Agent Skills › renoir1220/esse › batch-generate-images

batch-generate-images

GitHub

通过本地 Esse MCP 进行批量图片生成与管理。支持持久化状态、自动提交任务、多语言提示词处理及基于本地文件的参考引用,实现高效且受控的图片生产流程。

sidecars/agent/skills/batch-generate-images/SKILL.md renoir1220/esse

Trigger Scenarios

用户请求生成或修改图片 用户要求查看 Esse 工作台

Install

npx skills add renoir1220/esse --skill batch-generate-images -g -y
More Options

Non-standard path

npx skills add https://github.com/renoir1220/esse/tree/main/sidecars/agent/skills/batch-generate-images -g -y

Use without installing

npx skills use renoir1220/esse@batch-generate-images

指定 Agent (Claude Code)

npx skills add renoir1220/esse --skill batch-generate-images -a claude-code -g -y

安装 repo 全部 skill

npx skills add renoir1220/esse --all -g -y

预览 repo 内 skill

npx skills add renoir1220/esse --list

SKILL.md

Frontmatter
{
    "name": "batch-generate-images",
    "description": "Use Esse for durable image batches from an Agent; preserve prompts and references, use the configured model, and continue already-authorized tracking, image verification, and bounded rework."
}

Esse batch generation

Use the authenticated local Esse MCP. Esse is a local image task workspace and execution harness, not an image-generation model or model architecture. It sends each job to the Provider and model already configured by the user. Do not describe Esse as a diffusion model or infer the configured model's abilities or limitations from Esse itself. Preserve the user's requested content faithfully and submit it; ask a question only when a required input or target is genuinely missing or ambiguous.

Esse is the durable owner of batch state, original files, retries, and history. Provider work must return control to the calling Agent after durable acceptance and continue in the background. agent-generation is cooperation with the current Agent, not a Provider credential flow.

Workflow

  1. Call open_esse only when the user asks to see the Esse workbench. Use tab: settings only for setup; otherwise use tab: batches and include a known batchId. Routine headless work must not focus the app or interrupt the user.
  2. A direct request to generate or modify images with Esse is sufficient authorization to submit the work. For ordinary work, do not call list_image_offerings, do not ask for a second confirmation, and omit the legacy approvedEstimatedCostMicros field. Do not interrupt a sufficiently specified request with a generic warning about text, numbers, charts, infographics, or what image models may handle imperfectly; write the best faithful prompt and submit it. Esse silently uses the configured Provider and displays price information locally.
  3. Write every image prompt in the language the user is currently using. Chinese requests must produce Chinese image prompts. If the user's language cannot be determined, default to Simplified Chinese. Use English prompts only when the user explicitly requests English.
  4. Omit offeringId so Esse uses the user's configured model. Never select a model based on price, subject, or your own preference. Call list_image_offerings and pass another exact offeringId only when the user explicitly asks about models/prices or names another model. Select workbuddy-agent-generation only when the user explicitly asks the current Agent's image capability to own the jobs. Never ask for Provider credentials in conversation; API Keys are entered and protected inside Esse.
  5. When a request depends on local image content, call inspect_image_folder before writing prompts. Page through the directory when needed and preserve the returned paths exactly; do not claim to have inspected unseen files.
  6. Treat every batch child as an independent job with its own prompt and references. Use jobs[] whenever prompts or references differ. Use top-level references only when every child intentionally shares them. folderPath or imagePaths creates one aligned job per input image, and perImagePrompts may key prompts by full path, basename, one-based index, or zero-based index. Each job supports at most 20 references.
  7. Use referenceImagePaths for ordinary local files. A picture pasted or attached to the current WorkBuddy message is a real input attachment: materialize it to a real absolute local path, then pass that path through referenceImagePaths. For modify_selected_images, keep the Esse target in imageIds and put every pasted or attached background/style/content reference in referenceImagePaths; describing the attachment in prompt is not a substitute for sending it. When the user names an existing Esse result such as 图1 or 图1-1, pass referenceImages: [{ batchId, image }]. If the exact batch is unknown, call list_image_batches with a limit from 1 to 50 and resolve it. Ask when multiple batches are plausible. Never invent an output path or silently omit a requested reference. If an attachment cannot be materialized to a readable local file, do not submit a misleading text-only edit; report that the attachment could not be transferred.
  8. For genuinely new work, call create_image_batch once with a stable requestKey. Never use it to modify an existing image. Esse discovers and activates the accepted batch without another open_esse call.
  9. For more work in an existing batch, call append_image_batch_jobs with the exact batchId and a stable requestKey. Append to active or terminal batches in place; never create a temporary batch or merge to simulate append. Omit offeringId to reuse the batch model unless the user explicitly names another.
  10. Inspect the returned execution mode and retain the exact batch/job handles. A submit-only Provider request may end after handoff. An original task or active Goal that already authorizes tracking, verification, or bounded rework continues under Authorized continuation below; background acceptance is not final task acceptance.
  11. When the returned offering uses adapterId: agent-generation or execution: current-agent, complete every accepted Agent-owned job instead of returning after acceptance. For append, act only on appendedJobIds:
    • Call start_agent_image_job before each generation and use its exact prompt and every referenceImagePaths entry. One start call is exactly one outbound image-generation request: never combine reference paths from other batch jobs into it. Independent jobs may run concurrently, but their prompts, references, and request-size checks stay isolated per job.
    • Use the current Agent's available image capability; do not require OAuth, Provider keys, Codex CLI, or a particular image tool.
    • On success, call complete_agent_image_job with the real absolute imagePath. On failure, call fail_agent_image_job with the real error. If generation is unavailable, fail every pending Agent-owned job instead of leaving it queued.
    • Agent job callbacks update Esse directly; query the exact batch only when needed for already-authorized verification.
  12. Resolve modification targets before calling modify_selected_images:
    • Use exact image IDs for named current results, numbered backups such as 图2-1, and failed-job source images.
    • If the request names no target and the batch has multiple available images, ask which image to change. A sole image may be inferred only when the request is otherwise unambiguous.
    • Call modify_selected_images once with the exact batchId and imageIds. Never create a replacement batch. Current results update in place while prior versions remain as 图1-1, 图1-2, and so on; selecting a backup or failed source creates a new job in the same batch from that exact asset.
    • Omit offeringId to reuse the batch model unless the user explicitly names another, then follow the managed or Agent-owned execution branch above.
  13. Delete only explicitly authorized exact image IDs with delete_esse_images. Deleting a current image also deletes its preserved versions. Do not delete queued/running images or interpret image deletion as permission to delete a batch.
  14. Combine distinct terminal batches only with merge_image_batches, one exact target and exact source IDs, and a stable requestKey. Merge moves jobs, images and history into the target, then removes the source batches after durable acceptance. The legacy deleteSourceBatches argument does not change this behavior. Do not use merge for append work.

