The Agent Skills Directory

[COMMAND_EXECUTION]: The skill detects project ecosystems (Node.js, Python, Rust, Go, Java, Ruby) and executes standard linting and testing commands such as npm lint:fix, ruff check --fix, cargo clippy, and go test based on the detected manifests.
[COMMAND_EXECUTION]: It performs dynamic execution of Node.js scripts (precommit-runner.js, review-state.js) which it locates within the local workspace or vendor-specific plugin directories (sd0x-dev-flow). This is used to orchestrate the pre-commit workflow.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data by reading manifest files and directory structures to determine execution logic.
Ingestion points: Reads files like package.json, pyproject.toml, and Cargo.toml using the Glob and Read tools.
Boundary markers: The skill does not explicitly use boundary markers for manifest data, but uses static command templates for execution.
Capability inventory: The skill has access to the Bash tool to execute a wide range of shell commands and ecosystem binaries.
Sanitization: The skill maps manifests to predefined command strings, limiting the ability of manifest content to directly inject arbitrary shell commands.

precommit-fast