The Agent Skills Directory

[COMMAND_EXECUTION]: Executes bundled Python scripts including scripts/ad-budget-pacer.py, scripts/budget-optimizer.py, and scripts/performance-monitor.py to calculate budget pacing, generate optimization recommendations, and persist historical snapshots. These operations are core to the skill's intended analytical functionality.
[EXTERNAL_DOWNLOADS]: Fetches real-time marketing spend and efficiency metrics from well-known advertising services such as Google Ads, Meta Marketing, LinkedIn Marketing, and TikTok Ads. These network operations are necessary for tracking actual expenditure against defined targets.
[DATA_EXFILTRATION]: Reads brand-specific configuration files, budget targets, and marketing SOPs from the local ~/.claude-marketing/ directory. This data access is used to contextualize the analysis within the user's specific business environment.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by ingesting data from external advertising platforms and local configuration files.
Ingestion points: External ad platform APIs (Google, Meta, LinkedIn, TikTok) and local brand JSON profiles.
Boundary markers: None specified in the instructions to delimit external data from agent instructions.
Capability inventory: Execution of local Python scripts for data modeling, optimization, and snapshot persistence.
Sanitization: No explicit sanitization or validation of the external platform data is described prior to processing.

budget-tracker