Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Calculates a composite trust score for skills and agents by combining time elapsed since last verification with the rate of change in permissions, dependencies, and behavior. Produces a single trust velocity score and projects when trust falls below configurable thresholds. Outputs re-verification urgency ratings ranging from CURRENT to REVERIFY NOW.
Binary verified/unverified models ignore post-verification changes, so a skill with an old badge and 14 recent updates is treated the same as one that hasn't changed — trust velocity makes that difference quantitative.
When to use it
- Checking whether a frequently updated skill still warrants its original trust rating
- Prioritizing which skills need re-audit before a production deployment
- Detecting sudden spikes in update velocity that signal elevated risk
- Comparing relative trustworthiness of two skills before integrating either
- Setting automated re-verification triggers when change velocity exceeds a threshold
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Calculate trust velocity for workflow-optimizer, last verified 213 days ago with 14 updates since verification
- 1Accepts skill identifier, last verification date, and update history as input
- 2Applies exponential time decay curve to compute raw time factor (0.74 at 213 days)
- 3Calculates change velocity ratio by comparing actual update rate to historical baseline (4.7 updates/month vs 0.8 historical)
- 4Computes change velocity penalty from permission expansions, new endpoints, dependency bumps, and instruction drift
- 5Combines all factors into a composite score and generates 30/60/90-day projections with a re-verification urgency rating
Trust velocity report: 43/100 composite score, 62% of surface area outside last audit coverage, threshold already breached 41 days ago, urgency REVERIFY NOW