AC caption-writer
Use to write platform-native social media captions (post copy) in the brand's voice — the words that accompany a post on Instagram, LinkedIn, TikTok, Facebook, X/Twitter, Threads, Pinterest, YouTube, or Bluesky. Run when the user says "write a caption," "caption this," "post copy," "write the copy for this photo/video/Reel," "IG caption," "what should I write for this post," or needs the words to go with a visual. Reads brand-profile and voice first so captions sound like the brand, not generic AI. For long-form LinkedIn thought-leadership posts use linkedin-post-writer; for X/Threads multi-post threads use thread-writer; for video scripts use the video skills. This skill writes the caption itself.
Use to write platform-native social media captions (post copy) in the brand's voice — the words that accompany a post on Instagram, LinkedIn, TikTok…
As a process C 59/100 · 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 59/100
- 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
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 31 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1528 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 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 707: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 31 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.