DD image-edit
Requires OFOX_API_KEY — create one at https://app.ofox.ai. Change one thing in an image you already have and leave the rest of the picture alone — swap the background, recolour a part, remove or add an object, clean up a photo — from a local jpeg/png/webp file. Delegates to ofox-image-core's `edit` subcommand (POST /v1/images/edits, one synchronous request), prices the job with --dry-run before spending, and reports the real token cost including the uploaded picture, which is billed. Use when a user hands over an image and asks for a change to it, e.g. "change the background of this photo to a beach and keep the person unchanged", "make this button green", "remove the car in the background", or "put this product on a plain white background". Do not use to draw a new image from a text description with no input picture (that is ofox-image-core's `generate`), to produce a set of several images to choose between (see product-image), or to turn a photo into video (see seedance-product-video or seedance-ad-creative). Editing the content of an existing video — "change the background of my clip, keep the product" — has no route here and none in the video API either (measured; the mode field an edit would use is accepted and silently ignored, so nothing errors); this skill edits a single still, and routing such a request to a video skill generates brand-new footage instead of changing theirs.
Requires OFOXAPIKEY — create one at https://app.ofox.ai. Change one thing in an image you already have and leave the rest of the picture alone — swap the…
As a process D 47/100 · Unfinished process — References files that are not bundled: ../ofox-image-core/SKILL.md, ../product-image/SKILL.md, ../ofox-video-core/references/creative-brief.md
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1406 chars, limit 1024 - warning
body-longSKILL.md body ≈ 10382 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../ofox-image-core/SKILL.md - warning
missing-refreference to a missing file: ../product-image/SKILL.md - warning
missing-refreference to a missing file: ../ofox-video-core/references/creative-brief.md - warning
missing-refreference to a missing file: ../ofox-video-core/references/approval-gate.md - warning
missing-refreference to a missing file: ../seedance-product-video/SKILL.md - warning
missing-refreference to a missing file: ../video-extend-edit/SKILL.md - warning
missing-refreference to a missing file: ../seedance-ad-creative/SKILL.md - warning
missing-refreference to a missing file: ../seedance-anime-drama/SKILL.md - warning
missing-refreference to a missing file: ../hal-image/SKILL.md - warning
missing-refreference to a missing file: references/*.md - warning
missing-refreference to a missing file: references/api-params.md - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 47/100
- 0Tools and files. 11 referenced file(s) missing: ../ofox-image-core/SKILL.md, ../product-image/SKILL.md, ../ofox-video-core/references/creative-brief.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 10382 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 100Steps. 28 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +3Description length 1406: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 25 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (13 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 39.