ig-caption-writer — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ig-caption-writer (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A caption isn't decoration. It's the second hook.
[Hook line — 5-9 words, scroll-stopper]
[blank]
[Body — 1-3 short lines, plain English, no fluff]
[blank]
[CTA — one ask, never two]
[blank]
[Hashtags — 8-15, mixed reach tiers]| Pattern | Example |
|---|---|
| Specific number | "I made ₹4,300 in 14 minutes." |
| Contrarian | "Everyone says learn React. They're wrong." |
| Confession | "I lost my first ₹10k in options. Here's the lesson." |
| Question with stakes | "Would you pay ₹999 for this AI tool?" |
| Open loop | "The one BGMI setting nobody uses." |
Skip: "Check this out", "Watch till the end", "You won't believe".
One only. Pick by goal:
Avoid banned hashtags — check periodically.
HOOK: <one line>
BODY:
<2-3 lines>
CTA: <one line>
HASHTAGS:
#small1 #small2 #small3 #small4 #mid1 #mid2 #mid3 #large1~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.