The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes Python scripts (video_rank.py, video_detail.py) to handle communication with the Nexscope API proxy. These scripts are self-contained, use standard Python libraries (urllib, json, os), and are designed to facilitate data discovery and detailed analysis within the agent's environment.
[EXTERNAL_DOWNLOADS]: The skill connects to the vendor's proxy infrastructure (NEXSCOPE_PROXY_BASE) to retrieve TikTok video metrics. This external communication is the core functionality of the skill and is documented as a research tool interfacing with the Kalodata data source.
[DATA_EXPOSURE]: The skill implements a local storage mechanism that writes API responses to a nexscope/ directory within the current project. This allows users to access raw research data and is a documented behavior intended for offline analysis and context window optimization.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for external data via API responses.
Ingestion points: Data enters the context through API responses processed by video_rank.py and video_detail.py.
Boundary markers: Results are presented in structured tables or profiles, separating external data from agent instructions.
Capability inventory: The skill's scripts are restricted to HTTP communication, local file writing, and JSON processing; no dangerous execution capabilities (like eval or generic subprocess calls) are exposed.
Sanitization: Structural validation is provided through standard JSON parsing.
[SAFE]: The skill follows security best practices by recommending the use of environment variables for API key management and provides clear user guidance on credit usage and data provenance.

ecommerce.tiktok-video-analytics