image-batch-runner — Claude Code skill: what it does, how to install
Runs prepared image briefs and reference edits via the postplus CLI. Produces local files and run manifests for downstream review.
npx skills add PostPlusAI/postplus-skills --skill image-batch-runner -a claude-codeWhat image-batch-runner does
This skill processes pre-defined briefs for characters and product concepts. It skips prompt brainstorming, focusing entirely on validating parameters and sending jobs to cloud endpoints through postplus media create. Internal requests and manifests remain under the .postplus directory, while final image assets land in the active workspace folder.
Executions run asynchronously, which means rendered files must be retrieved manually via postplus media-file download. When managing batches, the runner fires an initial canary item first. A content policy block on that item gets logged and skipped, while connection errors or authentication failures immediately halt the entire queue. Without the postplus CLI installed and authenticated, jobs cannot execute.
What it helps with
- execute prepared image briefs across hosted generation endpoints
- apply reference-guided edits to existing local files or URLs
- record execution manifests and artifact metadata for QA
- isolate safety-filtered items during batch execution without stopping the run
Example prompts for the agent
- Execute the image briefs from
.postplus/brief.jsonusing the default endpoint - Edit the product shot with
input.pngas reference usingimage-gpt-image-2-edit - Run diagnostics with doctor before dispatching the batch run
How to install image-batch-runner
1Skills CLI (Vercel)
npx skills add PostPlusAI/postplus-skills --skill image-batch-runner -a claude-code2Manually: put the files in place
~/.claude/skills/image-batch-runner/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/image-batch-runner/
1Skills CLI (Vercel)
npx skills add PostPlusAI/postplus-skills --skill image-batch-runner -a codex2Manually: put the files in place
.agents/skills/image-batch-runner/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add PostPlusAI/postplus-skills --skill image-batch-runner -a cursor2Manually: put the files in place
.cursor/skills/image-batch-runner/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install PostPlusAI/postplus-skills image-batch-runner2Manually: put the files in place
.github/skills/image-batch-runner/SKILL.md1Skills CLI (Vercel)
npx skills add PostPlusAI/postplus-skills --skill image-batch-runner -a gemini-cli2Platform CLI
gemini skills install https://github.com/PostPlusAI/postplus-skills --path skills/40-creative/image-batch-runnerManually: put the files in place
.devin/skills/image-batch-runner/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add PostPlusAI/postplus-skills --skill image-batch-runner -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about image-batch-runner
How to install image-batch-runner in Claude Code?
Run npx skills add PostPlusAI/postplus-skills --skill image-batch-runner -a claude-code. The skill definition file is placed at ~/.claude/skills/image-batch-runner/SKILL.md.
What does image-batch-runner do?
It validates finalized briefs, triggers hosted image runs via the postplus CLI, and monitors async generation jobs until completion.
Can I pass reference images to text generation endpoints?
No, flags like --reference-image are restricted to edit endpoints such as image-gpt-image-2-edit. Standard text endpoints reject this option.
