The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill identifies modernization opportunities by reading project files via Read, Glob, and Grep tools. This ingested content is used to generate code modifications through Edit and Write. The instructions do not define delimiters or specific safety warnings to prevent the agent from being influenced by potentially malicious strings or instructions embedded in comments within the analyzed source code.
Ingestion points: Codebase files accessed via Read, Glob, and Grep tools during scanning.
Boundary markers: No explicit markers or "ignore embedded instructions" warnings are defined for the project data.
Capability inventory: Edit, Write, Bash (scoped to go/git/lint), Agent, and EnterWorktree permissions are granted to perform and apply refactoring changes.
Sanitization: No specific sanitization, escaping, or filtering logic is defined for the interpolated code content before processing.
[EXTERNAL_DOWNLOADS]: The skill fetches Go release documentation and changelogs from official sources at go.dev to verify version constraints and feature availability. It also references established developer tools such as golangci-lint and govulncheck to enhance its analysis capabilities.
[COMMAND_EXECUTION]: Utilizes Bash commands restricted to go:*, git:*, and golangci-lint:* to execute builds, check tool versions, manage dependencies, and isolate refactoring changes within git worktrees for safe review.

golang-modernize