The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes npx tsx scripts/validate-skill.ts to perform linting and structure checks on SKILL.md files. It also uses git fetch to retrieve content from specified branches.
[EXTERNAL_DOWNLOADS]: The skill's installation instructions utilize npx skills add to download the skill builder from the author's repository at https://github.com/peter-tu-zynkr/zynkr-skill-builder.
[DYNAMIC_EXECUTION]: The skill uses tsx to execute a local TypeScript script (validate-skill.ts) for processing skill files. This is a core component of the skill's validation logic.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes content from external SKILL.md files (paths, slugs, or branches).
Ingestion points: Reads SKILL.md files from the local filesystem or fetched git branches.
Boundary markers: Boundary markers are absent in the prompt instructions.
Capability inventory: File system reads, file system writes (for auto-fixes with confirmation), and git fetch operations.
Sanitization: The skill relies on an external TypeScript engine (validate-skill.ts) to parse and validate content rather than direct LLM interpretation of raw file text.

skill-qa