vantage-monitor — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited vantage-monitor (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.
Competitive facts decay. This skill stands up a repeatable watch over the set, captures a baseline, and on each run reports only what changed and what to do about it — so the landscape report and battlecards never go stale.
Web-only. Brief format = template E in ../vantage/references/deliverable-templates.md.
| Signal | Source | Why it matters |
|---|---|---|
| Pricing & packaging | /pricing (+ Wayback diff) | Price moves = strategy shifts; battlecard-critical |
| Homepage hero / positioning | Homepage H1+subhead | Repositioning = vulnerability or new threat |
| New ad campaigns | Meta Ad Library, Google ATC | New offers/angles to counter or swipe |
| New content / launches | /blog, /changelog, /news, sitemap lastmod | Product & content momentum |
| Reviews & sentiment | G2/Capterra/Trustpilot counts + recent text | Emerging strengths/complaints for battlecards |
| Funding / M&A / news | WebSearch <brand> news | Resourcing, threat level, market moves |
| Social cadence shifts | Profile activity | Channel strategy changes |
+ capture date into a COMPETITIVE-WATCH-BASELINE.md (or update the existing landscape report's Evidence Log).
the Wayback Machine to confirm when a change happened where the live page hides it.
on which channel, the source, and the recommended response. No-change items get a one-line "no material change" — don't pad.
map as action-required.
This skill defines what to check. To actually run it on a cadence, use the harness's scheduling — don't reinvent it:
reports deltas. Best for hands-off, runs-without-you monitoring.
while.
Recommend a cadence by volatility: weekly for active markets / live deals, monthly for stable categories, ad-hoc before a launch or big pitch. Suggest the specific command, e.g. "Want me to `/schedule` this competitive watch weekly on Mondays?" — and only offer if there's a real ongoing need.
# Competitive Watch — [date] (since [last date])
## Material changes
| Competitor | What changed | Channel | Source | When (Wayback) | So what |
|-----------|--------------|---------|--------|----------------|---------|
## Action required (invalidates a battlecard / map)
- …
## New entrants / exits
- …
## No material change
- [competitors with nothing notable]
## Recommended responses
1. …~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.