The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources that may contain embedded instructions.
Ingestion points: Resolves stubs and proposal issue references (#N) to populate skill content.
Boundary markers: None mentioned; the instructions do not require the use of delimiters for external content.
Capability inventory: Shell access for file operations, version control, and tool execution via grep, git, and npx.
Sanitization: Absent; there are no instructions to validate or sanitize the data retrieved from issues or stubs.
[COMMAND_EXECUTION]: The skill provides the agent with instructions to execute various shell commands including grep, sort, git, and npx for repository management and ID verification.
[EXTERNAL_DOWNLOADS]: The skill contains an installation snippet that fetches resources from the GitHub repository https://github.com/peter-tu-zynkr/zynkr-skill-builder.
[DYNAMIC_EXECUTION]: The skill executes a local script scripts/validate-skill.ts using npx tsx to perform quality checks on the authored content.

skill-author