---
name: adobe-core-workflow-a
description: >-
  Run a current Adobe Firefly image generation job with prompt approval, response-led polling, artifact custody, and cancellation. Use for approved creative automation. Use when the task requires firefly controlled async generation. Trigger with "generate with Firefly", "Firefly async job", or "Adobe image generation".
allowed-tools: Read,Glob,Grep,Write,Edit
argument-hint: "<approved-prompt> <model-operation> <output-destination>"
version: 1.8.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags: [ saas, adobe, firefly ]
model: inherit
effort: high
compatibility: "Designed for Claude Code; live Adobe actions require network access, appropriate entitlement and authentication, and explicit approval"
title: adobe-core-workflow-a
canonical_url: https://skilld.dev/gh/jeremylongshore/tons-of-skills-marketplace/adobe-core-workflow-a
last_updated: 2026-10-07T06:06:28.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [references/official-docs.md](https://skilld.dev/api/skills-raw/jeremylongshore/tons-of-skills-marketplace/adobe-core-workflow-a/references/official-docs.md).
>
> If the user asked to install this Skill, run `npx skilld install jeremylongshore/tons-of-skills-marketplace/adobe-core-workflow-a`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/adobe-core-workflow-a`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/jeremylongshore/tons-of-skills-marketplace/adobe-core-workflow-a) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/adobe-core-workflow-a`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/adobe-core-workflow-a --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/adobe-core-workflow-a --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Firefly Controlled Async Generation

## Overview

Run a current Adobe Firefly image generation job with prompt approval, response-led polling, artifact custody, and cancellation. This workflow produces a reviewable artifact and evidence before any live side effect.

## Prerequisites

- Current first-party Adobe documentation for every selected service, API version, auth flow, limit, and lifecycle.
- Named product, identity, security, data, budget, release, and operations owners appropriate to the scope.
- Synthetic or approved non-production fixtures with secret and content canaries.

## Current Contract

Current Firefly asynchronous operations return jobId, statusUrl, and cancelUrl. Follow those returned URLs rather than inventing a jobs route. Model/API versions and supported input-storage domains are mutable; recheck usage notes for the selected operation. Recheck the dated evidence map before relying on mutable product behavior.

## Authentication

Acquire OAuth Server-to-Server credentials only after enterprise entitlement and product assignment are proven. Send x-api-key and bearer headers server-side; never expose them to a browser or job record.

## Instructions

1. Record the approved business purpose, prompt, model/operation, dimensions, quantity, budget, and content owner.
2. Read the current API and usage notes; validate endpoint version, request schema, supported signed-URL hosts, and content rules.
3. Create a redacted idempotency record and submit one bounded asynchronous job.
4. Persist jobId plus returned statusUrl and cancelUrl, then poll with jitter and strict elapsed-time limits.
5. On success, validate media type and size, transfer the artifact to approved storage, and preserve provenance/content-credential metadata.
6. On failure or timeout, classify the vendor response, cancel when approved, reconcile spend, and expire temporary access.

## Tool Discipline

Use Read, Glob, and Grep to inspect current documentation, configuration, code, fixtures, and evidence. Use Write and Edit only for approved repository artifacts. Skill invocation alone does not authorize network access, credentials, Adobe content, consent, uploads, generation, spend, deployment, registration changes, replay, cancellation, or deletion.

## Approval Boundaries

Require creative and budget approval before submission. External storage, personal/regulated content, bulk generation, cancellation, publication, and deletion each require the named owner.

## Error Handling

- Never retry a policy or validation rejection by silently rewriting the prompt.
- After ambiguous submission, reconcile by idempotency evidence before resubmitting.
- Stop if a returned URL leaves the documented allowlist or includes a secret in logs.

## Output

Return prompt and policy receipt, version/operation evidence, job ledger, polling history, artifact hash/location, provenance, spend class, and cleanup. Mark assumptions, observed environment behavior, owners, evidence dates, and unresolved gaps explicitly.

## Examples

- Complete a synthetic async job by following returned URLs.
- Cancel a sandbox job after the polling budget expires.

## Validation

Exercise and record expected and observed results for:

- success
- policy rejection
- 429
- unknown status
- timeout/cancel
- artifact validation

## Resources

- [Current first-party evidence map](https://skilld.dev/api/skills-raw/jeremylongshore/tons-of-skills-marketplace/adobe-core-workflow-a/references/official-docs.md) — recheck dated Adobe sources before execution.
- Treat observed tenant or product behavior as environment-specific evidence, never a universal Adobe guarantee.
