CD ofox-image-core
Requires OFOX_API_KEY — create one at https://app.ofox.ai. Shared execution layer for the Ofox image API (api.ofox.ai) — validates parameters client-side, sends one synchronous request, base64-decodes the result, saves it to a file, and reports the real usage token counts and the computed dollar cost. Does both text-to-image (generate) and editing an existing image you supply as a local file (edit — change the background, recolour an element, alter a product photo, while leaving the rest of the picture intact). This is a library skill, not a standalone user-facing one — it is meant to be invoked by scenario skills that build model/prompt/size choices for a specific use case and then call into this skill's script rather than re-implementing the API calls — image-edit owns "change this image so that...", product-image owns a set of product images to choose between, and seedance-anime-drama owns character images for a video pipeline. Load this skill directly only when a user explicitly names the Ofox image API, asks to call it with specific low-level parameters, asks to debug a failed Ofox image request, or wants a plain "generate an image of..." from text — which is the one common case no scenario skill covers.
Requires OFOXAPIKEY — create one at https://app.ofox.ai. Shared execution layer for the Ofox image API (api.ofox.ai) — validates parameters client-side, sends…
As a process D 45/100 · Unfinished process — References files that are not bundled: ../ofox-video-core/references/approval-gate.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 · 2
✓ No critical or high findings
Medium and low: 2
✓ Guard found no suspicious behaviour. 2 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1228 chars, limit 1024 - warning
body-longSKILL.md body ≈ 12546 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../ofox-video-core/references/approval-gate.md - note
frontmatter-keyunknown frontmatter key "homepage" - note
edit-residuethe text marks something as outdated (lines 163): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 45/100
- 0Tools and files. 1 referenced file(s) missing: ../ofox-video-core/references/approval-gate.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 18 mutating operations with no state check
- 40Execution cost. Instruction body is 12546 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 100Steps. 41 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1228: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 22 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.