The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of external components from vendor-managed sources.
Installs the CLI tool using npx -y @mvanhorn/printing-press.
Downloads and builds Go binaries from github.com/mvanhorn/printing-press-library.
Installs an MCP server for interaction with Claude Code via go install.
[COMMAND_EXECUTION]: The skill executes local commands to drive the Product Hunt interface.
Invokes the producthunt-pp-cli binary with various subcommands to retrieve and analyze data.
Provides a sql subcommand for read-only querying of the local SQLite database used for caching.
Features a which command that uses natural language to resolve intent to specific CLI subcommands.
[PROMPT_INJECTION]: The skill processes untrusted external data, creating a potential surface for indirect prompt injection.
Ingestion points: Untrusted content including product taglines, descriptions, and user comments are ingested from the Product Hunt API via posts get, posts list, and posts comments (referenced in SKILL.md).
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are provided in the instructions for handling retrieved data.
Capability inventory: The skill has access to the Read Bash tool and can write output to local files or external URLs via the --deliver sink feature (referenced in SKILL.md).
Sanitization: The instructions do not specify any validation or sanitization of external data before it is presented to the agent.

pp-producthunt