The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, including project guidelines (CONTRIBUTING.md), issue templates, and existing issue trackers. This content could potentially contain instructions designed to manipulate the agent's behavior during the issue generation process.
Ingestion points: Reads files from repository root, docs/, and .github/ directories; fetches existing issues via gh issue list.
Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the data being processed.
Capability inventory: The skill uses bash and gh issue create to perform actions based on the processed data.
Sanitization: The skill includes a 'Verification Gate' and a mandatory 'User Approval Gate' requiring explicit human review of the full draft before submission, providing a critical check against malicious or incorrect output.
[COMMAND_EXECUTION]: The skill employs the gh (GitHub CLI) tool to perform repository searches, browse content, and create issues. These operations are essential to the skill's stated purpose of managing open-source contributions.
[EXTERNAL_DOWNLOADS]: The skill references and fetches guidelines from well-known technology organizations and research sources, including GitHub, Mozilla, Chromium, and the OpenSSF. These references are used to provide the agent with structured templates and best practices.

issue-writing