asc-metrics — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited asc-metrics (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.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.
You analyze the user's official App Store Connect data synced into Appalize — exact downloads, revenue, IAP, subscriptions, and trials. This is first-party data, not estimates.
If ASC is not connected, prompt the user to connect it at www.appalize.com/settings and return.
app-marketing-context.md — read it for app contextGET /v1/connect/metrics/appsMatch the user's app to an app_apple_id if not already known.
GET /v1/connect/metrics?from=YYYY-MM-DD&to=YYYY-MM-DDGET /v1/connect/metrics/apps/:appId?from=YYYY-MM-DD&to=YYYY-MM-DDResponse includes: daily[], countries[], totals.
See full API reference: appalize-connect.md
Fetch two equal-length windows and compare:
| Metric | Prior Period | Current Period | Change |
|---|---|---|---|
| Downloads | [N] | [N] | [+/-X%] |
| Revenue | $[N] | $[N] | [+/-X%] |
| Subscriptions | [N] | [N] | [+/-X%] |
| Trials | [N] | [N] | [+/-X%] |
| Trial → Sub Rate | [X]% | [X]% | [+/-X pp] |
What to look for:
From daily[], identify:
Sort countries[] by downloads and revenue:
Compute from the data:
| Metric | Formula | Benchmark |
|---|---|---|
| ARPD | Revenue / Downloads | > $0.05 good; > $0.20 excellent |
| Trial rate | Trials / Downloads | > 20% means strong paywall reach |
| Sub conversion | Subscriptions / Trials | > 25% is strong |
| Revenue per sub | Revenue / Subscriptions | Depends on pricing |
📊 [App Name] — [Period]
Downloads: [N] ([+/-X%] vs prior period)
Revenue: $[N] ([+/-X%])
Subscriptions: [N] ([+/-X%])
Trials: [N] ([+/-X%])
IAP Count: [N] ([+/-X%])
Trial→Sub: [X]%
Top Markets (downloads):
1. [Country] — [N] downloads, $[N]
2. [Country] — [N] downloads, $[N]
3. [Country] — [N] downloads, $[N]
Key Observations:
- [What the trend means]
- [Any anomaly and likely cause]
- [Opportunity identified]
Recommended Actions:
1. [Specific action based on data]
2. [Specific action based on data]When a significant change (>20%) is detected, flag it:
⚠️ Downloads dropped [X]% this week
Possible causes: [list 2-3 hypotheses]
Next steps: [specific diagnostic actions]"Why did my downloads drop?"
keyword-research skill)competitor-analysis skill)"Which countries should I localize for?" Pull country breakdown → sort by downloads → flag high-download, non-English markets → use localization skill
"Is my monetization improving?" Compare trial rate and trial→sub rate period over period → use monetization-strategy skill for paywall improvements
app-analytics — Full analytics stack setup and KPI frameworkmonetization-strategy — Improve subscription conversion and paywallretention-optimization — Reduce churn using the metrics as inputlocalization — Expand top-performing markets seen in country dataua-campaign — Validate whether paid installs show in downloads spike~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.