The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates extensive command-line operations across various roles. The System Analyzer specialist utilizes kubectl, psql, docker, and argocd for live environment investigation and triage. The Developer and QA agents leverage Bash to execute builds and run test suites.
[EXTERNAL_DOWNLOADS]: During the bootstrapping of the E2E testing framework, the skill automates the installation of standard Node.js development dependencies (including playwright, jest, and typescript) from the public npm registry.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its orchestration logic.
Ingestion points: The orchestrator reads untrusted local project files, such as CLAUDE.md, AGENTS.md, and CONTRIBUTING.md, to extract project conventions.
Boundary markers: There are no explicit boundary markers or instructions used to delimit this external content from the system prompts provided to specialist agents.
Capability inventory: Specialist agents (Developer, System Analyzer, QA) possess powerful capabilities, including the Bash, Edit, and Write tools, which could be misused if influenced by malicious content in project documentation.
Sanitization: The skill performs no sanitization or validation of the content read from local files before interpolating it into agent prompts.

neo-team-copilot