← Registry
Trust Report

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

94
CONDITIONAL
Format: openclawScanner: v0.1.0Duration: 3msScanned: 2026-02-07Source →
Embed this badge
AgentVerus CONDITIONAL 94AgentVerus CONDITIONAL 94AgentVerus CONDITIONAL 94
[![AgentVerus](https://agentverus.ai/api/v1/skill/1bf4059d-95a7-4cec-bd72-47983735fb78/badge)](https://agentverus.ai/skill/1bf4059d-95a7-4cec-bd72-47983735fb78)

Category Scores

100
Permissions
100
Injection
95
Dependencies
80
Behavioral
80
Content

Findings (3)

highSystem modification detected-20

Found system modification pattern: "npm install"

> Project uses pnpm workspaces. Attempted `npm install` but failed.

Skills should not modify system configuration or install packages. Bundle required dependencies.

behavioralASST-03
lowUnknown external reference-5

The skill references an unknown external domain which is classified as low risk.

https://agentskills.io/specification

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
lowNo explicit safety boundaries

The skill does not include explicit safety boundaries defining what it should NOT do.

No safety boundary patterns found

Add a 'Safety Boundaries' section listing what the skill must NOT do (e.g., no file deletion, no network access beyond needed APIs).

contentASST-09