agentleFS
IvanLi-CNIvanLi-CN/agent-toolkit/skills/cvm-imagegen/SKILL.md

cvm-imagegen

Skill0 starsChanged 17 days agoMITView on GitHub

Explicit CLI fallback for GPT Image workflows through a configured OpenAI-compatible endpoint.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All three values are explicit.

    line 17
  2. Distinctive:

    Run the following command from this Skill directory:

    line 21
  3. Very specific:

    Use --dry-run to inspect a request without network access.

    line 32
  4. Distinctive:

    Use this Skill only when an explicit CLI/API path is required.

    line 36
  5. Distinctive:

    Keep credentials outside source files, command history and ordinary logs.

    line 37
  6. Distinctive:

    Do not create an additional resident service or endpoint proxy.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CVM Image Generation

This Skill provides an explicit CLI fallback for image generation and editing. It preserves the fallback CLI surface while taking the endpoint and credential names from configuration.

Runtime contract

  • CVM_API_KEY supplies the credential for live calls.
  • CVM_BASE_URL supplies the OpenAI-compatible endpoint.
  • AGENT_IMAGEGEN_SYSTEM_PATH points to the fallback implementation used by the wrapper.
  • scripts/image_gen.py is the public entrypoint.

All three values are explicit. Dry-run validation does not require the key or endpoint; live calls fail fast when either is missing. The wrapper does not modify an installed runtime or assume a particular agent home directory.

Usage

Run the following command from this Skill directory:

export AGENT_IMAGEGEN_SYSTEM_PATH=/path/to/image_gen.py
export CVM_BASE_URL=https://api.example.invalid/v1
export CVM_API_KEY=provided-out-of-band
python3 scripts/image_gen.py generate \
  --prompt "A cozy alpine cabin at dawn" \
  --out /path/to/output/imagegen/cabin.png

Use --dry-run to inspect a request without network access. The wrapper supports generate, edit and generate-batch, including repeated --image reference inputs and the model-specific validation inherited from the configured fallback.

Guardrails

  • Use this Skill only when an explicit CLI/API path is required.
  • Keep credentials outside source files, command history and ordinary logs.
  • Do not create an additional resident service or endpoint proxy.
  • Backend HTTP errors are reported as backend rejections; local request errors stop before a network call.

See the CLI reference, the API reference and the wrapper.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.