The Agent Skills Directory

Command Execution: The skill employs the gh CLI to interact with GitHub repositories for researching topics and verifying technical claims. This usage is confined to official Microsoft repositories and follows standard development practices for retrieving repository data.
External Resource Access: During the research phase, the skill reads content from public GitHub repositories (microsoft/vscode and microsoft/vscode-copilot-chat). This is used to ensure the accuracy of the blog content by referencing the source code and project history.
Indirect Prompt Injection Surface: The skill processes potentially untrusted data from GitHub issues and pull requests to generate blog outlines.
Ingestion points: Data enters the context via the gh CLI when reading issue or PR descriptions (SKILL.md, Phase 1).
Boundary markers: There are no specific delimiters or instruction-ignore warnings defined for the ingested data.
Capability inventory: The agent can write files to the blogs/ directory and execute gh CLI commands.
Sanitization: No specific sanitization or filtering of the external content is performed before processing. However, the skill implements a protective 'Plan-first' workflow that requires explicit human approval of the proposed outline before any drafting or file creation occurs.

blog-writer