The Agent Skills Directory

[DYNAMIC_CONTEXT_INJECTION]: The skill uses dynamic context syntax (!command) in SKILL.md to execute shell commands automatically when the skill is loaded. These commands (git status, git branch --show-current, gh issue list, and gh auth status) are used to populate the agent's context with real-time repository metadata.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the repository that may be controlled by external actors, creating a surface for indirect prompt injection.
Ingestion points: The skill reads repository-specific data including existing issue lists (SKILL.md), contributing guidelines such as CONTRIBUTING.md, and issue templates from the .github/ISSUE_TEMPLATE/ directory (references/repository-templates.md).
Boundary markers: The skill does not define clear delimiters or use specific instructions to prevent the agent from following directions potentially embedded within the ingested repository files.
Capability inventory: The skill has the capability to modify the repository environment by creating labels (gh label create) and issues (gh issue create), and it initiates an autonomous pull request creation and review cycle.
Sanitization: There is no evidence of sanitization or text filtering for content retrieved from the repository files before it is used to influence the agent's output.
[COMMAND_EXECUTION]: The skill instructions direct the agent to execute various shell commands to manage the repository and validate code quality.
Repository Management: Uses the gh CLI to interact with GitHub for label and issue management in references/decision-logic.md.
Validation Workflow: Instructs the agent to execute build scripts and test suites (e.g., npm test, pnpm build, pytest) as part of its TDD requirements in references/quality-validation.md.

create-issues