The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and templates. No executable scripts, network requests, or obfuscated patterns were found.
[NO_CODE]: There are no script files included with the skill; it relies on instructional guidance for the agent to use existing workspace tools like grep.
[PROMPT_INJECTION]: No evidence of prompt injection or bypass instructions was found. The skill handles external data via ingestion points such as specifications and change plans. It utilizes boundary markers like markdown tables and structured headers in the task template. Its capability inventory involves local code searching and command execution from a local file, and no sanitization issues were identified in the workflow.

write-rewrite