self-improving-question-system-for-better-results
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is an instruction-only prompt-improvement skill that may ask clarifying questions before answering, with no code, credentials, installation steps, or data access shown.
Install only if you want an assistant behavior that critiques and improves vague prompts before answering. It does not show code execution or data access, but it may ask follow-up questions instead of answering immediately.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The assistant may delay a direct answer and ask for more details first.
The skill intentionally changes the response flow by asking clarifying questions before answering when it judges the prompt underspecified. This is disclosed and aligned with the prompt-improvement purpose.
Quality Failed → Enter "Enhancement Mode" → List Clarification Points → User Input ... Loop Until Passed or User Confirms "Proceed Anyway"
Use this skill when you want prompt refinement; if you want an immediate answer, say "PROCEED ANYWAY" or provide enough context up front.