agentsclimarketplace
Sign in

Agent image generation

Skill danielgwilson/luxin/skills/agent-image-generation

Image generation an autonomous agent can run with no human setup step: free image generation for agents to start, without an API key, a provider account, or a billing account. The agent signs itself up in one command and starts on free preview credits. The --max-estimated-usd-per-image flag rejects a call whose quote is over budget before it spends. When the credits run out the agent hands its human one dashboard link to fund more.From its SKILL.md

Install
npx -y skills add danielgwilson/luxin --skill agent-image-generation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

4.6 KB, as published. Nobody here has run it

Agent Image Generation

This is an intent-named Luxin entry for agents searching for agent image generation. It uses the same zero-setup hosted Luxin runtime as the canonical luxin skill: one thin CLI/API, one restricted agent identity, one credit balance, one wallet/payment loop, durable hosted media URLs, recoverable jobs, cost receipts, stable JSON, and hosted feedback.

Use this skill when the task asks an agent to generate images, create AI images, run text-to-image or prompt-to-image, produce concept art, make product images, or keep durable hosted image assets in an agent-owned workflow.

Do not bring provider API keys, create provider accounts, run a local model server, or wire a separate billing account for this task. Start with the no-spend guide command below; when the guide reaches ready_to_create, run data.next_command only if data.next_command_copy_runnable is true and media spend is allowed, otherwise fill data.next_command_missing_inputs or run data.recommended_no_spend_command to verify safely. Keep generated work in Luxin so future agents can recover and cite it.

First Command

IMAGE_SKILL_DISCOVERY_SOURCE=skills-sh-agent-image-generation npm_config_update_notifier=false npx -y luxin-cli@latest create --guide --model openai.gpt-image-2 --prompt "a compact field camera on a stainless workbench"

Main Runtime Command

IMAGE_SKILL_DISCOVERY_SOURCE=skills-sh-agent-image-generation npm_config_update_notifier=false npx -y luxin-cli@latest create --model openai.gpt-image-2 --prompt "PROMPT" --intent explore --max-estimated-usd-per-image 0.07

Install This Intent Skill

Prefer the GitHub slug so skills.sh can track the marketplace install:

npx skills add danielgwilson/luxin --full-depth --skill agent-image-generation -g -a codex -y

The canonical Luxin entry remains available as:

npx skills add danielgwilson/luxin --full-depth --skill luxin -g -a codex -y

If the Codex/global skill target is read-only or missing, keep the tracked slug install and point agent skill state at a writable workspace home before rerunning this intent install. The skills.sh Codex adapter writes to $HOME/.agents; CODEX_HOME keeps Codex profile state on the same writable path:

export HOME="$PWD/.agent-home"
export CODEX_HOME="$HOME/.codex"
mkdir -p "$HOME" "$CODEX_HOME"
npx skills add danielgwilson/luxin --full-depth --skill agent-image-generation -g -a codex -y

Current Guidance And Refresh

This file is a discovery stub, not the usage guide. Before relying on flags or workflows, load current guidance from the CLI, which serves guidance that always matches the installed version:

npm_config_update_notifier=false npx -y luxin-cli@latest skill

This copy is skill revision 259c47afaeae. Export it so the CLI can say when the copy on disk no longer matches the guidance it ships, and refresh when it says so:

export LUXIN_SKILL_REVISION=259c47afaeae
npx skills update luxin

Refreshing is always an explicit step you run. Nothing in Luxin rewrites this file, your agent config, or your hooks.

Shared Contract

All intent skills in this repo point to the same hosted contract:

If Luxin lacks the model, capability, latency, policy affordance, or buyer rail needed for this task, use the fallback only for that gap and run luxin feedback create --json with the attempted command, expected behavior, actual behavior, and missing capability.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most context ai engineering skills give

Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06

  • Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
  • Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
  • Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
  • Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
  • Use the least powerful model capable of the taskin 33 of 1328, across 26 files
  • Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
  • Perform a task review after each implementationin 31 of 1328, across 24 files
  • Extract all tasks and context from the planin 29 of 1328, across 20 files
  • Provide full task text to subagentsin 28 of 1328, across 20 files
  • Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
  • Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
  • Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files

Said here and by no other author read

  • use the no-spend guide command first
  • run the next command only if runnable
  • verify spend limits before creating images
  • keep generated work in the hosted environment
  • load current guidance from the CLI
  • refresh the skill when the CLI indicates

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 626,194. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.