AC carousel-writer
Use to write a carousel — a swipeable multi-slide post (Instagram carousel, LinkedIn document/PDF carousel, or TikTok photo carousel) — one of the highest-save, highest-dwell formats. Run when the user says "write a carousel," "carousel post," "slides for X," "LinkedIn document/PDF post," "swipe post," "turn this into a carousel," or wants multi-slide teaching or story content. Reads brand-profile and voice first; the cover slide hooks and promises the swipe (via hook-writer); each slide advances one idea and earns the next swipe; ends on a save-leaning CTA. Specifies the design direction and bundles an image-generation prompt pack (Nano Banana / Ideogram) for the slide visuals. Hands the caption to caption-writer and scheduling to scheduling-and-queue.
Use to write a carousel — a swipeable multi-slide post (Instagram carousel, LinkedIn document/PDF carousel, or TikTok photo carousel) — one of the…
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 34 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1432 tokens
- low 12 top-level sections: this looks like several domains in one skill
- medium 8 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 763: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 34 items
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.