The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to perform local analysis of the project.
Uses git ls-files and grep to identify file types and language distribution.
Uses recursive grep on the src/ directory to extract function, variable, and class declarations.
Scans openapi.yaml and openapi.json for API field names.
Executes git log to analyze naming patterns within the commit history.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the analysis of untrusted project data.
Ingestion points: Reads source code from the src/ directory, API definitions, and git commit history.
Boundary markers: None identified; the agent is instructed to scan the output of the grep/git commands directly.
Capability inventory: Uses shell commands (grep, git) to read and pipe data for analysis.
Sanitization: The skill does not explicitly sanitize or validate the content of the files or logs before the agent evaluates them against the naming rules.

find-clear-names