The Agent Skills Directory

[SAFE]: The skill defines a set of idiomatic patterns for Go CLI development, utilizing well-established and trusted community libraries such as Cobra and Viper for command and configuration management.\n- [METADATA_POISONING]: The skill metadata identifies the author as 'samber', which differs from the 'marcioaltoe' author context provided. However, the skill correctly references the official 'samber' public GitHub repository for its homepage and related skill links, suggesting the metadata is consistent with the skill's source.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to perform code reviews and extensions, which involves processing untrusted source code as part of its 'Review' and 'Extend' modes.\n
Ingestion points: Existing project source files processed in 'Review' and 'Extend' modes.\n
Boundary markers: Absent; the skill does not specify delimiters or instructions for the agent to distinguish between its own logic and the content of analyzed files.\n
Capability inventory: The skill utilizes Bash(go:*), Write, and Edit tools to perform its tasks.\n
Sanitization: No specific sanitization or filtering of input source code content is defined, relying on the agent's default safety guardrails.

golang-cli