AF text-in-image
Generate images where the copy has to be exactly right: posters, packaging, ads, social graphics, UI mockups, menus, signage, infographics. Use when the user says "put the text X on it", "a poster that reads ...", "a label with the brand name", "make the headline say ...", "an ad with this tagline", or any design where a misspelled or paraphrased word is a failure. The thing most image models get wrong, so reach for this whenever exact lettering matters, even if the user just says "a poster" or "a label". For scalable vector output like a logo or SVG icon, use logos-and-vectors instead.
Generate images where the copy has to be exactly right: posters, packaging, ads, social graphics, UI mockups, menus, signage, infographics.
As a process F 52/100 · Will not run — References files that are not bundled: references/examples.md
How to improve
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/examples.md
Process rating: all ten parameters 52/100
- 0Tools and files. 1 referenced file(s) missing: references/examples.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 35 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2410 tokens
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 593: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.