The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill performs remote code execution by cloning the gsd-build/get-shit-done repository and executing the bin/install.js script with node. It also utilizes npx -y get-shit-done-cc@latest to download and run code directly from the npm registry.
[EXTERNAL_DOWNLOADS]: The skill fetches software and dependencies from external sources, including github.com and the Python Package Index (PyPI) for the graphifyy package.
[COMMAND_EXECUTION]: Several shell commands are executed to manage the environment, including pip install for Python packages, npm install for Node.js modules, and various filesystem operations using find and sed.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted documentation from the repository to seed project planning files.
Ingestion points: Reads content from README.md, AGENTS.md, and docs/current-state.md to establish project context.
Boundary markers: None. The skill does not use delimiters or instructions to ignore embedded commands in the source files.
Capability inventory: The skill has the ability to write to the filesystem, install packages, and execute shell scripts.
Sanitization: No sanitization or validation is applied to the repository content before it is used to generate the .planning/ directory structure.

gsd-graphify-brownfield-bootstrap