The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the adhere lint command and repository-specific tests/type-checking commands to identify, verify, and resolve code violations.
[EXTERNAL_DOWNLOADS]: The skill references rule definitions and documentation located in the official darkmatter GitHub repository and the @drkmttr/adhere package directory.
[INDIRECT_PROMPT_INJECTION]: The skill ingests findings from the adhere lint tool, which are generated by an external AI model. Ingestion points: Findings reported by adhere lint in SKILL.md. Boundary markers: Includes instructions to verify findings before fixing and to only fix 'real' violations in SKILL.md. Capability inventory: Execution of shell commands (adhere, tests), file system writes, and environment variable checks in SKILL.md. Sanitization: Relies on the agent's verification process rather than programmatic sanitization.

adhere-fix