Guardrails

  • Keep ordinary price details in Esse unless the user asks or they are needed to enforce the original budget. Give task-relevant progress and an honest final acceptance summary.
  • Retrieve, verify, or display only the exact results covered by the existing task authorization. Use returned handles and actual file paths; do not guess paths, copy unrelated completions, or treat acceptance as image completion. Input attachment materialization remains required.
  • Tell the user when selected local files will be sent to the chosen external Provider or the current Agent's image-generation service/model.
  • Never overwrite source images. Use the Esse-owned batch output and native Save As flow.
  • Never automatically resubmit an uncertain Provider request or one whose chargeState is unknown. A direct click on the retry button authorizes that exact retry. Definitely-not-charged failures may retry only within the original bounded retry authorization; there is no implicit retry allowance.
  • Preserve paths, image IDs, prompts, references, request keys and waiting deadlines exactly; never claim completion from queued/running state or background acceptance.
  • Never infer one target from a multi-image batch without a name or exact selection context.
  • Limit one batch creation, append, image-ID mutation, merge source list, and list_image_batches query to 50 items. Split larger work deliberately with distinct request keys.

Authorized continuation

Background acceptance means the request is durably saved, not that the image or the user's task has passed acceptance. A submit-only request may end after handoff. When the original user task or an active persistent Goal already authorizes tracking, image verification, or bounded rework, automatically query that task and read its actual results within the existing authorization; no new user message is required. A Goal or a tool response never grants additional spending or scope. Respect the client's actual Plan mode: plan and perform only plan-improving non-mutating exploration, not image generation or rework. Preserve the exact batch/job handles and the original waiting deadline across turns and restarts. Use get_image_batch for known handles; reconcile a missing response using list_image_batches with the exact requestKey, never by guessing from the newest batch. Missing or ambiguous receipts remain unresolved and do not authorize another submission. Poll no faster than polling.minIntervalMs, back off toward polling.maxIntervalMs, and stop waiting at the earlier of the original task deadline or polling.timeoutMs from the first handoff; do not reset the deadline on each query or continuation. Stop polling on terminal state, pause, or cancellation, and report unfinished acceptance honestly. Before accepting an image, read the actual file and check its pixels, dimensions, references, and requested parameters; queued/running status or HTTP 200 is insufficient. Rework must stay within the original model, references, targets, quantity, budget, and attempt limit, preserving prior versions. Track actual, estimated, and reserved image costs separately from any Goal token budget. If a price or charge is unknown and cannot be bounded by the existing budget, stop new paid work but allow authorized read-only verification. An uncertain submission or chargeState=unknown requires read-only reconciliation or retrieval of an existing task/checkpoint, never automatic resubmission. Definitely-not-charged failures do not grant retry authorization; use only the original bounded retry policy. Do not retrieve, display, or act on unrelated tasks.

Version History

  • 2453f89 Current 2026-10-18 18:59

    修复授权续传后的图像验证问题;对齐安装指南;增强重做工作的持久性及参考输入保留;修复批量移动和Tuzi图像协议。

  • 283ee14 2026-07-30 20:29

Same Skill Collection

plugins/codex/skills/batch-generate-images/SKILL.md

Metadata

Files
0
Version
2453f89
Hash
8043f590
Indexed
2026-07-30 20:29

Accueil - Wiki
Copyright © 2011-2026 iteam. Current version is 2.156.0. UTC+08:00, 2026-11-20 20:46
浙ICP备14020137号-1