The Agent Skills Directory

[DATA_EXFILTRATION]: The skill provides instructions for managing a sensitive FIGMA_ACCESS_TOKEN. It adheres to security best practices by explicitly warning against hardcoding the token and recommending the use of environment variables or Docker secrets.
[EXTERNAL_DOWNLOADS]: The skill references the author's repository at https://github.com/sarveshsea/memi as the source for tool functionality. This resource belongs to the skill's author and is documented neutrally.
[COMMAND_EXECUTION]: The skill details the use of standard container commands, such as docker compose and npm ci, for managing dependencies and running design system tasks in isolated environments.
[DATA_EXFILTRATION]: The skill describes a surface for processing local project configuration files to adapt its behavior. 1. Ingestion points: Detects and reads Dockerfile, docker-compose.yml, and .devcontainer/ files from the project root. 2. Boundary markers: No explicit boundary markers or 'ignore' instructions are specified in the guide for these files. 3. Capability inventory: The tool possesses capabilities for code generation, spec validation, and network synchronization. 4. Sanitization: No explicit sanitization or validation of the ingested Docker configuration files is described in this configuration guide.

docker-environments