections

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.

939 words in SKILL.md; 1 bundled file. Read the assessed SKILL.md (November 19, 2026).

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 checks56 of 56
Description length5 of 5
Boundary clause0 of 4
Example request0 of 3
Instruction depth7 of 7
Reference files0 of 3
Bundled scripts0 of 2
Recent maintenance9 of 9
Curated-list citations0 of 7
Tool permissions declared0 of 2
Compatibility declared0 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: cloudgpu-ai-short-drama
npx skills add https://github.com/mrhy7176/cloudgpu-agent-skills/tree/main/cloudgpu-ai-short-drama

Download cloudgpu-ai-short-drama score report · Read the full cloudgpu-ai-short-drama review and install guide

cloudgpu-comfyui-images 77/100 · C

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.

870 words in SKILL.md; 1 bundled file. Read the assessed SKILL.md (November 19, 2026).

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 checks56 of 56
Description length5 of 5
Boundary clause0 of 4
Example request0 of 3
Instruction depth7 of 7
Reference files0 of 3
Bundled scripts0 of 2
Recent maintenance9 of 9
Curated-list citations0 of 7
Tool permissions declared0 of 2
Compatibility declared0 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: cloudgpu-comfyui-images
npx skills add https://github.com/mrhy7176/cloudgpu-agent-skills/tree/main/cloudgpu-comfyui-images

Download cloudgpu-comfyui-images score report · Read the full cloudgpu-comfyui-images review and install guide

cloudgpu-discover-compute 77/100 · C

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.

783 words in SKILL.md; 1 bundled file. Read the assessed SKILL.md (November 19, 2026).

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 checks56 of 56
Description length5 of 5
Boundary clause0 of 4
Example request0 of 3
Instruction depth7 of 7
Reference files0 of 3
Bundled scripts0 of 2
Recent maintenance9 of 9
Curated-list citations0 of 7
Tool permissions declared0 of 2
Compatibility declared0 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: cloudgpu-discover-compute
npx skills add https://github.com/mrhy7176/cloudgpu-agent-skills/tree/main/cloudgpu-discover-compute

Download cloudgpu-discover-compute score report · Read the full cloudgpu-discover-compute review and install guide

cloudgpu-lora-finetune 77/100 · C

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.

864 words in SKILL.md; 1 bundled file. Read the assessed SKILL.md (November 19, 2026).

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 checks56 of 56
Description length5 of 5
Boundary clause0 of 4
Example request0 of 3
Instruction depth7 of 7
Reference files0 of 3
Bundled scripts0 of 2
Recent maintenance9 of 9
Curated-list citations0 of 7
Tool permissions declared0 of 2
Compatibility declared0 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: cloudgpu-lora-finetune
npx skills add https://github.com/mrhy7176/cloudgpu-agent-skills/tree/main/cloudgpu-lora-finetune

Download cloudgpu-lora-finetune score report · Read the full cloudgpu-lora-finetune review and install guide

cloudgpu-open-model-inference 77/100 · C

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.

860 words in SKILL.md; 1 bundled file. Read the assessed SKILL.md (November 19, 2026).

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 checks56 of 56
Description length5 of 5
Boundary clause0 of 4
Example request0 of 3
Instruction depth7 of 7
Reference files0 of 3
Bundled scripts0 of 2
Recent maintenance9 of 9
Curated-list citations0 of 7
Tool permissions declared0 of 2
Compatibility declared0 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: cloudgpu-open-model-inference
npx skills add https://github.com/mrhy7176/cloudgpu-agent-skills/tree/main/cloudgpu-open-model-inference

Download cloudgpu-open-model-inference score report · Read the full cloudgpu-open-model-inference review and install guide

Install and verify your selection

  1. 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.
  2. 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.
  3. 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.
  4. 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.

Step-by-step installation for Claude Code, Codex and Cursor · Read the directory's security and source policy.

Skills in mrhy7176/cloudgpu-agent-skills

Use the table to compare the full collection. Linked names open a detailed review when available; other names open the publisher's source folder.

SkillCategoryWhat it does
cloudgpu-ai-short-drama 77/100 · CMediaPlan staged GPU-rendered shots with open video models, character LoRA and image workflows, then export reusable assets within an approved budget.

Source assessed November 19, 2026.

Improve this score

Download report · Request a fresh review

cloudgpu-comfyui-images 77/100 · CMediaRun an approved ComfyUI image workflow on rented GPU compute and retrieve images with their workflow metadata.

Source assessed November 19, 2026.

Improve this score

Download report · Request a fresh review

cloudgpu-discover-compute 77/100 · CDevOpsCompare GPU capacity and task costs without creating a paid instance, then prepare a proposal for user approval.

Source assessed November 19, 2026.

Improve this score

Download report · Request a fresh review

cloudgpu-lora-finetune 77/100 · CAI agentsPlan a bounded LoRA or QLoRA training run on rented GPUs and export adapters, checkpoints and metrics.

Source assessed November 19, 2026.

Improve this score

Download report · Request a fresh review

cloudgpu-open-model-inference 77/100 · CAI agentsRun an approved open-model inference or evaluation workload with protected serving and explicit output retrieval.

Source assessed November 19, 2026.

Improve this score

Download report · Request a fresh review

Compare before adding more skills

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.

Compare AI agent and LLM engineering skills across publishers · Build a side-by-side comparison.

Show the listing in your README

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.

Suede Skills Directory: listed

Markdown
[![Suede Skills Directory: listed](https://suedeai.directory/mrhy7176/cloudgpu-agent-skills/badge.svg)](https://suedeai.directory/mrhy7176/cloudgpu-agent-skills/)
HTML
<a href="https://suedeai.directory/mrhy7176/cloudgpu-agent-skills/"><img src="https://suedeai.directory/mrhy7176/cloudgpu-agent-skills/badge.svg" alt="Suede Skills Directory: listed" height="20"></a>

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.