The Agent Skills Directory

[SAFE]: The skill is composed entirely of markdown documentation and reference files. It contains no scripts, binaries, or automated shell commands that could perform malicious actions.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external artifacts such as logs, traces, and bug reports. While processing untrusted data is a potential injection surface, the skill's core methodology—emphasizing evidence-based verification, minimal instrumentation, and hypothesis testing—serves as a procedural safeguard against obeying instructions embedded in that data.\n- [EXTERNAL_DOWNLOADS]: The NOTICE.md file contains a plain-text reference to a GitHub repository (github.com/cfircoo/claude-code-toolkit) for licensing and attribution purposes. There are no instructions for the agent to download or execute content from this or any other external source.

z-systematic-debugging