The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends installing the pbi-search CLI tool from the vendor's official GitHub repository using cargo install or by downloading binaries from the repository's releases page. This is a standard installation method for the tool as provided by the author.
[COMMAND_EXECUTION]: The skill instructs the agent to use the pbi-search CLI to execute search and fetch operations against multiple documentation repositories.
[DATA_EXFILTRATION]: The skill includes scripts and guidance for reading and validating Tabular Editor configuration files, such as Preferences.json and .tmuo files. These files are known to contain sensitive connection strings and potentially credentials (encrypted or plain-text). The skill implements security controls by warning the user against committing these files to version control, recommending the use of .gitignore, and including validation logic that alerts users if plain-text credentials are detected.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it fetches and processes content from external documentation sources.
Ingestion points: External data enters the context through pbi-search search and pbi-search fetch commands targeting various documentation domains.
Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded within the fetched documentation content.
Capability inventory: The agent has the capability to execute shell commands via the CLI tool and run Python validation scripts.
Sanitization: The skill relies on the CLI tool to return cleaned markdown, which provides some filtering of raw HTML/external content.

te-docs