The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The instructions explicitly direct the agent to inline private ingest keys (maple_sk_...) directly into the application's bootstrap source code for server-side services, while specifically advising against using environment variables or standard secret management practices.\n- [COMMAND_EXECUTION]: The skill requires the execution of shell commands to install dependencies via package managers (npm, pip, cargo, etc.), run application build and smoke tests, and configure environment-level MCP servers using the claude mcp add command.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes the user's entire repository, including third-party code and project-specific services, to determine instrumentation points. This large ingestion surface, combined with the agent's file-writing and shell-execution capabilities, creates a vulnerability to indirect prompt injection if the project files contain malicious instructions.\n- [EXTERNAL_DOWNLOADS]: The skill fetches supplemental instructional content from an external GitHub repository at https://github.com/MapleTechLabs/maple/tree/main/skills and installs various telemetry-related packages from public registries.

maple-onboard