The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple shell commands including git, but (GitButler), and no-mistakes to perform repository operations such as status checks, diffing, committing, and pushing.
Evidence: Commands found in references/procedure.md including git status, but commit, and no-mistakes axi run.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources (git diffs and logs) which is then used by the agent to analyze changes and generate commit messages.
Ingestion points: Step 1 in references/procedure.md uses git status, git diff, and git log to gather context.
Boundary markers: Absent; there are no specific instructions to ignore adversarial content embedded within the code changes or commit history.
Capability inventory: The skill has the ability to execute shell commands (git, but, no-mistakes).
Sanitization: Absent; the data from diffs is processed directly to determine change types and write descriptions.
[COMMAND_EXECUTION]: The skill interpolates user-supplied strings (the 'intent') directly into shell commands for the No Mistakes tool.
Evidence: no-mistakes axi run --intent "<what the user set out to accomplish>" in references/procedure.md.

do-commit