The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the paperclipai CLI tool to fetch data and standard Node.js package managers (npm, npx) to configure and manage the Paperclip environment.
[EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing the paperclipai CLI and the @bbengamin/paperclip-mcp-server package from the NPM registry. These resources are provided by the skill author for legitimate organizational orchestration.
[DATA_EXFILTRATION]: The skill accesses organizational data, including goals, projects, and issues. It also references local authentication credentials stored in ~/.paperclip/auth.json. The instructions include explicit best practices to avoid printing authentication tokens or sensitive credentials to logs or chat interfaces.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and processes data from external sources, such as issue descriptions and goal titles.
Ingestion points: Data enters the context through paperclipai issue list --json and paperclipai goal list --json in SKILL.md.
Boundary markers: The skill output is formatted as plain text in chat and does not utilize specific delimiters to isolate potentially malicious text within issues.
Capability inventory: The agent possesses shell execution capabilities for the Paperclip CLI and network access to the platform's API.
Sanitization: No specific filtering or sanitization logic is described for the retrieved task data before it is formatted into the final Focus Card.

paperclip-daily-focus