The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes system utilities such as coredumpctl, gdb, and the GitHub CLI (gh) to extract backtraces and manage issue reporting.
[DATA_EXFILTRATION]: Diagnostic data and bug reports are transmitted to the basecamp/omarchy repository. This is an official vendor resource corresponding to the skill's author, and the process requires explicit user confirmation of the report content.
[SAFE]: The skill handles process core dumps, which may contain sensitive data (passwords, tokens). It explicitly warns the user about this risk and employs secure practices, such as creating cores in temporary directories (mktemp) and ensuring their deletion via exit traps.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted output from external tools like gdb and gh search.
Ingestion points: External data is ingested from coredumpctl info, debugger output, and GitHub issue search results.
Boundary markers: The instructions do not specify delimiters to separate external data from agent instructions.
Capability inventory: The agent has the ability to write to external repositories using gh issue create and gh issue comment.
Sanitization: There is no automated sanitization of ingested tool output, though the skill mandates a human-in-the-loop review before any data is sent externally.

diagnose-crash