AB publish-preflight-studio
Check a post before it goes out, then fix what it finds. Paste the caption, title, script, on-screen text, or tags — this pre-publish content check reads the wording against advertising-copy restrictions and regulated-category claim rules and returns a replacement for every phrase it flags, reads the post back through the people you are writing for and names the exact line that loses each of them, scores the hook and the reason to share with the evidence behind each score, then hands back the corrected copy and renders the cover carrying the fixed wording. Use it as a social media copy check and a banned words checker before publishing, for ad-copy review, superlative screening, audience reaction testing, hook strength scoring, and pre-checking brand or client copy before it reaches an approver, for Instagram, TikTok, Facebook, YouTube, and LinkedIn.
Check a post before it goes out, then fix what it finds.
As a process B 68/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
How to improve
- 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: 16. 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 68/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 16 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2183 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 862: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -32 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.