The Agent Skills Directory

Local Command Execution: The skill executes a Python module (python -m analysis.snapshot) to perform its analysis. This is a standard pattern for technical skills that rely on local scripts or binaries to process data and generate reports within the user's environment.
Data Ingestion Surface: The skill analyzes repository files and git history to identify code complexity and technical debt markers. This represents an indirect prompt injection surface as it processes external, potentially untrusted data.
Ingestion points: The skill reads files throughout the repository and parses git history as described in SKILL.md.
Boundary markers: No specific delimiters or "ignore instructions" prompts are defined in the instruction file to separate code content from analysis instructions.
Capability inventory: The skill uses shell commands via Python to perform analysis and writes the results to a local file (analysis-snapshot.json).
Sanitization: The instructions do not specify any sanitization or filtering of the source code content before analysis.

generate-snapshot